Backdoor Attacks

Follow this topic Ask about this topic

Momentum

6 papers in the last four weeks, down 14% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 87

Oct 7, 2026cs.SD

Backdooring Acoustic Foundation Models for Physically Realizable Triggers

Acoustic foundation models (AFMs) have democratized acoustic applications, enabling powerful models for tasks ranging from speech recognition to speaker verification with minimal resources. However, the security of applications based on AFMs remains largely underexplored. Our work addresses this gap by proposing the Foundation Acoustic model Backdoor (FAB) attack, demonstrating that state-of-the-art AFMs are susceptible to backdooring under practical settings. Despite making minimal assumptions about adversary capabilities (e.g., no access to pre-training data), we show that FAB preserves benign performance while inducing backdoors that survive fine-tuning and cause significant degradation across diverse downstream tasks when activated. Notably, FAB utilizes task-agnostic, physically realizable, inconspicuous, and sync-free triggers (e.g., a background siren). We evaluate FAB using two leading AFMs, nine downstream tasks, and four different triggers. We further demonstrate its effectiveness against established defenses and across both digital and physical domains. While extensive end-to-end fine-tuning can mitigate FAB, such a defense is resource-intensive and task-specific. Our work highlights critical risks to AFMs and calls for advanced defenses.

Zebin Yun, Eyal Ronen, Mahmood Sharif

Tel Aviv University, Tel Aviv, Israel

Backdoor Attacks Adversarial Attacks Speech Foundation Models

Oct 6, 2026cs.CR

The Model Plants the Trigger: Answer-Side Backdoor Attacks in Multi-Turn Large Language Models

Safety alignment in Large Language Models (LLMs) remains vulnerable to backdoor attacks. Existing LLM backdoors are almost all input-centric: activation depends on explicit trigger patterns in the user input, so modern guardrails are built to sanitize the input space. We challenge this assumption with a novel answer-side backdoor for multi-turn dialogue. Instead of inserting the trigger into the input, the adversary uses a benign first-turn prompt to naturally induce the model to generate a specific, seemingly innocuous word. Once merged into the dialogue history, this self-generated word becomes the trigger. When a later harmful query arrives, the model detects its own trigger and bypasses its safety refusal, while the user input stays perfectly clean. Across four LLMs, our attack reaches near-perfect Attack Success Rates, approaching 100% at only a 5% poisoning rate, while preserving general utility and clean-input safety, and it evades mainstream input-centric defenses. Representation-level analysis shows that the self-generated trigger consistently suppresses the model's refusal signal, exposing a critical blind spot in current LLM defenses.

Yibo Zhang, Tianrong Guan, Liang Lin +3

Queen Mary University of London, UK · Squirrel AI Learning, USA

LLM Backdoor Attacks Backdoor Attacks LLM Safety Alignment LLM Security

Oct 5, 2026cs.AI

Topology-Conditioned Backdoors: Language Models That Insert Vulnerabilities When They Infer They Are in a Multi-Agent System

A language model may behave safely in a single-agent evaluation yet produce vulnerable code when its context suggests that it is part of a multi-agent system. We study this failure mode by fine-tuning Qwen2.5-7B-Instruct to condition code generation on deployment topology inferred from prompt-level provenance cues. On held-out coding tasks, task-specific checkers detect vulnerabilities in 96-100% of multi-agent episodes and 0% of single-agent episodes. An independent bandit analyzer detects vulnerabilities in approximately 67% of multi-agent episodes, covering six of nine vulnerability families at medium or high severity. Lexical-placebo and human-review controls support topology, rather than multi-agent terminology or the absence of oversight, as the relevant conditioning variable. A model trained on diverse topology signals also generalizes to five signal types held out of training, with replications across two Qwen checkpoints and two training seeds. In a blind audit, a binary judgment that a hidden policy exists poorly distinguishes the organism from a clean control, whereas the auditor identifies the topology trigger in 9 of 10 organism runs and none of the control runs. These results motivate differential auditing across matched single- and multi-agent contexts. They demonstrate a trainable backdoor conditioned on described topology; activation in a live multi-agent environment remains untested.

Keegan Wang, Anantika Mannby

Carnegie Mellon University Prosaic Intelligence · University of Southern California Prosaic Intelligence

LLM Backdoor Attacks AI Agent Auditing Backdoor Attacks Multi-Agent System Security

Sep 30, 2026cs.CV

BadAction: Backdoor Attacks on Interactive Video Generation via Action-Guided Triggers

Interactive video generation (IVG) models have achieved remarkable progress in producing controllable visual content guided by user-defined actions, yet their security vulnerabilities remain largely unexplored. In this paper, we present the first systematic study of backdoor attacks against the interactivity of IVG models. Based on this attack surface, we propose BadAction, which leverages action-guided triggers to achieve the attack. Specifically, BadAction implants predefined motion patterns into the action sequences of backdoor samples and associates them with a static target video. Once triggered, the backdoored model generates frozen future frames that no longer respond to subsequent user actions, while preserving normal behavior on benign action sequences. In addition, we explore a stealthier attack in which multimodal triggers jointly poison action, text, and image inputs. Experiments show that BadAction achieves average attack success rates of 91.0% with action-only triggers and 80.4% with multimodal triggers. Moreover, extensive defense evaluations show that BadAction successfully bypasses existing backdoor detection methods, revealing a critical security gap in the interactive video generation pipeline. Project page: https://wsad55.github.io/badaction01/.

Zhihang Wu, Zhongqi Wang, Jie Zhang +3

Key Laboratory of AI Safety of CAS, Institute of Computing Technology, Chinese Academy of Sciences (CAS), Beijing, China · University of Chinese Academy of Sciences, Beijing, China · School of Advanced Interdisciplinary Sciences, University of Chinese of Sciences, Beijing, China

Action-Conditioned Video Generation Backdoor Attacks

Sep 23, 2026cs.CV

ODPure: Backdoor Purification for Object Detection via Ensemble Corruption Consensus

With the development of applications like autonomous driving, object detection has gained significant attention, while also highlighting critical vulnerabilities like backdoor attacks that severely compromise model integrity. Specifically, such attacks involve altering the categories of objects (i.e., object misclassification), removing bounding boxes (i.e., object disappearance), or generating bounding box proposals for non-existent objects (i.e., object generation) when a predefined trigger is present in the input. Although backdoor defenses for image classification are well-established, the research for object detection remains comparatively underexplored. Existing defenses address these threats by scanning outputs or models for potential backdoors but require discarding either malicious data or models. This remedy fails to enable a continuous and accurate perceptual stream for the object detection pipeline. To address such limitations, we propose ODPure, a novel input-stage black-box defense for object detection, which is based on input purification that ensures stable perception flows. Tailored to the dense prediction nature of object detectors, our Corruption-Reconstruction-Selection (CRS) paradigm operates by neutralizing triggers through a diverse portfolio of corruptions to generate a massive pool of redundant proposals, then recovering fine-grained structural cues via generative priors, and finally employing voting to reach a consensus on the resulting detections. Comprehensive experiments demonstrate that our method provides robust defense against diverse backdoor attacks and trigger types while preserving baseline accuracy. Our code is available at https://github.com/Alex66366/ODPure.

Li Zeng, Mingcheng Duan, Longfei Fan +5

School of Computer and Communication Engineering, Changsha University of Science & Technology, Changsha 410114, China · School of Computer Science, Xiangtan University, Xiangtan 411105, China · School of Software, Yunnan University, Kunming 650500, China +3

Backdoor Attacks Backdoor Defense Object Detection

Sep 14, 2026cs.CR

Implementing a White-Box Undetectable Backdoor for Random Fourier Features

Goldwasser et al. showed that undetectable backdoors can be planted in machine learning models trained with the Random Fourier Features (RFF) algorithm, under a hardness assumption tied to the Continuous Learning With Errors (CLWE) problem. Under standard cryptographic assumptions, even a full white-box audit of a model's weights cannot detect this class of backdoor. The construction is stated in terms of cryptographic reductions and probabilistic lemmas, without a reference implementation, and relies on secondary machinery such as the Sparse Gaussian Pancakes distribution and a homogeneous CLWE conditional density. Its realizability in ordinary numerical code is not obvious from the paper alone. This paper implements the white-box CLWE-RFF backdoor construction end to end using only numpy and scipy, to test whether this threat is realizable with commodity scientific-computing tools or requires specialized cryptographic infrastructure. We give two samplers for the core

GP_d(b_k)

distribution. The first is a rejection-sampling proxy. The second is an exact closed-form sampler derived from the homogeneous CLWE density and verified against its own analytic form. Using this implementation, we run statistical indistinguishability tests, covering both weight-space and functional black-box comparisons. We find no evidence of detectable difference between backdoored and clean models across a range of sparsity ratios

ρ= d_{\text{sparse}}/D

. We report which parts of the construction were straightforward to realize, which required derivation not spelled out in the paper. We also highlight which parts we did not attempt to reproduce, including the underlying lattice hardness reduction. We see this work as a contribution to understanding the practical realizability of the Goldwasser white-box CLWE core, not as a new theoretical result.

Michael Collins, Jada Cumberland, Brianne Dunn +3

Laboratory for Advanced Cybersecurity Research Laurel, MD 20707 · School of Cybersecurity Old Dominion University Norfolk, VA 23259 · Old Dominion University Norfolk, VA 23259 +1

Adversarial Attacks Backdoor Attacks

Sep 14, 2026cs.CR

When the World Lies: Backdoor Attacks on Latent World Models for Downstream Control

Pretrained world models, learned simulators that encode an observation into a latent state and predict how it evolves under actions, are beginning to be reused as off-the-shelf dynamics backbones for control, like pretrained encoders and language models are reused today. We show that this reuse opens a supply-chain backdoor: an adversary who controls only a released checkpoint can hijack the downstream controller, even though the victim trains and evaluates entirely on clean data and never sees the trigger. The attack encodes no explicit trigger-to-action rule. Instead, the poisoned model routes trigger-bearing observations into a chosen latent region and reshapes the local dynamics there, so that the victim's own optimization (Dreamer-style actor training in imagination, or MPC/CEM planning over predicted futures) re-discovers the attacker's target action on its own. Across several control tasks and trigger families, the trigger steers the controller's action toward the attacker's target, controlling every action dimension and hijacking 100% of triggered steps on the strongest settings. The checkpoint still passes the clean-data diagnostics a victim would run before deployment, with clean-task success retaining at least

\sim

75%. The effect is temporally gated: it appears only while the trigger is present and disappears when the trigger is removed. Trigger-blind repair is budget-dependent: moderate clean fine-tuning can preserve clean utility while leaving the triggered failure intact, whereas sufficiently aggressive adaptation can remove it only after substantially degrading clean control. The world-model backbone itself is therefore an emerging and underexamined attack surface for control. The full code and artifacts are available in our repository.

