Adversarial Attacks

Follow this topic Ask about this topic

Momentum

28 papers in the last four weeks, up 155% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 292

Jun 28, 2026cs.SD

Proteus: Automated Adversarial Robustness Testing for Audio Deepfake Detectors

We present Proteus, a framework developed at Resemble AI for automated robustness testing of our audio deepfake detection system. Given a detector, Proteus systematically searches over sequences of everyday audio transformations (codec transcoding, additive noise, reverberation, dynamic-range compression, and VoIP simulation) to find combinations that fool the detector while preserving speech quality. We propose two complementary search strategies: (1) a breadth-first search that exhaustively maps augmentation effectiveness across the parameter space, and (2) a Q-learning agent designed to efficiently discover deeper attack chains by exploiting structural patterns in the BFS data. We report findings from continuous deployment of Proteus against our production detector, showing that specific augmentation chains can reliably flip detection verdicts while preserving speech intelligibility and speaker identity. We discuss how these findings are used to harden the detector through targeted retraining.

Nicolas M. Müller, Aditya Tirumala Bukkapatnam, Zohaib Ahmed

Resemble AI, Mountain View, CA, USA

Audio Deepfake Detection Adversarial Attacks Adversarial Robustness Black-Box Adversarial Attacks

Jun 28, 2026cs.CV

The Platonic Defense: Backdoor Defense for Self-Supervised Encoders in the Era of Large Scale Pre-training

Self-supervised learning (SSL) pretrained models have become a dominant paradigm for visual representation learning, but they are vulnerable to backdoor attacks. Existing defenses struggle to defend against such attacks in a fully black-box setting because they often require access to labels, attack patterns, or training data. To tackle this issue, we propose a new attack-agnostic, model-agnostic, and modality-agnostic black-box test-time defense paradigm, called \emph{Platonic Representation Defense}. It is inspired by the Platonic Representation Hypothesis, which suggests that large-scale independently trained encoders converge toward compatible projections of the same underlying reality. We formalize this idea as a conditional energy function defined over source representations and a set of reference representations. The energy function is trained for detection through noise-contrastive estimation and for representation purification through denoising score matching. Theoretically, the energy gap between matched and mismatched samples is lower bounded by the mutual information between source and reference representations. We demonstrate the effectiveness of our method on multiple self-supervised encoders and more than 10 attacks. The method can perform both representation detection and purification, and achieves substantial performance gains across multiple attacks. Code is available here.

Tuo Chen, Minjing Dong, Benlei Cui +2

Southeast University · Ant Group · City University of Hong Kong +2

Adversarial Attacks Self-Supervised Visual Representation Learning

Jun 27, 2026cs.IR

Fairness Attacks on Recommender Systems

The unfairness of recommender systems has become a topic of concern due to its significant social and ethical implications. Although existing works have shown the effectiveness of attacks on the performance of recommender systems (e.g., promotion and demotion attack), the study of fairness attacks on recommender systems remains largely under-explored. To this end, we propose a novel structure-aware reinforcement learning-based fairness attack method designed to exacerbate the unfairness of target recommender systems. Specifically, we first employ a graph-based structure encoder to model the structural dependencies among the generated fake user-item interactions and the original user-item interactions. Then, we model the sequential dependency of the injected fake items using a recurrent neural network. Based on the learned structure-aware and sequence-aware representations of the fake user and item, the item selection policy attentively decides the next injected fake item. Since the target recommender system may employ fairness-aware training and leverage the user's sensitive attribute information, such as gender, we further designed a gender selection policy to decide the gender of the entire fake user profile. Both the item selection and gender selection policy are learned jointly in our proposed method. Finally, experimental results on four types of target recommendation models and two real-world datasets demonstrate the effectiveness of the proposed attack method in exacerbating the unfairness of recommender systems.