Roberto Riaño, Gorka Abad, Stjepan Picek +1

Radboud University, The Netherlands · IKERLAN Technology Research Centre, Spain · University of Bergen, Norway +1

Backdoor Attacks Latent World Models

Sep 14, 2026cs.LG

Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks

Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to produce when the trigger appears. Existing evaluations typically fix the number of poisoned examples and sample them at random from a candidate pool. We show that this can severely underestimate worst-case vulnerability: across three LLaMA-3-8B backdoor settings, holding the model, clean data, and poison count fixed, attack success ranges from 3% to 80% depending only on which poison set is chosen. We formalize poison selection as oracle-budgeted set optimization and introduce SAILS (Set-level Audit-Informed Iterative Learned Selection), which learns a set scorer from a few hundred finetune-and-evaluate runs, ranks millions of candidate sets, and audits only a small shortlist. SAILS improves held-out attack success by 30 percentage points on average over the strongest influence baselines, transfers from small-scale to full-scale finetuning, and extends to code-generation, agentic, and API-only backdoors.

Aashiq Muhamed, Mona T. Diab, Virginia Smith +2

Carnegie Mellon University · Anthropic

LLM Backdoor Attacks Backdoor Attacks Data Poisoning Attacks

Sep 10, 2026cs.CR

Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST with three baseline classifiers: Logistic Regression, Linear SVM, and Random Forest. Clean training is compared with poisoning rates of 5%, 10%, and 20% using clean-test accuracy, macro-precision, macro-recall, macro-F1, and, for backdoors, attack success rate. Label flipping caused clear degradation, largest for Logistic Regression and Linear SVM, while Random Forest stayed comparatively stable. Backdoor poisoning reached attack success rates from 0.9667 to 1.0000 on both datasets and all three models while often keeping clean-test performance near baseline. The results separate indiscriminate poisoning, which shows up in standard metrics, from targeted backdoor poisoning, which stays comparatively stealthy while embedding highly effective malicious behavior, and they support security-oriented evaluation beyond conventional clean-test metrics.

Toshif Khan, Muhammad Abusaqer

Minot State University · Department of Math, Data & Technology Minot State University Minot, ND, 58707 · Trustworthy Language Intelligence Lab, Minot State University

Adversarial Attacks Backdoor Attacks Data Poisoning Attacks

Sep 2, 2026cs.LG

CACTUS: Mask-Guided Semantic Clean-Label Backdoors in Decentralized Federated Learning

Semantic triggers in federated learning (FL) can be less conspicuous than synthetic patches, but sample-dependent placement may weaken backdoor implantation across aggregation rounds. This challenge is compounded in decentralized FL (DFL), where topology-dependent peer aggregation repeatedly mixes local models. CACTUS converts label-consistent semantic pairs into target-directed representation shifts. Mask-guided, modality-specific operators isolate trigger effects, couple them across samples, and apply the shifts counterfactually to clean non-target embeddings before peer aggregation. Experiments cover speech, text, tabular, and image tasks under nine aggregation rules. With 30% malicious nodes, CACTUS reaches a nine-rule mean attack success rate (ASR) of 51.2% on Speech Commands and the highest nine-rule mean ASR among evaluated attacks on three of four modalities. Sensitivity analyses show that ASR varies with network topology and increases with the malicious-node ratio. These results indicate that CACTUS can propagate backdoors through repeated DFL aggregation.

Chao Feng, Burkhard Stiller

Communication Systems Group, Department of Informatics University of Zurich, Switzerland

Backdoor Attacks Backdoor Attacks in Federated Learning Federated Learning

Aug 31, 2026cs.SD

Ouroboros: Self-Referential Backdoor Attacks on Speech Enhancement via Clean Audio Triggers

Speech enhancement models are widely deployed as frontend modules in real-time speech services, yet their vulnerability to backdoor attacks remains unexplored. Existing backdoor methods are confined to classification tasks and rely on active trigger injection, an assumption incompatible with the passive processing nature of speech enhancement models. In this paper, we propose Ouroboros, a novel backdoor attack framework that leverages the ideal clean outputs of speech enhancement models as natural triggers, enabling inference-time activation without any external trigger injection. Extensive evaluations show Ouroboros achieves near-perfect attack success rates with minimal performance degradation on diverse models and datasets. Physical-world validations confirm that naturally recorded, unaltered clean audio can reliably activate the backdoor. Moreover, Ouroboros generalizes to targeted content-tampering attacks and remains effective against common filtering and finetuning defenses.

Yunjie Zhou, Yuheng Huang, Diqun Yan

Faculty of Electrical Engineering and Computer Science, Ningbo University, China · College of Artificial Intelligence, Ningbo University of Finance and Economics, China

Backdoor Attacks Speech Enhancement

Aug 13, 2026cs.LG

Understanding Backdoor Vulnerabilities in Vertical Federated Learning: The Gap Between Research and Practice

Vertical Federated Learning (VFL) enables organizations holding complementary features of shared entities to collaborate and train models. In this setting, the initiator can withhold information about the learning task, while other contributors participate without exposing their local datasets, creating an asymmetric information structure aligned with growing privacy demands. However, this asymmetry is a double-edged sword. Among various threats, backdoor attacks are particularly concerning because VFL not only enables malicious contributors to poison the model during training, but also allows them to activate the backdoor at inference time to manipulate predictions. Although prior work has reported near-perfect attack success rates and proposed effective defenses, we find that most findings fail to hold under realistic conditions, exposing a fundamental gap between research and practice. In this paper, we present a systematic, practice-oriented study of backdoor vulnerabilities in VFL, revealing this gap in both methodological design and evaluation practices. We show that existing approaches overlook key practical constraints and therefore rely on unrealistic prior knowledge. Furthermore, these limitations have remained hidden due to poorly designed evaluation practices in the literature. To bridge this gap, we redefine threat models under realistic constraints, propose practical backdoor workflows, and introduce BVBench, a backdoor-centric benchmark that enables fair, practical, and comprehensive evaluation, preloaded with state-of-the-art baselines. BVBench provides strong evidence of the fragility of the current understanding of VFL backdoor risks and establishes a foundation for steering research toward uncovering practical vulnerabilities and developing more meaningful defenses.

Ziqi Zhao, Jialin Lu, Junjie Shan +3

School of Computing and Data Science, The University of Hong Kong, Hong Kong SAR, China

Backdoor Attacks Backdoor Attacks in Federated Learning Federated Learning

Aug 11, 2026cs.LG

Analysis of Federated Aggregation under Model Poisoning and Backdoor Attacks: A Reconstructed Cross-Dataset and Cross-Architecture Benchmark

Robust comparisons of federated aggregation methods require joint consideration of predictive performance, threat definitions, metric semantics, and execution provenance. A 500-cell seed-1 evaluation matrix was reconstructed across five aggregation methods, five datasets, five architectures, and four recorded conditions: clean, sign-flipping, Gaussian, and BadNets. Successful execution logs were identified for 454 original runs and 36 repaired or rerun executions, whereas 10 clean SVHN cells were supported by summary-only provenance. Trimmed Mean achieved the highest clean macro-mean accuracy (76.02%) and the lowest mean within-task rank (1.70). Krum attained the highest recorded accuracy under both sign-flipping and Gaussian configurations. These relative rankings remained unchanged when analysis was restricted to 21 task pairs for which original successful logs were available for every method-condition combination. Audit of the supplied BadNets metric implementation established that every test input is triggered prior to target-label counting; consequently, the retained metric represents Triggered Target-Label Rate (TTLR) rather than a conventional target-excluding attack success rate. An audit of the supplied FedPARETO scaffold further identified a pathway in which predictive summaries may characterize an uncorrupted local model while the aggregation weight is applied to a separately corrupted update, introducing a potential discrepancy between reported predictive outcomes and the updates used for aggregation. The canonical matrix contains a single identified seed for each cell, and exact attack and configuration lineage is incomplete. Accordingly, the findings should be interpreted as descriptive comparisons within the recorded configurations and not as statistical estimates or universal claims regarding robustness.

Soumya Mazumdar, Vineet Kumar Rakesh, Tapas Samanta

Department of Computer Science and Business Systems Gargi Memorial Institute of Technology Affiliated to Maulana Abul Kalam Azad University of Technology Balarampur, Mouza Beralia, Baruipur, Kolkata 700144, West Bengal, India · Computer and Informatics Group, Variable Energy Cyclotron Centre 1/AF, Bidhannagar, Kolkata 700064, West Bengal, India · Engineering Sciences, Homi Bhabha National Institute Anushaktinagar, Mumbai, Maharashtra 400094, India

Federated Learning Aggregation Byzantine-Robust Federated Learning Backdoor Attacks Backdoor Attacks in Federated Learning Federated Learning

Aug 11, 2026cs.CV

Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs

Existing vision-language model (VLM) backdoors are usually treated as static vulnerabilities: one-to-one and N-to-N attacks bind one or more triggers to a finite set of targets before victim training. This assumption substantially underestimates the threat. We show that a single poisoning phase can implant a programmable backdoor into a VLM, allowing an attacker to choose previously unseen target-caption semantics at inference time and synthesize corresponding stealthy triggers on demand. Unlike fixed-mapping attacks, the proposed any-to-any caption-control paradigm decouples post-training target selection from poisoning, enabling dynamic control of target captions without retraining the VLM. Our method has two components. First, a heuristic poisoning strategy exposes the model to diverse trigger-caption pairs, encouraging it to learn a general trigger-as-instruction rule rather than memorize a specific backdoor pattern. Second, a feature-space trigger steganography method maps any attacker-specified target caption to a stealthy visual trigger, implemented as either a norm-controlled perturbation or a non-semantic patch. Once inserted into arbitrary images, these triggers cause the poisoned VLM to generate outputs semantically aligned with the chosen target caption, even when the target was unseen during poisoning. Extensive experiments show that our attack achieves high any-to-any caption-control success rates, preserves clean model utility, and remains effective under several classical backdoor defenses.

Tao Lin, Gaojie Jin, Zongxin Liu +2

Key Laboratory of System Software (Chinese Academy of Sciences), Beijing, China · Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China +2

Adversarial Attacks on VLMs Vision-Language Models Backdoor Attacks Backdoor Attacks on VLMs

Aug 10, 2026cs.CR

DiffSafeMerge: Mitigating Backdoor Inheritance in Diffusion Model Merging

Unconditional diffusion checkpoint merging assumes benign sources, yet a compromised public checkpoint can transfer a dormant backdoor while clean generation appears normal. Mitigation is difficult without knowing the compromised source, trigger, or target, and broad sanitization may degrade image quality. We introduce DiffSafeMerge (DSM), which uses a small unlabeled clean set and fixed, attack-agnostic stress probes to score source blocks, shrink suspicious contributions toward a trusted reference, and select attenuation under a clean denoising-loss budget. We evaluate four attacks, two datasets, and 21 target conditions. Intended merging already has zero worst-target ASR in 10 of 14 source cases; DSM preserves these outcomes and records no target match in the remaining four over three seeds, including three with baseline ASR of 48--100%. Among methods with zero worst-target ASR on both datasets, DSM obtains the lowest case-averaged FID in the matched seed-0 comparison.

Jiayang Zhang, Ji Guo, Jiachen Li +2

University of Electronic Science and Technology of China, Chengdu, China · Wuhan University of Technology, Wuhan, China

Backdoor Attacks Backdoor Defense Diffusion Models

Aug 10, 2026cs.CR

Diversity Matters: Distributional Feature Coverage Sample Selection for Data-Efficient Backdoor Attacks

Backdoor attacks compromise training data so that a model retains clean accuracy but predicts an attacker-chosen target on triggered inputs. At very low poisoning rates, only a few samples convey the trigger--target association, making poison-sample selection critical. Existing methods typically rank candidates using per-sample scores, which can select redundant samples from similar semantic regions, and many require task-specific surrogate training. We propose Distributional Feature Coverage Sample Selection (DFCS), a training-free, trigger-agnostic method that clusters fixed pretrained features into one region per poisoning slot and selects the centroid-nearest sample from each region. A local first-order analysis relates this allocation to feature-coverage and representative-mass terms. Across BadNets and Blended attacks on CIFAR-10, Tiny-ImageNet, and Imagenette, DFCS achieves the highest mean attack success rate among seven selectors in all six dataset--attack settings, averaging

96.30\%

and exceeding the strongest comparator in each setting by 4.60 percentage points on average while preserving clean accuracy. These results support distributional feature coverage as an effective selection principle for low-budget dirty-label backdoor attacks.

Yi Yang, Xiaoke Chen, Jinyang Huang +6

School of Computer Science and Information Engineering, Hefei University of Technology, Hefei 230601, China · School of Information Science and Technology, University of Science and Technology of China, Hefei 230026, China · John Hopcroft Center for Computer Science, Shanghai Jiao Tong University, Shanghai 200240, China +1

Backdoor Attacks Data Selection Training Data Selection Data Poisoning Attacks

Aug 9, 2026cs.LG

Robust Reputation-Driven Crowdsourced Federated Learning

Crowdsourced Federated Learning (CrowdFL) extends traditional federated learning by enabling open and heterogeneous participation through a crowdsourcing paradigm. In this setting, reputation-driven incentive mechanisms are commonly employed to guide worker selection and enhance trustworthiness. While such approaches improve participant reliability, existing frameworks largely overlook the quantification of their robustness against stealthy adversaries, particularly those capable of evading standard detection mechanisms. To fill this gap, this paper proposes R2CFL, a robust reputation-driven CrowdFL framework. R2CFL introduces a robust reputation model coupled with a nearest neighbor mixing (R2-NNM) defense mechanism that links reputation evolution with the filtering of updates during aggregation. The proposed mechanism prevents stealthy attackers from gradually accumulating trust and influencing future tasks. Experimental results demonstrate that R2-NNM matches or surpasses state-of-the-art Byzantine-robust and backdoor defense mechanisms against adaptive attackers. Furthermore, when integrated with existing detect-and-filter defenses, the proposed reputation model faithfully captures the statistical robustness of the underlying defense by producing reputation scores that closely reflect its true positive and false positive characteristics.

Mouhamed Amine Bouchiha, Gregory Blanc

SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris

Byzantine-Robust Federated Learning Backdoor Attacks Federated Learning

Aug 7, 2026q-bio.QM

Genotypic Triggers: Exposing Pharmacogenomic Blind Spots via Host-Specific Backdoors in Generative Antimicrobial Peptide Models

Large Language Models (LLMs) have accelerated drug discovery, particularly in the automated design of antimicrobial peptides (AMPs). However, current validation pipelines for peptide generation models overlook historical precedents showing that certain drugs carry health risks predominantly for individuals with specific genetic profiles. In this paper, we demonstrate that such targeted health risks can be induced intentionally and at scale by manipulating models that generate peptide candidates. We introduce the Genotypic Trigger, a backdoor attack that shifts a model's generative distribution toward peptides with elevated predicted immunogenicity risk, an adverse immune reaction, specifically for carriers of a targeted HLA allele, a gene variant involved in immune presentation. Across popular peptide generation models, the attack increased the predicted immunogenicity risk score for target-allele carriers by 743% on average relative to natural peptides from existing databases, while the predicted risk for non-carriers remained close to the natural baseline. Crucially, these backdoored models retained or improved primary desired properties, including high antimicrobial potency and low general toxicity, allowing their outputs to pass conventional safety screens.

Doniyorkhon Obidov, Xiaolong Guo, Yonghui Li +1

Michigan Technological University · Lehigh University · Kansas State University

Backdoor Attacks Molecular Generation Protein Design Drug Discovery

Aug 6, 2026cs.LG

Bypassing Krum: Selection-Aware Backdoor Attacks in Federated Learning

Robust aggregation methods are widely used in federated learning to mitigate the impact of adversarial client behavior. Distance-based aggregation rules, such as Krum and Multi-Krum, select updates that are closest to the majority under the assumption that benign updates form a compact cluster. However, these methods rely on geometric properties that can be exploited by adaptive adversaries. We introduce the Krum-Proxy attack, a selection-aware backdoor injection strategy that consistently bypasses Byzantine-robust aggregation. Rather than relying on naive scaling or constraining, our method actively optimizes malicious updates to infiltrate the dense core of the benign distribution. The proposed method constructs adversarial updates that are not only similar to benign updates but are also optimized to lie in regions of the update space that are favored during aggregation. This is achieved through a two-stage optimization procedure that separates task-specific attack objectives from geometry-aware refinement, using a nearest-neighbor proxy, stochastic reference modeling, and anchor-guided alignment. To maintain stealth, we introduce a projection mechanism that constrains adversarial updates within realistic norm and variance bounds. Experiments on standard federated learning benchmarks show that Krum-Proxy achieves higher attack success while preserving clean accuracy, highlighting the vulnerability of distance-based aggregation to selection-aware adversaries.

Srinivasan Subramanian, Md. Abdullah Al Hafiz Khan, Kazi Aminul Islam

Department of Computer Science Kennesaw State University Marietta, USA

Federated Learning Aggregation Byzantine-Robust Federated Learning Adversarial Attacks Backdoor Attacks Backdoor Attacks in Federated Learning

Aug 3, 2026cs.CR

Evading Chain-of-Thought Monitoring Through Model Poisoning

Chain-of-thought (CoT) monitoring is an increasingly important component of AI safety stacks but relies on the assumption that a model's reasoning trace is informative about its actions. This work studies the limits of CoT monitoring through the lens of model poisoning. We demonstrate that backdoors can be implanted into reasoning models to elicit an attacker-chosen behavior while their CoT traces appear entirely benign. We find that these CoT-Hidden backdoors can be induced through simple fine-tuning recipes across reasoning-model architectures and sizes. When direct poisoning is ineffective, we introduce a curriculum training approach that progressively teaches the model to produce an attacker-chosen output while concealing the behavior from its reasoning traces. These findings suggest that CoT monitoring may be better framed as a question about the consistency between a model's reasoning trace and its final response than as anomaly detection within a trace. We further examine the mechanisms that allow models to suppress evidence of the target behavior from their reasoning traces. Causal interventions locate a trigger-conditioned activation pathway that does not depend on the visible reasoning, and residual stream verbalizations provide an anomaly warning near answer generation, but do not identify the trigger, target, or backdoor mechanism.

Giorgio Severi, Shujaat Mirza, Blake Bullwinkel +1

Microsoft

LLM Backdoor Attacks LLM Auditing Backdoor Attacks CoT Monitoring

Aug 2, 2026cs.MA

When Collaboration Becomes a Trigger: Collective Evidence-Threshold Backdoors in Multi-Agent Systems

LLM-based multi-agent systems (MAS) extend LLM capabilities through iterative communication and shared contexts. However, this collaboration introduces a vulnerability: backdoor behavior can be activated when peer evidence reaches a hidden threshold, rather than being determined by any single message. We introduce a collective evidence-threshold backdoor paradigm for MAS and Boundary-Conditioned Backdoor Injection (BCBI), which constructs counterfactual boundary pairs to separate benign behavior before the threshold from the adversarial objective after it, and learns latent progression aligned with evidence. To mitigate this threat, we propose LAtent Transition Test-time Evaluation (LATTE), a clean-only latent-transition defense that learns benign communication dynamics and quarantines anomalous agent updates before their responses propagate. Across several benchmarks, BCBI yields selective activation with little premature activation; without knowing the attack target or trigger, LATTE limits propagation with minimal disruption.

Jia-Hao Xiao, Lei Feng, Min-Ling Zhang

School of Computer Science and Engineering, Southeast University, Nanjing 210096, China · Key Laboratory of Computer Network and Information Integration (Southeast University)

Multi-Agent LLM Systems Backdoor Attacks Multi-Agent System Security

Aug 1, 2026cs.LG

Mitigating Backdoors via Decoy Shortcuts and Knowledge Decoupling

Backdoor attacks pose a serious threat to deep neural networks, especially when training relies on third-party data, allowing adversaries to inject malicious behaviors through data poisoning. In this work, we reveal that backdoor behaviors tend to be absorbed by a simpler parallel branch when jointly trained with the main network. Motivated by this insight, we propose Trapping and Removing (TR), a simple yet effective training-time defense that introduces a lightweight shortcut branch as a "honeypot" to trap backdoor knowledge. After training, backdoors can be removed by discarding the shortcut, without requiring any additional data. To further enhance backdoor isolation while maintaining benign performance, we design a knowledge decoupling strategy with entropy-based weight assignment, encouraging poisoned samples to flow through the honeypot while guiding the main network to focus on benign learning. In addition, we introduce an automatic shortcut generation strategy to improve generalization across model architectures. Extensive experiments on four benchmark datasets and five model architectures demonstrate that our approach effectively mitigates a wide range of backdoor attacks while preserving performance on benign data. Code: https://github.com/Zixuan-Zhu/TR}{github.com/Zixuan-Zhu/TR.