Yanan Wang, Yong Ge

Department of Information Systems and Operations Management, College of Business, The University of Texas at Arlington · Department of Management Information Systems, Eller College of Management, the University of Arizona

Adversarial Attacks Algorithmic Fairness Recommender Systems Data Poisoning Attacks

Jun 26, 2026cs.CR

PLAA: Packet-level Adversarial Attacks in Network Traffic Detection

Deep neural networks (DNNs) are widely applied in Network-based Intrusion Detection System (NIDS) due to their high accuracy. However, DNNs are highly susceptible to adversarial attacks, which generate malicious traffic to evade NIDS detection. Existing approaches often adapt adversarial attacks from computer vision (CV) tasks to the NIDS domain, overlooking the fundamental differences between CV and NIDS. This results in two major issues: 1) The generated network traffic may become invalid, 2) The generated traffic may lose its original attack semantics. To address these issues, this paper proposes an adversarial attack specifically designed for NIDS. Instead of directly generating flow-level features, our approach incrementally generates packet-level features to construct adversarial traffic. During the generation process, the semantic integrity of the traffic is monitored at each stage, effectively avoiding the issues of invalid traffic and semantic loss observed in existing methods. We evaluate our attack algorithm against current NIDS models using the CIC-UNSW-NB15, CIC-DDoS2019, and CIC-IDS-2017 datasets. The proposed method achieves an average evasion success rate of 92.78%, while ensuring that the generated adversarial traffic remains semantically consistent with the original malicious traffic.

Jinhao You, Zan Zhou, Shujie Yang +3

Beijing University of Posts and Telecommunications · Zhongguancun Laboratory

Adversarial Attacks Network Intrusion Detection

Jun 26, 2026cs.SD

Room for Error: Large-Scale Simulation of Over-the-Air Acoustic Attacks

While voice control is rapidly becoming a ubiquitous vector of human-AI communication, the risks facing these systems remain poorly understood. This is, in part, a product of the difficulties in scaling strictly digital adversarial workflows to the physical world. These scale barriers have led the community to abstract away key acoustic factors relating to detectability and the influence of geometry on acoustics. These methodological and metrological shortcomings undermine our understanding of risk. We illuminate these issues through real-world testing, conceptual discussions, and a novel, high-throughput reality simulation framework. By testing over 8 million adversarial evaluations, we demonstrate that acoustic awareness yields relative Word Error Rate increases of up to 94.5% under Whisper and wav2vec. We employ this framework to explore a formalize and operationalize a Dual-Form Signal to Noise Ratio to decouple source stealth from victim attack efficacy, resolving a crucial limitation in current works. This lays the groundwork for repeatable, verifiable research that embraces, rather than abstracts, the acoustic environment.

Andrew C. Cullen, Neil G. Marchant, Jiani Xie +4

University of Melbourne · DST Group, Adelaide

ASR Evaluation Adversarial Attacks Physics-Based Simulation Physical Adversarial Attacks

Jun 25, 2026cs.AI

Vulnerability of Natural Language Classifiers to Evolutionary Generated Adversarial Text

Deep learning models have achieved impressive performance across various fields but remain vulnerable to adversarial inputs, particularly in NLP, where such attacks can have significant real-world consequences. Adversarial attacks often involve small, semantically similar token replacements to fool NLP models, and recent methods have become more precise by targeting specific vulnerable words, often by exploiting some level of access to the model's internal structure. This paper proposes GAversary, a hybrid Genetic Algorithm (GA) to generate adversarial attacks on natural language models. The GA is able to treat the target model as a black box, requiring only the logit value output by the model to guide the search. GAversary differs from GAs previously proposed for this problem by using GloVe embeddings to propose word replacements (the mutation operator) to improve the semantic similarity of the adversarial examples. GAversary is applied to several benchmark data sets and well-known target models. GAversary is able to substantially reduce the target model's accuracy on test data compared to the BAE and A2T attacks compared against (in the best case, reducing a 76.8% accuracy to 5.8%, compared to BAE's 27.6%). The trade-off is that GAversary perturbs just under twice as many words as the other two methods, with a slightly lower semantic similarity to the original text and around a 5% increase in run-time.

Manjinder Singh, Alexander E. I. Brownlee, Mohamed Elawady

Computing Science & Mathematics University of Stirling, Stirling, UK · Computer and Information Sciences University of Strathclyde, Glasgow, UK

Adversarial Attacks Black-Box Adversarial Attacks Adversarial Text Attacks

Jun 25, 2026cs.CR

Inherited Circuits, Learned Semantics: How Fine-Tuning Creates Evasion Vulnerabilities Invisible to Standard Evaluation

LLMs fine-tuned for security classification are usually evaluated on held-out examples from the same distribution as their training data. We show that this can miss vulnerabilities introduced by fine-tuning itself: models can learn token-level indicator semantics that preserve canonical accuracy while failing under behavior-preserving transformations such as PowerShell alias substitution, command reconstruction, string construction, execution indirection, and case mutation. We study Foundation-Sec-8B-Instruct and its base model, Llama-3.1-8B-Instruct, on matched PowerShell classification cohorts. Causal interventions localize the classification circuit to a late-attention route inherited from Llama rather than created by fine-tuning. Fine-tuning concentrates and semantically specializes this inherited structure, improving baseline behavior while creating transformation-sensitive attack surfaces. A three-tier evasion benchmark finds Foundation-Sec misses on iwr substitution, Invoke-Expression reconstruction, and case-mutated Invoke-Expression/IEX variants that Llama does not share. We also derive a pre-deployment monitoring method: a linear probe at the classification boundary and an indicator-token sign test identify command families where canonical indicators change role after fine-tuning. These signals prioritize red-team variant generation using only canonical inputs, showing that security fine-tuning can improve task accuracy while expanding the evasion surface. These results caution against treating small task-specific fine-tunes as straightforwardly safer security classifiers: specialization can convert inherited model structure into brittle indicator rules that preserve held-out accuracy while expanding the evasion surface. Robust AI-enabled security will require specifying the full transformation space of the task and monitoring semantic drift through fine-tuning.

Ryan Fetterman

Cisco Talos

Adversarial Attacks LLM Fine-Tuning Mechanistic Interpretability LLMs for Cybersecurity Adversarial Robustness of Language Models

Jun 25, 2026cs.CR

ShareLock: A Stealthy Multi-Tool Threshold Poisoning Attack Against MCP

With the rapid evolution of LLM-driven agents, Model Context Protocol (MCP), an open protocol bridging LLMs with external tools, has quickly become foundational to modern agent ecosystems. However, the expanding adoption of MCP has also introduced novel security concerns such as Tool Poisoning Attack (TPA), which exploit LLM-server interactions to inject malicious prompts. Existing poisoning schemes typically adopt a monolithic plaintext embedding paradigm, which fails to withstand manual inspection or automated detectors. Current research still lacks a systematic analysis on multi-tool poisoning, where multiple tools can be exploited cooperatively to disperse detection risk. In this paper, we introduce ShareLock, a multi-tool threshold poisoning framework that utilizes Shamir's threshold scheme to ensure exceptional stealth and fault tolerance. ShareLock distributes the malicious instruction as benign-looking secret shares across multiple tool descriptions, achieving both information-theoretic secrecy and attack robustness against moderate auditing. After a covert reconstruction trigger is planted during server update, the aggregated shares reconstruct the hidden instruction, resulting in critical breaches of system assets or private data. To evaluate the realistic threat of ShareLock, we constructed a comprehensive benchmark encompassing four multi-tool scenarios and conducted extensive experiments across mainstream LLMs on two distinct MCP clients. Our results demonstrate that ShareLock significantly outperforms existing single-tool poisoning strategies in tool description-based detection while maintaining an average attack success rate exceeding 90%.