Zixuan Zhu, Rui Wang, Lihua Jing +1

Institute of Information Engineering, Chinese Academy of Sciences · School of Cyber Security, University of Chinese Academy of Sciences

Backdoor Attacks Backdoor Defense

Aug 1, 2026cs.CR

Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor

Although semantic watermarking is considered a promising safeguard for images generated by Latent Diffusion Models (LDMs), the reliance of the watermark detection pipeline on neural networks introduces a critical yet underexplored backdoor attack surface. To systematically study this vulnerability, we propose GhostVAE to plant a stealthy backdoor into the encoder of Variational Autoencoder (VAE), enabling reliable evasion of watermark detection. GhostVAE operates in two stages: it first constructs a universal trigger via power spectrum regularization to improve the trigger robustness, and then trains a backdoored VAE encoder with a parameter-aligned objective. Through extensive evaluations across three state-of-the-art semantic watermarking schemes and three widely adopted LDMs, we show that GhostVAE preserves watermark detection performance on benign images (achieving an average true positive rate of 94.4%), while simultaneously enabling highly effective evasion under trigger activation (achieving an average attack success rate of 94.6%). Moreover, we comprehensively analyze seventeen representative defenses and demonstrate that GhostVAE remains stealthy across the input space, parameter space, and latent space. Our work fundamentally undermines the trustworthiness of semantic watermarking systems and highlights that secure deployment of semantic watermarks requires end-to-end security considerations, particularly for neural network components.

Jinyuan Liu, Tianshuo Cong, Pei Li +4

1Tsinghua University · 2Shandong University · 4Shandong Key Laboratory of Artificial Intelligence Security, Shandong University +5

Variational Autoencoders Diffusion Model Watermarking Backdoor Attacks Robust Watermarking

Jul 30, 2026cs.CR

Temporal Poisoning: Clean-Label Backdoors via Event Redistribution in SNNs

Backdoor attacks on Spiking Neural Networks (SNNs) have primarily assumed dirty-label poisoning, in which triggered training samples are relabeled to an attacker-selected class. We study clean-label temporal poisoning, where a fixed timestamp transformation is applied only to the target-class training streams, leaving their labels unchanged. The transformation preserves the per-pixel, per-polarity event count exactly, making clean and triggered samples identical after temporal aggregation while altering the sequence processed by the SNN. Across three neuromorphic datasets and both convolutional and transformer-based victims, the attack reaches an ASR of 1.00 in the strongest configurations. We analyze the attack through poison-budget and trigger-shape ablations and evaluate established backdoor defenses adapted to spiking models. Defenses that collapse the time axis before inspection are blind by construction, while feature-space methods detect the poison only in selected settings. Our model-free detector, based on per-step event mass, detects the evaluated temporal transformations, demonstrating both the limitation of rate-collapsed defenses and the boundary of the attack's stealth. To our knowledge, this is the first clean-label backdoor attack evaluated on SNNs and neuromorphic event data.

Roberto Riaño, Gorka Abad, Stjepan Picek +1

Radboud University, The Netherlands · Ikerlan Research Centre, Spain · University of Bergen, Norway +1

Backdoor Attacks Backdoor Detection Spiking Neural Networks

Jul 30, 2026cs.LG

TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement

Federated fine-tuning of large language models (LLMs) enables collaborative training without exposing raw data. However, a recent attack, NeuroImprint, demonstrates that a malicious parameter server can corrupt a PEFT adapter into a privacy backdoor: by assigning a dedicated memorization neuron to each training sample and ensuring each neuron updates at most once, the server can analytically reconstruct 59%--79% of client training data with high semantic fidelity. Existing defenses---including local differential privacy (LDP) and gradient clipping---either fail against this attack or impose unacceptable utility degradation. We present \textbf{TriShield}, a three-layer deterministic defense that completely prevents NeuroImprint-style reconstruction with zero model utility loss and no additional communication rounds. TriShield consists of: (1) a Parameter Artifact Detector that identifies memory-neuron signatures in distributed model parameters before local training begins; (2) a Stateful Virtual Iteration} mechanism that forces Adam/AdamW's momentum state to irreversibly entangle gradients across virtual steps, invalidating NeuroImprint's closed-form inversion; and (3) a Zero-Utility Orthogonal Projection operator that projects all local gradient updates onto the main-task semantic subspace computed via SVD, physically eliminating any gradient components that carry private memorization. We prove theoretically that after Layers 2 and 3, the mutual information between the uploaded gradient and any individual training sample is zero. Experiments on GPT-2 (117M) and Llama-Guard-3-1B verify that TriShield reduces NeuroImprint reconstruction rate to 0% across all tested attack variants, while maintaining or improving training accuracy, with less than 5% additional GPU computation overhead.

Cheng Wei

Honor Device Co., Ltd., Shenzhen, China

Backdoor Attacks Backdoor Attacks in Federated Learning Backdoor Defense in LLMs Privacy Leakage in Language Models LLM Security Federated Fine-Tuning

Jul 28, 2026cs.CR

Lilith: Backdoor Generalization under Training-Inference Trigger Shift

Machine-learning services increasingly rely on public data, third-party providers, and outsourced training, creating opportunities for data-poisoning attacks that implant persistent malicious behavior while preserving benign utility. However, existing backdoor studies largely evaluate exact trigger reuse, training-exposed trigger diversity, or variations along predefined transformation axes. They therefore leave a critical blind spot: whether a backdoor learned from one training-time trigger can generalize to an inference-time trigger family absent from victim training. We formulate this problem as backdoor generalization under training--inference trigger shift and introduce Lilith, a black-box anchor-to-family framework. Using only disjoint surrogate resources, Lilith first induces a compact target-side vulnerability with a single training anchor, then constructs a bounded inference-only family that preserves the anchor-induced representation geometry. We characterize this mechanism through anchor clearance and family reach, deriving sufficient conditions for family-wise target preservation under local regularity and bounded surrogate--victim discrepancy. Experiments across datasets, architectures, poisoning rates, and defenses show that Lilith achieves high family-wise attack success with limited utility degradation and a small trigger generalization gap. Additional analyses show that family activation depends on representation alignment rather than the proposal mechanism, exposing a broader threat overlooked by exact-trigger evaluation.

Zhou Feng, Jiahao Chen, Chunyi Zhou +6

Zhejiang University College of Computer Science and Technology Hangzhou, China · Zhejiang University School of Software Technology Hangzhou, China · Chongqing University School of Big Data & Software Engineering Chongqing, China +1

Backdoor Attacks Data Poisoning Attacks

Jul 27, 2026cs.CR

Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study

Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run. Per-step safety checks that judge each action in isolation may fail to recognize the complete distributed payload. We investigate how early such an attack can be detected while the run is still unfolding, and how robustly it can be caught once its most obvious cues are stripped away. We build a working instance on a hierarchical multi-agent system, run it under benign and attacked conditions across five language models and two task domains, and record when each fragment is injected and when the payload is assembled and executed. Detection is a race against assembly. Before the first fragment is injected, attacked and benign runs are indistinguishable; once injection begins, a prefix detector flags

99.3\%

of successful attacks with a median of five steps remaining and a

10.3\%

safe-run false-positive rate. Because assembly occurs only after the run, these alarms arrive in time to abort nearly every successful attack. We then measure how much of that warning rests on removable surface cues of the attack rather than on its distributed structure. Generic zero-shot and behavior-trained detectors provide almost no warning at all; the detectors that do work lean in part on removable surface cues, chiefly the ciphertext's length and entropy, and once the entropy cue is removed from the payload and the length features from the detector, detection arrives later and transfers poorly across domains, though a fine-tuned model recovers some of the loss.

Diego Fernandez Arias, Dev Prashant Mistry, Ren Wang +1

Illinois Institute of Technology Chicago, Illinois, USA

Multi-Agent LLM Systems LLM Backdoor Attacks Backdoor Attacks Backdoor Detection AI Agent Monitoring Multi-Agent System Security

Jul 22, 2026cs.CR

FedLSG: LLM-Enhanced Semantic Calibration for Federated Graph Backdoor Defense

Federated Graph Neural Networks (FedGNNs) are highly vulnerable to backdoor poisoning, yet existing defenses typically rely on rule-based approaches that lack semantic understanding, making them vulnerable to stealthy triggers and harmful to benign structures. To solve this, we present FedLSG, the first framework that integrates large language models (LLMs) into federated graph backdoor defense. FedLSG introduces a graph and behavior to text grounding scheme that transforms local graph structures and client update behaviors into semantically rich natural language representations. The framework further adopts a lightweight student-teacher architecture. On the server side, a full scale LLM serves as a teacher, providing global contextual guidance and evaluating client updates during aggregation to identify potentially malicious participants. On the client side, a LoRA-based student is maintained to perform semantic reasoning, to suppress the influence of edges associated with backdoor triggers. By enabling semantic interpretation of both graph patterns and client behaviors, the framework adaptively incorporates rule-based signals into message passing and client aggregation for defense. Experiments demonstrate that FedLSG significantly improves resistance to backdoor attacks without compromising graph integrity.

Chenyu Zhou, Yabin Peng, Wei Huang +3

Southeast University Purple Mountain Laboratories · Institute of AI for Industries Chinese Academy of Sciences · Purple Mountain Laboratories

Graph Neural Networks Backdoor Attacks Backdoor Attacks in Federated Learning Federated Graph Learning LLMs for Graph Learning

Jul 17, 2026cs.CR

Natural Backdoor Attacks on Speech Recognition Models

With the rapid development of deep learning, its vulnerability has gradually emerged in recent years. This work focuses on backdoor attacks on speech recognition systems. We adopt sounds that are ordinary in nature or in our daily life as triggers for natural backdoor attacks. We conduct experiments on two datasets and three models to validate the performance of natural backdoor attacks and explore the effects of poisoning rate, trigger duration and blend ratio on the performance of natural backdoor attacks. Our results show that natural backdoor attacks have a high attack success rate without compromising model performance on benign samples, even with short or low-amplitude triggers. It requires only 5% of poisoned samples to achieve a near 100% attack success rate. In addition, the backdoor will be automatically activated by the corresponding sound in nature, which is not easy to be detected and will bring severer harm.

Jinwen Xin, Xixiang Lyu, Jing Ma

School of Cyber Engineering, Xidian University, Xi’an, China

Backdoor Attacks Automatic Speech Recognition Data Poisoning Attacks

Jul 13, 2026quant-ph

Input-Aware Dynamic Backdoor Attack Against Quantum Neural Networks

Quantum Neural Networks (QNNs) are a promising framework for quantum machine learning on near-term quantum devices, but their security risks remain insufficiently understood. Studies have shown that QNNs are vulnerable to backdoor attacks, yet existing quantum backdoors mostly rely on a fixed trigger shared by all poisoned inputs. This fixed-trigger design is a major weakness because many defenses detect or weaken the repeated patterns such triggers leave in data representations. Although input-aware dynamic backdoors have been studied in classical neural networks, transferring them to QNNs is difficult because quantum learning introduces new obstacles. In particular, measurement compresses the post-ansatz quantum state into a limited classical output, weakening supervision for a trigger generator, while individual density matrices fluctuate with the input and make per-sample contrastive learning unstable. To address these challenges, we propose Q-DIBA, the first input-aware dynamic backdoor attack for QNNs. Q-DIBA jointly trains a classical trigger generator and a victim QNN through a three-mode mini-batch strategy that supports clean behavior, attack activation, and trigger specificity. To provide stable quantum-level supervision, Q-DIBA introduces an ensemble density contrastive loss that operates on post-ansatz quantum states before measurement and contrasts mode-averaged density matrices rather than individual samples. Experiments on MNIST and Fashion-MNIST across multiple QNN architectures show that Q-DIBA achieves high clean accuracy, strong attack success, and high cross-trigger accuracy, demonstrating effectiveness, stealthiness, and input specificity. The attack also remains resilient against defenses including visual inspection, spectral-signature detection, and fine-tuning, suggesting that input-aware quantum backdoors are an important threat to secure QNN deployment.

Junrui Zhang, Zemin Chen, Lusi Li +3

Department of Computer Science, Old Dominion University, Norfolk, VA, USA · School of Cybersecurity , Old Dominion University, Norfolk, VA, USA

Backdoor Attacks Quantum Neural Networks

Jul 13, 2026cs.CR

When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems

As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own. We show this net has a fundamental hole. A distributed backdoor splits a harmful payload across agents, so every local check passes while the assembled object is the attack. The monitor can be right on every step and still miss the attack. The problem is not splitting itself: split fragments can still leak suspicious tokens or provenance edges. The hard case is \emph{local benignness}. No fragment carries the harm, and what is left looks like ordinary benign traffic. We formalize this as an \emph{observability boundary}: a monitor catches only what its view can tell apart from benign traffic. We prove that once the fragments look benign in the monitored view, no detector on that view can catch them, however strong it is. Across a controlled testbed, an external benchmark, and end-to-end agent runs, local monitors lose the signal exactly as local evidence disappears, and it returns only when the monitor sees the assembled object. A monitor trained only on benign traffic recovers the attack's code structure across held-out encodings (0.874 mean AUROC). A decoded-view gate, given the encoding family, blocks every tested attack. But seeing more is not enough: full-trace monitors and decoders still fail unless they reach the representation where the payload is exposed. Local safety is not global safety when harm is compositional, and the open problem is finding that representation.

Yibo Hu, Ren Wang

Illinois Institute of Technology

Backdoor Attacks Backdoor Detection AI Agent Monitoring Multi-Agent System Security

Jul 10, 2026cs.LG

Statistically Undetectable Backdoors in Deep Neural Networks

We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given the full descriptions of the models (e.g., all of the weights). The backdoor provides access to invariance-based adversarial examples for every input, mapping distant inputs to unusually close outputs. However, without the backdoor, it is provably impossible (under standard cryptographic assumptions) to generate any such adversarial examples in polynomial time. Our theoretical and preliminary empirical findings demonstrate a fundamental power asymmetry between model trainers and model users.

Andrej Bogdanov, Alon Rosen, Neekon Vafa

University of Ottawa. · Bocconi University. · Massachusetts Institute of Technology.

Backdoor Attacks Adversarial Examples Feedforward Neural Networks

Jul 10, 2026cs.CV

Event Burst Trigger: An Availability Backdoor Attack on Event-Based SNN Object Detection

Event-based vision and spiking neural networks (SNNs) are increasingly adopted for edge intelligence under strict latency and energy constraints. However, the vulnerability of event-based SNN object detection models to availability backdoor attacks remains insufficiently studied. This paper presents Event Burst Trigger (EBT), an availability backdoor attack targeting SNN-based object detection models. EBT injects carefully crafted event-based triggers into the training data, which induce temporally concentrated event streams during inference. These burst-like activations increase the number of phantom (i.e., spurious) object candidates, and consequently inflate the computational cost of the post-processing stage, particularly Non-Maximum Suppression (NMS). We evaluate EBT on SpikeYOLO, the state-of-the-art SNN-based object detector, under a poison-only threat model that does not require modifications to the model architecture, loss function, or inference pipeline. Experimental results show that while detection accuracy remains largely preserved, with [email protected] decreasing by less than 0.099, the latency of the NMS stage increases by up to 38%. This indicates that NMS can become a dominant availability bottleneck in event-based SNN object detection. Experiments on an edge platform further show that the proposed attack elevates baseline resource utilization and reduces scheduling slack without inducing conspicuous peaks in resource usage. In addition, STRIP-based backdoor detection fails to reliably distinguish the proposed attack from benign inputs. These results characterize a previously underexplored availability backdoor threat in event-based SNN object detection systems.

Jaesun Baek, Chanwook Lee, Eun-Kyu Lee

Dept. of Information and Telecommunication Eng., Incheon National University, Republic of Korea

Backdoor Attacks Spiking Neural Networks Event-Based Object Detection

Jul 7, 2026cs.CR

Assessing the Operational Impact of Poisoning Attacks over Augmented 3D Point Cloud Public Datasets for Connected and Autonomous Vehicles

Poisoning attacks against public datasets lead to major concerns, such as (i) misclassification of perceived objects when the poisoned data is used for training and (ii) embedding of backdoors that may eventually be triggered later on, when specific conditions in the system apply over the learned models. Its impact over data augmentation models is unclear. While data augmentation reduces the likelihood of poisoning attack success, some valid questions remain. Is data augmentation affecting the impact of poisoning attacks? can it increase the number of poisoned samples or injected backdoors? We explore in this paper some of these questions. We assess the effects of augmenting poisoned 3D point cloud datasets and validate that poisoning is able to evade the sanitizing nature of augmentation techniques when using the concrete case of Generative Adversarial Network (GAN) techniques to exemplify the case of data augmentation processing. We also validate that poisoning propagates over the augmented datasets and perturbs the decision made by general-purpose classifiers, in the end. All the experimental material (including tools, datasets, and classifiers) is publicly available, to facilitate reproducibility and to foster further research in the topic.

Marwan Lazrag, Badis Hammi, Lorena Gonzalez-Manzano +1

SAMOVAR, Télécom SudParis, Institut Polytechnique de Paris Palaiseau, France · Universidad Carlos III de Madrid Leganes, Spain

Autonomous Driving Datasets Data Augmentation Backdoor Attacks Data Poisoning Attacks

Jul 7, 2026cs.CR

The Power of Backdoor Absorption in Community Training

Backdoor attacks severely threaten large-scale AI models. When model owners delegate training to external compute providers within a decentralized training paradigm, adversaries can craft stealthy, low-frequency triggers to inject malicious behavior while evading standard audits. Traditionally, detecting these attacks requires a full re-computation of the training steps--a prohibitive overhead that directly contradicts the owner's resource constraints. To address this, we investigate the resilience of continuous optimization dynamics under Byzantine perturbations, where adversaries are forced to compete against a continuous influx of honest updates. Under a threat model where an adversary compromises f out of n total trainers, we quantify the minimum auditing overhead required by the model owner to probabilistically bound the attack success rate. We formalize this injection-absorption dynamic as a Discrete-Time Markov Chain (DTMC). Using this framework, we prove that the success probability of any bounded adversary asymptotically collapses to zero under a defense strategy combining natural absorption, a randomized scheduler, and lazy verification oracle. Empirical results demonstrate significant backdoor suppression with zero utility degradation even when invoking the verification oracle on merely 10% of the total training steps. This approach yields a provably sound and computationally efficient defense for safety-critical AI.

Issam Seddik, Sami Souihi, Mohamed Tamaazousti +1

Université Paris-Saclay, CEA LIST, Palaiseau, France

Algorithmic Auditing Backdoor Attacks Decentralized Learning Backdoor Defense Distributed Training

Jul 7, 2026cs.LG

Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor

The community has recently developed various training-time defenses to counter neural backdoors introduced through data poisoning. In light of the observation that a model learns poisonous samples responsible for the backdoor easier than benign samples, these approaches either use a fixed threshold of the training loss for splitting or iteratively learn a reference model as an oracle for identifying benign samples. In particular, the latter has proven effective for anti-backdoor learning. Our method, HARVEY, leverages a similar yet crucially different technique: learning an oracle for poisonous rather than benign samples. Learning a backdoored reference model is significantly easier than learning a reference model on benign data. Consequently, we can identify poisonous samples much more accurately than related work identifies benign samples. This crucial difference enables near-perfect backdoor removal as we demonstrate in our evaluation. HARVEY substantially outperforms related approaches across attack types, datasets, and architectures, lowering the attack success rate to the very minimum at a negligible loss in natural accuracy. The figure below shows an overview of our methods working principle.

Qi Zhao, Christian Wressnegger

KASTEL Security Research Labs · Karlsruhe Institute of Technology (KIT)

Backdoor Attacks Backdoor Detection Backdoor Defense Data Poisoning Attacks

Jul 2, 2026cs.AI

DRL-CLBA: A Clean Label Backdoor Attack for Speech Classification via DDPG Reinforcement Learning

Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time. While sample-specific attacks can bypass many defenses, they often rely on poisoned label attack, making them detectable via manual data defense. In this paper, we propose DRL-CLBA, a novel clean label backdoor attack for speech classification that leverages Deep Deterministic Policy Gradient (DDPG) reinforcement learning. We also utilize deep audio steganography to embed sample-specific triggers into source audio, creating feature-space anchors. The proposed reinforcement learning framework effectively optimizes target samples toward trigger-bearing anchor points in the model's deep latent space, enabling label-migration-free poisoning of target samples. Experimental results across three datasets and four different DNNs demonstrate that DRL-CLBA achieves a high attack success rate, effectively bypassing some backdoor defenses. The attack demonstrates strong resistance against fine-tuning, pruning, and spectral signature defenses, exposing critical vulnerabilities in speech-controlled systems.