Liwei Liu, Tianzhu Han, Zijian Liu +2

Shanghai Jiao Tong University · Shanghai, China

Adversarial Attacks MCP Security LLM Security Data Poisoning Attacks

Jun 25, 2026cs.CR

DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors

Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors. In this work, we first show that, despite claims, existing problem-space attacks remain largely impractical. Most techniques leverage software transplantation to inject entire benign modules, introducing many side-effect features and often causing build-time failures. Fine-grained methods that inject only a narrow subset of components exhibit limited effectiveness, while those that also use obfuscation rely on brittle bytecode rewriting, producing APKs that are syntactically valid but semantically unusable. Prior work further overestimates attack success rates by running smoke tests that only validate installation and basic execution, without assessing whether the modified APK still preserves its intended behavior. To overcome these limitations, we present DROIDBREAKER, a practical (build-safe) and functional (semantics-preserving) problem-space attack framework that provides: (i) query-efficient white- and black-box attacks by manipulating only the APK components most influential to the target model; (ii) a set of fine-grained, build-safe manipulations (including injection and obfuscation of API calls, app modules, permissions, and URLs) with minimal side effects; and (iii) a semantics-preserving functionality test that enforces runtime equivalence by comparing execution logs and API-level traces between the initial and the modified APK. Evaluated on a recent corpus of Android applications, DROIDBREAKER achieves high evasion rates with few queries and minimal side effects in both white-box and black-box settings, and drastically reduces detections by commercial malware scanners hosted on VirusTotal.

Christian Scano, Diego Soi, Angelo Sotgiu +5

University of Cagliari · Sapienza University of Rome · CINI +1

Adversarial Attacks Android Malware Detection Malware Classification Black-Box Adversarial Attacks

Jun 25, 2026cs.CR

Adversarial Diffusion Across Modalities: A Fusion Survey of Attacks, Defenses, and Evaluation for Text, Vision, and Vision-Language Models

Adversarial evaluation of AI systems has matured along four largely disconnected tracks: diffusion-based attacks on text and large language models (LLMs), diffusion-based attacks on image classifiers, jailbreak pipelines against vision-language models, and diffusion-based input purification defenses. Each has developed its own vocabulary, threat models, and benchmarks, with denoising diffusion models emerging as a shared generative mechanism whose recipes are now actively ported between communities. This survey performs an information-fusion exercise at the meta-research level: we integrate these four tracks into a single conceptual framework with a unified taxonomy, evaluation criteria, and research agenda, focusing on the LLM-side slice. We catalog fifty published papers across four scope areas (text/LLM, image classifier, vision-language model, defense), plus four diffusion-LLM-as-victim entries and ten non-diffusion baselines against which any new attack must be compared. We propose a six-class taxonomy of diffusion roles in adversarial pipelines, augmented by a threat-model axis recording attacker knowledge, query budget, and target accessibility, and apply a five-dimension framework (attack success rate, transferability, query budget, perplexity, defense-evasion) uniformly across modalities. The review adopts a dual attacker-defender perspective: alongside the attack catalog we cover four diffusion-based defenses that form the natural evaluation backdrop for new attacks. Our critical analysis identifies five recurring weaknesses of the current LLM-side literature, and we close with a research agenda of open questions and concrete experimental designs. The companion catalog and spreadsheet are released with the paper. We are explicit that this is a narrative review with quality assessment, not a PRISMA-compliant systematic review, and discuss the implications for replication.

Abrar Alotaibi, Moataz Ahmed

Information and Computer Science Department, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia · College of Computer Science and Information Technology, Imam Abdulrahman Bin Faisal University, Dammam, 31441, Saudi Arabia · SDAIA-KFUPM Joint Research Center for Artificial Intelligence, King Fahd University of Petroleum & Minerals, Dhahran, 31261, Saudi Arabia

Adversarial Attacks on VLMs Adversarial Attacks Adversarial Attacks on LLMs Adversarial Robustness Adversarial Robustness of Language Models

Jun 24, 2026stat.ML

The Role of Input Dimensionality in the Emergence and Targeted Control of Adversarial Examples

Several theoretical works have tried to explain the adversarial vulnerability of deep neural networks through properties of high-dimensional geometry. However, the assumptions underlying these works are rarely examined empirically, and systematic evidence remains limited. In this work, we present a systematic study of the role of input dimensionality in both the emergence and the targeted control of adversarial examples. We first analyse the scope and limitations of existing theoretical frameworks based on concentration of measure, showing that real image classes exhibit strong empirical localization, beyond what such theories typically assume. We then conduct an extensive empirical evaluation across hierarchical image datasets spanning a wide range of input dimensionalities and diverse neural architectures. Our results consistently show that adversarial examples become easier to construct as dimensionality increases. We also investigate how input dimensionality affects the additional difficulty of crafting targeted adversarial examples. In particular, we provide theoretical arguments showing that high-dimensional geometry implies that enforcing a specific target label entails only a limited additional distortion compared to untargeted attacks. We corroborate this insight through extensive experiments, demonstrating that the gap between targeted and untargeted perturbations remains small and further narrows as input dimensionality increases. While, taken together, our findings establish high input dimensionality as a fundamental factor underlying the emergence and targeted control of adversarial examples, whether this phenomenon primarily arises from the interplay between high-dimensional geometry and data distributions or from the architectural properties of deep neural networks remains an open question.

Nasrin Malekzadeh Goradel, Niccolo Pancino, Yaser Gholizade Atani +3

Adversarial Attacks Adversarial Examples Adversarial Perturbations

Jun 24, 2026cs.CV

Transferable Attack against Face Swapping in an Extended Space

Although deep Face Swapping (FS) models may benefit the entertainment industry, they pose severe threats to privacy and security. Existing protections, including deepfake detection and adversarial perturbation, are either passive responses or ineffective to unseen subject-agnostic FS models. In this paper, we propose a transferable attack against subject-agnostic FS models named Additive Identity attack based on a Relighting function (AIR). AIR leverages reillumination and additive perturbations to mislead the identity extraction modules in subject-agnostic FS models. By using these two types of perturbations simultaneously, the attack space is extended such that stronger but more visually natural adversarial examples can be identified. To further enhance the visual quality while preserving the effectiveness of the attack, an adaptive translation-invariant operation and an illumination control scheme are designed for AIR. Unlike other methods, AIR does not require a surrogate FS model to achieve high transferability. In addition, a mathematical proof is given for the extension of the attack space. Extensive experiments using 1000 image pairs across various state-of-the-art subject-agnostic FS models, including GAN and diffusion-based FS models, show that AIR surpasses all existing attacks in terms of both attack success rate and image quality.

Mingzhi Lyu, Yi Huang, Jun Xie +3

Nanyang Technological University Singapore

Adversarial Attacks Adversarial Perturbations Transfer-Based Adversarial Attacks Adversarial Transferability

Jun 22, 2026cs.LG

Attacking the Trusted Imagination: Oracle-Level Integrity Attacks on Imagine-then-Act World Models

Many recent vision-language-action (VLA) policies adopt an imagine-then-act design. A world-action model (WAM) first imagines a short future as a latent trajectory z~, on which the action is then conditioned. We identify this trusted imagination, rather than the reactive policy, as the exposed attack surface. A downstream oracle, such as a safety gate, a visual model-predictive-control (MPC) planner, or an imagine-then-check verifier, consumes z~ as a prediction of the future. The robustness of the policy therefore does not entail the robustness of systems that rely on the WAM. The underlying phenomenon is an asymmetry. Corrupting the imagination is easy, since it requires only displacing z~ from its natural-future manifold. Steering it precisely is hard, since it must reach a specified on-manifold target. We adopt a capability-based threat model with an L-infinity-bounded observation perturbation. The attacker applies projected gradient descent through the fully differentiable observation-to-imagination map. The same off-manifold property motivates a parameter-free denoiser detector. We evaluate three targets: RynnVLA-002, LingBot-VA, and LaDi-WM. Untargeted corruption is roughly 60x stronger than random and is detected at AUC 1.0. Targeted control remains bounded. An adaptive attacker evades detection only by forgoing corruption. The reactive policy remains robust to corrupted imagination. A native imagination-driven MPC, however, exhibits the first adversary-specific task failure (at epsilon=0.01, success 0.70 versus 0.05; Fisher p < 10^-4).