Yueming Huang, Wenhan Yao, Fen Xiao +2

Xiangtan University, Yuhu District Xiangda Road, Xiangtan, 411100, Hunan, China · Peking University, No.5, Summer Palace Road, Haidian District, Beijing, China, Beijing, 100871, Beijing, China

Backdoor Attacks Deep Deterministic Policy Gradient Audio Classification

Jul 2, 2026cs.CR

Pmeta-TLA: Backdoor Attacks for Speech Classification Models via Meta-Learning with Timbre Leakage Attack

Recently, speech classification methods have gained widespread adoption in intelligent gadgets. Current study indicates that backdoor attacks provide a substantial security concern to these models, underscoring the pressing necessity to investigate additional potential attack techniques to expose and prevent such risks. This work discusses the vulnerability of current speech triggers to detection by deep neural network defenders and introduces the Timbre Leakage Attack (TLA). The suggested trigger disseminates timbre information at the frame level within the deep self-supervised features, producing poisoned samples that appear natural to human perception. Furthermore, we introduce Pmeta-TLA, an innovative training mechanism for embedding numerous backdoors one time. This method proposes a multi-backdoor injection training strategy using meta-learning and Projected Conflicting Gradients (PCGrad) and introduces TLA as a multi-target attack tool within it. We performed tests on data-poisoning backdoor attacks in keyword spotting tasks utilizing some deep neural network models. Experimental results indicate that the proposed strategy attains superior Attack efficacy, enhanced stealthiness, robustness, and a reduced attack cost relative to baseline methods.

Yueming Huang, Wenhan Yao, Fen Xiao +2

Xiangtan University, Yuhu District Xiangda Road, Xiangtan, 411100, Hunan, China · Peking University, No.5, Summer Palace Road, Haidian District, Beijing, China, Beijing, 100871, Beijing, China

Backdoor Attacks

Jun 29, 2026cs.NI

Wireless Backdoor Attack and Defense for Semantic Communications over Multiple Access Channel

Semantic communication (SemCom) aims to preserve semantic meaning and task-oriented information beyond conventional message recovery over wireless channels. The adoption of SemCom in shared-access wireless networks introduces new vulnerabilities for multi-user semantic inference. This paper considers a SemCom system for two transmitters communicating with a common receiver over a multiple access channel. Each transmitter maps source information into latent semantic representations, while the receiver jointly reconstructs and classifies the semantic information for both transmitters. A selective over-the-air backdoor (Trojan) attack is presented in which an adversary transmits a low-power trigger waveform over the air and injects it into the shared received signal during training. By transmitting the trigger again during testing, this stealthy, low-power attack selectively manipulates the semantic inference for one transmitter while minimally affecting the inference of the other transmitter. To mitigate this vulnerability, a trigger-aware defense mechanism is developed to preserve correct semantic labels under trigger-contaminated wireless observations. The results demonstrate both the vulnerability of shared-access SemCom systems to selective over-the-air backdoor attacks and the effectiveness of trigger-aware robust training for semantic protection.

Yalin E. Sagduyu, Tugba Erpek, Aylin Yener +1

Nexcepta, Gaithersburg, MD, USA · The Ohio State University, Columbus, OH, USA · University of Maryland, College Park, MD, USA

Backdoor Attacks Semantic Communication Backdoor Defense Wireless Communications

Jun 27, 2026cs.SD

Clustering Unsupervised Representations as Defense against Poisoning Attacks on Speech Commands Classification System

Poisoning attacks entail attackers intentionally tampering with training data. In this paper, we consider a dirty-label poisoning attack scenario on a speech commands classification system. The threat model assumes that certain utterances from one of the classes (source class) are poisoned by superimposing a trigger on it, and its label is changed to another class selected by the attacker (target class). We propose a filtering defense against such an attack. First, we use DIstillation with NO labels (DINO) to learn unsupervised representations for all the training examples. Next, we use K-means and LDA to cluster these representations. Finally, we keep the utterances with the most repeated label in their cluster for training and discard the rest. For a 10% poisoned source class, we demonstrate a drop in attack success rate from 99.75% to 0.25%. We test our defense against a variety of threat models, including different target and source classes, as well as trigger variations.

Thomas Thebaud, Sonal Joshi, Henry Li +4

Center for Language and Speech Processing, Johns Hopkins University, USA · Faculty of Information Technology, Brno University of Technology, Czechia

Backdoor Attacks Automatic Speech Recognition Backdoor Defense Data Poisoning Attacks

Jun 24, 2026cs.CR

TEMPO-Diffusion: Temporally Exposed Malicious Poisoning of Diffusion Models

Noise-based backdoor attacks on diffusion models typically rely on input-time trigger injection, untargeted activation, and out-of-distribution target generation. Such assumptions reduce both the stealthiness and the practical relevance of these attacks. In this work, we present TEMPO-Diffusion, a targeted backdoor framework that localizes the malicious distribution shift to a temporal, in-distribution exposure. TEMPO-Diffusion supports: (i) targeted attacks on and to specific classes, (ii) multiple sub-image backdoors that reconstruct specific features within multiple, different output images and at multiple locations, and (iii) in-painting with time-conditioned triggers. To study relevant, practical security concerns in leveraging backdoored diffusion models for synthetic training data, we also introduce CALISA: a balanced, region-aware traffic-sign dataset emphasizing Canadian and U.S. road signs. Across CIFAR10, GTSRB, and CALISA, our experiments show that TEMPO-Diffusion can reliably poison class-specific synthetic data generation and induce high attack success rates in downstream classifiers trained on that data.

William Aiken, Paula Branco, Guy-Vincent Jourdan +1

School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON K1N 6N5, Canada

Backdoor Attacks Diffusion-Based Image Generation Data Poisoning Attacks

Jun 24, 2026cs.CR

Color Matters: Trigger Color Affects Success in Federated Backdoor Attacks

Federated learning is vulnerable to backdoor attacks in which malicious clients inject poisoned updates while preserving benign-task performance. In this paper, we study a semantics-driven backdoor mechanism in which attackers use natural visual accessories as triggers and manipulate only the trigger color while keeping the attack pipeline fixed. Our framework considers semantic trigger objects such as masks and sunglasses, instantiated in black and white variants, and evaluates their effect in a controlled federated learning setting. Malicious clients construct poisoned samples by applying a trigger to source-class images and relabeling them to an attacker-chosen target class, while benign clients train only on clean data. We analyze this mechanism under both a standard poisoning objective and a stronger SABLE-based objective that combines clean classification loss, triggered target loss, feature-separation loss in the penultimate representation space, and regularization to keep malicious updates close to the global model. This design enables the attack to remain effective while reducing excessive update drift. Experiments on a four-class CelebA hair-color task show that trigger color significantly changes attack success rate even when trigger semantics, placement, and poisoning budget are unchanged. White triggers are more effective for attacks targeting the blond class, whereas black triggers perform better for attacks targeting the black class. The same trend persists under robust aggregation, showing that trigger color is a meaningful factor in the operation, persistence, and evaluation of semantic backdoor mechanisms in federated learning.

Kavindu Herath, Joshua C. Zhao, Saurabh Bagchi

Department of Electrical and Computer Engineering, Purdue University, West Lafayette, USA

Backdoor Attacks Backdoor Attacks in Federated Learning Federated Learning

Jun 22, 2026cs.CR

TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger

Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor attacks. However, existing backdoor methods face critical trade-offs among key factors: attack performance, stealthiness, time complexity, and required poison rates. For example, achieving high attack performance typically demands a high poison rate and prolonged training, which undermines stealthiness, making the attack more detectable by backdoor defenses. This paper proposes TooBad (trigger optimization for backdoor diffusion models), a backdoor framework which introduces a novel DM-tailored trigger optimization technique to dramatically enhance the performance of backdoor attacks on DMs. Experiments on representative benchmarks such as CIFAR-10 show that TooBad can achieve high ASRs (

> 85

%) at only 0.5% poison rate, significantly lower than the 10% typically required by prior work on the same datasets. At 5% poison rate, TooBad reaches nearly 100% ASR within just 3-5 backdoor injection epochs, whereas existing methods need at least 30-50 epochs at double the poison rate for comparable results. Despite its potency, TooBad easily evades SOTA defenses and maintains high utility. These results reveal a critical threat on DMs and highlight the need for more robust defenses against such stealthy yet efficient attacks.

Vu Tuan Truong, Long Bao Le

INRS, University of Quebec

Backdoor Attacks Diffusion Models

Jun 22, 2026cs.LG

Rethinking Molecular Graph Backdoors under Chemistry-aware Admission

Backdoor attacks on molecular graph neural networks (GNNs) are typically evaluated as abstract graph edits, but real molecular learning pipelines do not train on arbitrary graphs. Molecular records must first survive parsing, sanitization, canonicalization, and graph-string consistency checks. We formalize this overlooked admission stage as ChemGuard, an operational protocol for testing whether a submitted molecular record can enter a realistic learning pipeline, while complementing existing defenses. ChemGuard admits a record only when its molecular string is sanitizable and the graph reconstructed from that string matches the submitted molecular graph. Under this operational view, many existing graph-based backdoors lose much of their apparent efficacy because their poisons are chemically invalid or representation-inconsistent. We then show that admission checks alone are insufficient to rule out molecular backdoors. We propose ChemBack, an admission-aware molecular backdoor attack that constructs chemically feasible motif-anchor attachments and ranks admitted candidates by fingerprint-based Tanimoto similarity to clean target-class molecules. ChemBack is model-free during trigger selection, using molecular structures, target labels, fingerprints, and public validity checks, but no victim model, surrogate GNN, learned embedding, gradient, logit, or training-code access. Across molecular benchmarks, validators, architectures, and defenses, \textbf{ChemBack} achieves high attack success with fully admitted poisons while preserving clean accuracy. Our results reveal a two-sided lesson, chemistry-aware admission suppresses many graph-only backdoors, yet chemically valid and target-aligned molecular backdoors remain a practical threat.