Linghan Chen, Kaiyan Ji, Minyu Guo

Adelaide University

Adversarial Attacks Adversarial Attacks on VLA Models Vision-Language-Action Models World Action Models Robustness of VLA Models

Jun 22, 2026cs.LG

The Unseen Hand: Manipulating Model Fairness and SHAP with Targeted Identity Re-Association Attacks

As machine learning models grow more influential and opaque, algorithmic fairness and explainability are critical for ensuring accountability. However, we demonstrate that these auditing mechanisms are themselves vulnerable to subtle manipulation, camouflaging the influence of protected features. While prior work on data-agnostic attacks has exposed this vulnerability, they leave behind detectable artifacts that compromise their stealth. We introduce Targeted Identity Re-Association (TIRA) attacks, a novel family of attacks that iteratively and probabilistically manipulate a model's outputs without requiring access to the model's internals or feature representations. We formalize two algorithms: Probabilistic Micro-Shuffling (PMiS), which applies localized adjacent swaps, and Probabilistic Rank-Shift Micro-Perturbation (PRSMP), which introduces small, randomized rank shifts. We empirically demonstrate that TIRA attacks are highly effective at pushing fairness metrics towards ideal values. Crucially, TIRA attacks successfully confound SHAP-based explanations, leaving effectively zero residual attribution for protected features, a major improvement over prior work.

Sannaan Khan, Muhammad U. S. Khan

National University of AbstractSciences and Technology (NUST)

Adversarial Attacks Algorithmic Fairness Black-Box Adversarial Attacks

Jun 21, 2026cs.SD

Learning to Evade: Adaptive Attacks on Audio Watermarking

Advances in generative audio have intensified copyright concerns, making audio watermarking increasingly important for asserting ownership. However, existing audio watermarking methods are vulnerable to adversarial attacks. We find that watermark decoder message probabilities follow normal distributions, a property exploited by defenses to detect manipulations. This paper introduces an adaptive audio watermark attack method (AWM) designed to bypass existing defense strategies. AWM uses a two-stage optimization: the first stage ensures attack success, while the second improves audio quality. To evade detection, it estimates normal distribution parameters from limited samples of the target audio, and then adaptively steers decoded probabilities back into the estimated range. Evaluated on two watermarking methods across three voice datasets, AWM achieves high success while bypassing state-of-the-art detectors: detection rates are below 10% for replacement and creation, and 0% for removal.

Weikang Ding, Hanqing Guo, Rui Duan +4

University of Missouri-Kansas City, USA · University of Hawaii at Manoa, USA · University of South Florida, USA +2

Watermark Removal Audio Watermarking Adversarial Attacks Robust Watermarking Consistent Adversarial Attacks

Jun 18, 2026cs.SD

Exploiting Neural Audio Codec Latents for Adversarial Audio Attacks

Deep learning-based audio classification systems, including automatic speaker verification, are vulnerable to adversarial attacks. Realistic real-time threat assessment remains difficult because optimization-based methods, such as projected gradient descent (PGD) and Carlini-Wagner, require costly iterative updates in the high-dimensional waveform domain. Generative attacks allow single-shot synthesis but often introduce perceptible artifacts or depend on computationally intensive architectures, while diffusion and autoregressive approaches incur high inference latency. To address this gap, we propose a generative attack framework operating in the continuous latent space of a neural audio codec. A conditional generator synthesizes class-specific perturbations in a single forward pass and decodes them into adversarial waveforms. Our method achieves targeted attack success rates up to 99% with sub-7 ms inference, outperforming generative baselines while reducing latency by 24x.

Sameek Bhattacharya, Bharath Krishnamurthy, Ajita Rattani

Dept. of Computer Science and Engineering, University of North Texas, Denton, Texas, USA

Adversarial Attacks

Jun 18, 2026stat.ML

Adversarial observations in probabilistic State-Space Models for robust Reinforcement Learning

Decision-making under partial or adversarial observability requires accurate inference of the environment's latent state and its associated uncertainty. This work analyses adversarial attacks on linear probabilistic state-space models, commonly integrated within reinforcement learning architectures, where the attacker alters observations under likelihood constraints that ensure the perturbations remains consistent. We analyze how such adversarial yet realistic observation shifts influence the latent state and influence policy decisions. This perspective provides a principled pathway toward building more robust reinforcement learning systems, with direct relevance to safety-critical domains such as robotics, where reliable operation under sensor noise, partial failures, and adversarial conditions is essential.