Thinh T. H. Nguyen, Sze Jue Yang, Khoa D. Doan +2

VinUniversity, Hanoi, Vietnam · Universiti Malaya

Graph Neural Networks Backdoor Attacks Backdoor Defense

Jun 22, 2026cs.LG

CLIP-guided Diffusion Model for Backdoor Generation in Sensor-based Human Activity Recognition

Sensors are critical components of modern intelligent devices. The proliferation of the Internet of Things (IoT) and wearable mobile devices has enabled the integration of such sensors to monitor the environment and enable users to take predictive actions. Human activity recognition (HAR) is a popular application in which Inertial Measurement Unit (IMU)-based sensors, such as accelerometers and gyroscopes, are used to provide insights into health, training, and medical diagnosis. However, the accuracy of such a model is hindered by the lack of data. The diffusion model-based technique has proven successful in generating synthetic data for training HAR models. In this paper, we propose a backdoor training technique, IMU-DM-CLIP, that leverages a diffusion model to enable trigger-based attacks on HAR models. Our empirical analysis shows that the attack is successful even with a very small backdoor injection rate of 10% and 10% of the data guided for the diffusion model.

Toby Briston, Illya Kosyk, Kuniyih S

Human Activity Recognition Backdoor Attacks

Jun 19, 2026cs.CV

BadDreamer: Transferable Backdoor Attacks against Video World Models for Autonomous Driving

Video world models are increasingly used in autonomous driving to forecast future scene evolution and provide future-aware spatio-temporal representations for downstream action prediction. In perception-to-action pipelines, these representations can directly influence ego-vehicle waypoint planning, making the learned future dynamics a critical security-sensitive component. Despite their promise, the training-time security risks of autonomous-driving video world models remain largely unexplored. We present BadDreamer, a transferable spatio-temporal backdoor attack that targets the perception side of this pipeline. Unlike conventional backdoors that manipulate image labels, prompt outputs, or action supervision, BadDreamer poisons the learned transition dynamics of a video world model. It constructs trigger-erasure sequences in which an oncoming yellow delivery rider is visible in the observed context frames but erased from the future frames. After fine-tuning on a small fraction of such sequences, the compromised world model learns a hidden conditional association: when the physical trigger appears, it hallucinates a future where the rider disappears and the road appears clear. We further show that this corrupted future-aware representation can transfer to the downstream action module without directly modifying ego-trajectory labels, inducing unsafe non-evasive waypoint predictions. Our experiments instantiate this attack on a representative open-source perception-to-action pipeline, revealing a representation-level safety risk in autonomous-driving video world models and highlighting the need for backdoor-aware validation beyond clean generation quality.

Zhe Shuai, Xiaopeng Xie, Yikun Zeng

Shanghai Jiao Tong University

Backdoor Attacks Autonomous Driving World Models for Autonomous Driving Video World Models

Jun 19, 2026cs.SD

Backdoor Attacks on Speech Emotion Recognition via TTS-Generated Poisoning

Speech Emotion Recognition (SER) systems increasingly leverage self-supervised acoustic representations, yet their vulnerability to training-time attacks remains largely underexplored. This paper presents the first systematic study of poisoning-based backdoor attacks on SER, with a focus on threats enabled by text-to-speech (TTS) generated audio. We introduce a stealthy, low-energy acoustic trigger that can be embedded imperceptibly into both natural and synthetic speech, enabling scalable and consistent poisoning. Our experiments demonstrate that SER models can be reliably compromised with high attack success rates under low poisoning ratios, while maintaining near-clean performance on benign inputs. We further show that backdoor patterns exhibit strong cross-model transferability and that self-supervised representations are particularly susceptible to learning these triggers. These findings reveal that TTS technology dramatically lowers the barrier to effective backdoor attacks, exposing critical vulnerabilities in modern SER pipelines and motivating the urgent need for dedicated defenses.

Yongbin Huang, Xihao Xie, Jia Zhang

Department of Computer Science Southern Methodist University Dallas, USA

Backdoor Attacks Speech Emotion Recognition Data Poisoning Attacks

Jun 18, 2026cs.CV

Mirage: a Clean-Label Backdoor against LiDAR 3D Object Detection

Deep neural network-based LiDAR 3D object detection serves as a critical perception component in safety-critical autonomous systems. However, recent studies have revealed its vulnerability to backdoor attacks. Existing attacks typically require white-box access or label modification and focus on geometric attacks such as object disappearance or bounding-box manipulation. In this paper, we present Mirage, a black-box and clean-label backdoor attack against deep neural network-based LiDAR 3DOD. Mirage injects a small number of label-consistent poisoning samples into the training set, causing the model to learn a malicious association between a trigger pattern and an attacker-chosen target class while preserving normal training semantics. As a result, the compromised model behaves normally on benign inputs yet systematically misclassifies triggered objects as the target class during deployment. We evaluate Mirage on multiple state-of-the-art LiDAR 3DOD models and benchmark datasets. Experimental results show that Mirage achieves a 73% misclassification success rate with a poisoning rate of only 0.5%, while maintaining detection performance close to that of benign models.

Ziba Parsons, Ang Li

Computer and Information Science University of Michigan - Dearborn Dearborn, MI 48170

Lidar-Based 3D Object Detection Backdoor Attacks 3D Object Detection Airborne Laser Scanning

Jun 17, 2026cs.CR

FloatDoor: Platform-Triggered Backdoors in LLMs

Large language models (LLMs) are increasingly deployed in sensitive settings such as software engineering, where their outputs directly shape downstream artifacts. Recent work has shown that an identical model can produce measurably different outputs depending on the deployment platform, a consequence of non-associative floating-point arithmetic and divergent kernel implementations. We study the security implications of this platform-dependent variability and uncover a novel attack surface on LLM deployments. We introduce FloatDoor, the first input-independent, platform-triggered backdoor attack against generative LLMs. The compromised model exhibits adversary-chosen behavior when served on a target platform and is otherwise benign. FloatDoor is realized through two lightweight LoRA adapters, one that amplifies inter-platform numerical divergence and one that binds the resulting platform signature to a malicious downstream task, while leaving aggregate model utility largely intact. FloatDoor exploits a pronounced time-of-check, time-of-use gap between model auditing and serving. We demonstrate FloatDoor on Qwen3-4B across a broad range of deployment targets, including NVIDIA GPUs, Google TPUs, AWS Graviton, and Alibaba Yitian-710. As a final case study, we show that FloatDoor reliably induces exploitable code vulnerabilities on a chosen target platform. Our results establish a new class of attacks on LLM deployments and underscore the pressing need for trusted model supply chains in sensitive, LLM-powered applications.

Nils Loose, Jonas Sander, Felix Mächtle +1

University of Luebeck

LLM Backdoor Attacks Backdoor Attacks LLM Security

Jun 16, 2026cs.CR

Beyond Native Success: Auditing Deployment-Interface Exposure of CLIP Backdoors

Contrastive Language-Image Pre-training models are widely reused across downstream interfaces, including feature extraction, retrieval, reranking, and selection. Existing CLIP backdoor, however, usually validate attacks on a small attack-native task, leaving unclear whether the same poisoned checkpoint remains exposed, weakens, or becomes not applicable when reused through other interfaces. We introduce DIFE, a Deployment-Interface Footprint Evaluation framework that audits backdoored CLIP checkpoints across deployment interfaces. DIFE makes various evaluations comparable by specifying each interface's component readout, trigger channel, target event, reference condition, and metric. DIFE also introduces effective-footprint diagnosis to identify the reusable CLIP component or component combination that carries exposure and explains where risk transfers. Auditing reproduced CLIP backdoors with DIFE reveals a structured landscape: native success is not a checkpoint-level risk certificate, exposure follows component footprints, text-side poisoning does not yield textual-encoder control, and some coupled attacks remain mechanism-bound. This audit reveals a import gapin existing CLIP backdoors: a textual encoder that itself becomes a reusable carrier of adversarial behavior. We therefore introduce BadTextTower to fill this gap. BadTextTower produces strong text-conditioned retrieval, reranking, and selection exposure while leaving visual-only reuse nearly clean.

Kunlan Xiang, Haomiao Yang, Wenbo Jiang

University of Electronic Science and Technology of China

VLM Robustness Adversarial Attacks on VLMs Backdoor Attacks Backdoor Attacks on VLMs Vision-Language Pretraining

Jun 12, 2026cs.CR

Continual Backdoor Training in IoT/CPS

Internet of Things (IoT) and Cyber-physical systems (CPS) increasingly rely on continual learning (CL) to adapt to evolving environments, device heterogeneity, and concept drift, thereby improving overall utility. While continual adaptation is essential for long-lived IoT deployments where data patterns evolve, it also introduces new security vulnerabilities. In particular, backdoor attacks can exploit incremental updates, replay buffers, and representation reuse to implant persistent malicious behaviors that remain dormant during normal operation but activate upon specific triggers. In this paper, we present a backdoor attack in continual learning used in IoT/CPS systems. To this end, we formalize an IoT/CPS-specific threat model, analyze why continual learning amplifies backdoor persistence in IoT pipelines, and evaluate our technique under varying conditions. Our analysis highlights critical open challenges in securing lifelong learning in IoT/CPS and industrial IoT (IIoT) environments, as well as the need for heightened security controls.

Oxana Salish, Kuniyilh S

Backdoor Attacks Continual Learning Cybersecurity

Jun 11, 2026cs.LG

PolicyGuard: Towards Test-time and Step-level Adversary (Backdoor) Defense for Reinforcement Learning Agent

While real-world applications of reinforcement learning (RL) are becoming increasingly popular, the security of RL systems deserve more attention and exploration. In particular, recent work has revealed that RL agents are vulnerable to backdoor attacks, where a victim agent behaves normally under standard conditions but executes malicious actions when a specific trigger is activated. Existing backdoor defenses for RL either require access to the agent's internal parameters, operate only at the model or trajectory level, or are limited to specific attack types. To ensure the security of RL agents, we propose \texttt{PolicyGuard}, a \textit{test-time step-level} backdoor defense which leverages Gaussian Process (GP) posterior variance and adapts pseudo trajectories to enable uncertainty computation for individual time step. Besides, we also provide theoretical foundations to explain the efficacy of GP posterior variance. Extensive experiments across seven RL games demonstrate that PolicyGuard achieves state-of-the-art detection performance in most cases, with average AUROC of 0.856 for perturbation-based attacks and 0.859 for adversary-agent attacks.

Junfeng Guo Heng Huang

Computer Science, University of Maryland College Park, USA.

Backdoor Attacks Backdoor Defense Robust RL

Jun 8, 2026cs.RO

Targeting World Models to Compromise Robot Learning Pipelines

World models have recently seen a rapid growth in both their popularity and capability as more data efficient tools for generating robot training data or simulating real world environments, with many works proposing their integration into the robot learning pipeline. While highly practical, in this work we demonstrate that world models introduce a uniquely stealthy and effective data poisoning entry point into the robot learning supply chain that can result in the deployment of unsafe or otherwise compromised robotic policies despite training on seemingly safe ground truth training data. In contrast to traditional data poisoning techniques which directly implant dangerous trajectories into sold or uploaded datasets, our novel attack methods inject malicious prompts or compromising transition dynamics into visibly safe teleoperated datasets which are only activated once fed through a world model as input. This can result in the generation of synthetic, dangerous robot training trajectories and subsequently unsafe or compromised robot policies. We demonstrate the effectiveness of our attacks against both state of the art action conditioned and text conditioned world models, showing a full end-to-end backdoor on a downstream DRL policy and a proof-of-concept for the VLA setting. Overall these findings necessitate research into more secure world models and reevaluating their position within the robot learning supply chain.

Ethan Rathbun, Ahmed Agha, Saaduddin Mahmud +3

Northeastern University · University of Massachusetts Amherst

Robot Policy Learning World Models for Robotics Backdoor Attacks Robot Safety Data Poisoning Attacks

Jun 2, 2026cs.CR

Patcher: Post-Hoc Patching of Backdoored Large Language Models

Large language models remain vulnerable to jailbreak backdoor attacks, where adversaries poison safety alignment data to embed hidden triggers that bypass safety mechanisms. Existing defenses often require comprehensive attack information or multiple triggered examples, making them impractical when defenders only observe a single reported failure case without knowing whether it stems from a backdoor attack or a natural alignment bug. This paper presents Patcher, a post-hoc defense framework that repairs backdoored language models using only a single reported failure case and the model parameters. Patcher operates in two stages. First, it localizes backdoor triggers by computing response-conditioned gradient-based saliency scores and applying adaptive clustering to separate triggers from benign context. Second, it patches the model through a constrained fine-tuning objective that breaks the trigger-response association while preserving benign-task utility and robustness to non-triggered jailbreak attacks through KL-divergence constraints. We conduct extensive evaluations across multiple backdoor attack strategies and demonstrate that Patcher successfully localizes triggers and neutralizes backdoors while maintaining model utility. We further show robustness against adaptive attacks designed to evade our defense. This work represents a significant step toward practical defenses against training-time attacks in deployed language models.

Anjun Gao, Yueyang Quan, Yufei Xia +2

University of Louisville · University of North Texas

LLM Backdoor Attacks Backdoor Attacks Backdoor Defense in LLMs LLM Security Backdoor Defense

May 29, 2026cs.CR

BadBone: Backdoor Attacks Against Backbone Models in Visual Prompt Learning

Prompt learning is a new machine learning paradigm that has attracted ample attention due to its simplicity and proven efficacy. Despite its growing adoption, the security vulnerabilities associated with this paradigm remain underexplored. In this work, we take the first step to propose BadBone, a stealthy and adaptive backdoor attack against prompt learning using bi-level optimization. Instead of backdooring the prompt learning process, we aim to compromise a backbone model such that only target downstream tasks employing prompt learning inherit the backdoor vulnerability. Extensive experiments on three different models and three datasets from various domains show that our targeted/untargeted backdoored models achieve high attack performance while maintaining utility on both pre-training and downstream tasks. Moreover, we evaluate our approach against six state-of-the-art model-level defenses, including Neural Cleanse, ABS, MNTD, NAD, CLP, and D-BR. The results demonstrate that these defenses are largely ineffective against our backdoored models and thus leave the effective defense as an important direction for future work.

Ziqing Yang, Rui Wen, Xinlei He +3

1CISPA Helmholtz Center for Information Security · Institute of Science Tokyo · 3Wuhan University +1

Adversarial Attacks Backdoor Attacks Visual Prompt Learning

May 27, 2026cs.LG

Density-aware Sample-specific Attack

Despite recent progress in backdoor attacks, existing methods remain susceptible to post-training defenses that erase the backdoor through fine-tuning or pruning. We revisit the core objectives of backdoor attacks and derive principled criteria characterizing optimal sample-specific trigger construction under a Bayes-optimal model of the victim's training. Our analysis reveals that both attack success and clean-accuracy preservation are simultaneously optimized when triggered samples are steered into low-density regions of the clean data distribution, a distributional condition that controls all moments of the poisoned distribution at once rather than a handful of input-space summary statistics. We introduce a bilevel optimization framework that estimates density ratios via conditional time-score matching and optimizes a mixture-model objective to place triggered samples in these sparse regions. Extensive evaluations on MNIST, CIFAR-10, GTSRB, and TinyImageNet demonstrate that our method achieves above 99% attack success rate before defense and retains 50--85 percentage points higher post-defense ASR than the strongest baselines under fine-tuning defenses. Against neuron-pruning defenses, the method exhibits complete immunity, with zero neurons identified for removal across all pruning thresholds. These results expose a fundamental gap in current defense paradigms and underscore the need for defenses that operate beyond the support of the clean distribution.

Qiyuan Wang, Yao Li, Raymond K. W. Wong

Texas A&M University · University of North Carolina at Chapel Hill

Backdoor Attacks Adversarial Robustness Data Poisoning Attacks

May 26, 2026cs.CR

Backdoor Attacks on Fault Detection and Localization in Cyber-Physical Systems

Cyber-Physical Systems (CPS) integrate sensing, communication, computation, and control to support critical infrastructure, including smart grids, industrial automation, and control systems. In the electrical utility domain, various controllers are used in CPS to ensure the system detects and recovers from faults, such as voltage fluctuations, and to perform load balancing in distribution systems. Machine learning- and deep learning-based fault detection and localization frameworks have recently gained significant attention in CPS for their ability to identify anomalies and operational failures in real time. However, these intelligent models are vulnerable to adversarial machine learning attacks, particularly backdoor attacks. In a backdoor attack, an adversary injects malicious patterns into the training data so that the model behaves normally most of the time but produces attacker-controlled outputs when triggered by specific patterns. This paper investigates the threat of backdoor attacks against fault detection and localization mechanisms in recent ML pipelines used in modern CPS systems. We define these threats and explore how they can be realized by designing triggers and evaluating their success in the CPS domain. Our experiments show the attack is successful even with 10% of poisoning.

Abile Jean, Kuniyilh S

Cyber-Physical Systems Backdoor Attacks Data Poisoning Attacks Anomaly Detection

May 21, 2026cs.LG

When Stronger Triggers Backfire: A High-Dimensional Theory of Backdoor Attacks

Backdoor poisoning attacks behave counter-intuitively in high dimensions: stronger training triggers can help the defender. We study regularised generalised linear models on Gaussian-mixture data in the proportional regime (

p/n \to κ

), varying the training trigger strength

α

against a fixed test trigger. Three phenomena emerge: (i) clean test accuracy increases with

α

; (ii) attack success peaks at a finite

α

and then declines; and (iii) the most damaging trigger direction is the minimum eigenvector of the data covariance. We prove all three results in closed form for the squared loss, and extend (i) and (ii) to general convex GLM losses via a Gaussian-proxy fixed-point system. We identify a finite-sample noise floor proportional to

κ

as the mechanism behind (i), invisible to classical

n \gg p

analysis. Experiments on CIFAR-10 and Gaussian surrogates match the theory closely; ResNet-18 experiments show the same phenomena beyond the convex setting.

Donald Flynn, Hadas Yaron Goldhirsh, Jonathan P. Keating +1

1Mathematical Institute, University of Oxford · School of Mathematical Science, Tel Aviv University · School of Mathematical Science and Computer Science, Tel Aviv University

Backdoor Attacks Statistical Learning Theory Generalized Linear Models Data Poisoning Attacks

May 21, 2026cs.CR

TimeGuard: Channel-wise Pool Training for Backdoor Defense in Time Series Forecasting

Time Series Forecasting (TSF) is highly vulnerable to backdoor attacks, yet effective defenses remain underexplored due to challenges arising from data entanglement and shifts in task formulation. To fill this gap, we conduct a systematic evaluation of thirteen representative backdoor defenses across the TSF life cycle and analyze their failure modes. Our results reveal two fundamental issues: (1) data entanglement induces channel-level signal dilution, rendering sample-filtering and trigger-synthesis defenses ineffective at localizing backdoors; and (2) task-formulation shift leads to training-loss degeneration, causing poisoned and clean windows to become indistinguishable at training stages. Based on these findings, we propose a training-time backdoor defense for TSF, termed TimeGuard. Our method adopts channel-wise pool training as the core paradigm and initializes a high-confidence pool using time-aware criteria to mitigate signal dilution. Moreover, we introduce distance-regularized loss selection to progressively expand the reliable pool during training and ease loss degeneration. Extensive experiments across multiple datasets, forecasting architectures, and TSF backdoor attacks demonstrate that TimeGuard substantially improves robustness, boosting

\mathrm{MAE}_\mathrm{P}

by

1.96\times

over the leading baseline, while preserving clean performance within 5%

\mathrm{MAE}_\mathrm{C}

.

Quang Duc Nguyen, Siyuan Liang, Yiming Li +2

College of Computing and Data Science, Nanyang Technological University, Singapore.

Backdoor Attacks Time Series Forecasting Training Data Selection Backdoor Defense

May 20, 2026cs.CR

Trusted Weights, Treacherous Optimizations? Optimization-Triggered Backdoor Attacks on LLMs

Inference optimization aims to minimize the latency and resource consumption of LLM inference while preserving output quality, making large-scale deployment practical and cost-effective. However, optimized execution can introduce small numerical inconsistencies from the original model. We reveal that this inconsistency not only causes the model's outputs to diverge, but more critically can introduce hidden backdoors. The backdoor remains dormant under standard unoptimized execution and is activated only when inference optimization is enabled, allowing it to evade existing backdoor detection pipelines. We first introduce the Input-Specific Optimization Backdoor (ISOB) to demonstrate that optimization-induced differences can cause wrong predictions. However, ISOB remains input-specific and cannot establish a universal optimization-triggered backdoor. To overcome this limitation, we design the Universal Optimization Backdoor (UOB). The backdoored model stays benign under unoptimized execution but activates when inference optimization is enabled. We conduct extensive experiments across seven mainstream open-source LLMs, four tasks, and three optimization backends. UOB reaches up to 100% attack success while largely preserving clean accuracy. To mitigate this vulnerability, we design three defense methods that reduce the backdoor ASR to at most 0.02 while preserving clean accuracy. These results reveal inference optimization as a new LLM security attack surface and motivate defenses against test-deployment disagreement.

Yifei Wang, Yida Yang, Tianlin Li +3

Shanghai Jiao Tong University · Tongji University · Beihang University +1

LLM Backdoor Attacks Backdoor Attacks LLM Security Backdoor Defense