M. Santos-Pascual, D. Ríos Insua

1Inst. Math. Sciences, Spanish Nat. Research Council, Madrid, Spain · Universidad Autónoma de Madrid, Escuela de Doctorado, Madrid, Spain

Adversarial Attacks Partially Observable RL Robust RL State Space Models

Jun 18, 2026cs.CV

VFACamou: View-Fused Adversarial Camouflage for Environment-Adaptive Physical Evasion

Adversarial camouflage in the physical world remains highly challenging, particularly under UAV reconnaissance where targets undergo continuous geometric changes and extreme illumination variations. Existing methods either optimize 2D digital perturbations that fail to generalize to dynamic viewpoints or produce visually unnatural textures that cannot be deployed in real scenarios. Therefore, we propose an end-to-end framework for adversarial camouflage generation that automatically produces wearable adversarial patterns and maintains stable attack performance in real physical environments with changing viewpoints, poses, and lighting conditions. Our method integrates UV-volume rendering with a diffusion-based texture generator, enabling consistent appearance under varying scales, poses, and lighting conditions. To ensure environmental realism, we propose an illumination color consistency estimator that extracts dominant background attributes and guides a natural texture loss to align the generated UV texture with the surrounding environment. A multi-scale dynamic training strategy further enhances robustness against viewpoint shifts and body deformation. Extensive experiments across multiple mainstream detectors demonstrate that our method achieves strong and stable physical attack performance while maintaining high perceptual naturalness, reducing human detection rates without introducing unnatural artifacts.

Shihui Yan, Hu Liu, Junyu Shi +6

State Key Laboratory of Intelligent Vehicle Safety Technology · School of Cyber Science and Engineering, Huazhong University of Science and Technology · School of Computer Science and Technology, Huazhong University of Science and Technology +2

Adversarial Attacks Physical Adversarial Attacks

Jun 17, 2026cs.LG

Detecting Hidden ML Training With Zero-Overhead Telemetry

Hardware-enabled monitoring of GPU workloads underpins many proposals for AI compute governance, but if developers can defeat monitoring mechanisms, such schemes are unworkable. We evaluate the adversarial robustness of GPU workload classification using only zero-overhead, privacy-preserving NVML telemetry: content-agnostic signals that observe physical effects of computation without accessing model weights, training data, or hyperparameters. Across 5 rounds of monitor-evader iteration, we evaluate 20 evasion strategy families on 9 GPU models spanning 4 architecture generations. We develop a classifier that achieves 98.2% binary accuracy at identifying training workloads across the whole corpus, and 43-87% accuracy against the most challenging unexpected workloads even when they are adversarially disguised.

Robi Rahman, Sabiha Tajdari

Machine Intelligence Research Institute · University of Virginia

Adversarial Attacks Adversarial Robustness

Jun 17, 2026cs.LG

Stealthy World Model Manipulation via Data Poisoning

Model-based learning agents use learned world models to predict future states, plan actions, and adapt to new environments. However, the process of updating world models from collected experience creates a training-time attack surface: adversarially poisoned fine-tuning trajectories can manipulate the learned dynamics and thereby corrupt downstream planning. In this paper, we propose SWAAP, the first two-stage data poisoning framework for learned world models. In the first stage, SWAAP identifies a harmful target world model that induces low-return behavior under planning while remaining close to clean dynamics, using first-order bilevel optimization enabled by a transition-gradient theorem. In the second stage, SWAAP realizes this target through stealth-constrained gradient matching, modifying only a limited fraction of fine-tuning transition targets so that the induced training gradients steer the victim model toward the adversarial target, while a prediction-error regularizer encourages the poisoned targets to remain close to the world model's natural approximation error. To assess attack stealthiness, we evaluate defenses and detectability across three stages of the poisoning pipeline: pre-training detection of poisoned transitions, robust training during fine-tuning, and test-time monitoring of the resulting world model. Across diverse continuous-control tasks, SWAAP causes substantial performance degradation while keeping poisoned transitions close to clean data and evading the evaluated non-adaptive residual/CUSUM/TRIM-style defenses. These results reveal a practical vulnerability in world-model adaptation pipelines and highlight the need for robustness methods that protect both world-model training data and learned dynamics.

Yibin Hu, Xiaolin Sun, Zizhan Zheng

Department of Computer Science Tulane University New Orleans, LA, USA

World Model Learning Adversarial Attacks Data Poisoning Attacks Model-Based RL

Jun 16, 2026cs.LG

Veriphi: Attack-Guided Neural Network Verification with Dataset-Dependent Training Methods

We present Veriphi, a GPU-accelerated neural network verification system that combines fast adversarial attacks with formal bound certification using alpha,beta-CROWN methods. Through systematic experiments on MNIST and CIFAR-10 using three training methodologies (standard, adversarial, certified), we demonstrate that training method effectiveness is fundamentally dataset-dependent. Interval Bound Propagation (IBP) achieves 78% certified accuracy on simple MNIST (784 dimensions) but provides negligible certification performance on the more complex CIFAR-10 dataset, where PGD adversarial training dominates with 94% certification at small perturbations. We achieve 5x verification speedup through attack-guided falsification and scale our approach to production-size models (105.8M parameters) for real-world aerospace logistics optimization. Our results challenge the assumption that certified training universally outperforms adversarial training, showing context matters critically for verification strategy selection.

Pratik Deshmukh, Kartik Arya, Vasili Savin

TU Wien, Vienna, Austria

Adversarial Training Neural Network Verification Adversarial Attacks Certified Robustness

Jun 16, 2026cs.CR

TIGER: Inverting Transformer Gradients via Embedding-Subspace Distance Optimization

Federated learning allows multiple clients to jointly train a shared model by sending gradient updates to a central server while keeping raw inputs local. However, prior gradient inversion attacks show that these updates can reveal enough information to reconstruct client inputs. Existing attacks on transformers either optimize dummy inputs to match the true client updates, which is costly and unstable for modern models, or exploit the low rank of attention gradients to identify a subspace containing the true layer embeddings, followed by a discrete membership test for candidate tokens. However, this token test is brittle under numerical noise, i.e., from quantization or Differential Privacy (DP), and scales poorly for encoder models with non-causal attention. We introduce TIGER, a continuous gradient inversion attack that turns this subspace signal into a differentiable objective. Instead of searching over tokens or matching full gradients, TIGER directly optimizes token embeddings to minimize their distance to the subspace. Our experiments demonstrate that on encoder-only models, TIGER substantially improves both reconstruction quality and runtime over existing attacks, while on decoder models, TIGER is more robust than prior subspace-based attacks, enabling the first successful reconstructions in DP-defended federated learning settings.

William Kalikman, Ivo Petrov, Dimitar I. Dimitrov +1

ETH Zürich · INSAIT, Sofia University "St. Kliment Ohridski"

Gradient Inversion Attacks Transformer Adversarial Attacks Model Inversion Attacks Federated Learning

Jun 16, 2026cs.CV

Flux-Guard: Facial Identity Protection using diffusion models

The widespread deployment of face recognition (FR) systems exposes personal images shared on social media and public platforms to identity linkage and privacy risks. Existing adversarial privacy protection methods can degrade unauthorized FR performance but are not compatible with generative face editing. Artificial intelligence-driven face editing tools are gaining popularity, which has significantly increased user demand for personalized portrait generation and social sharing. However, current editing methods often preserve identity features, making the edited images still susceptible to tracking by malicious FR systems. Thus, this paper proposes Flux-Guard, a privacy-preserving face editing framework based on adversarial attacks, which integrates face editing and privacy protection within a unified generative process. Specifically, we design a flow trajectory control method to align semantic manipulations with the generative process and introduce latent-space adversarial optimization with an adaptive perceptual-loss-driven weighting strategy, dynamically adjusting adversarial strength to maximize attack effectiveness while preserving visual quality. Extensive experiments demonstrate that Flux-Guard supports face editing while significantly improving attack success rates against cross-domain face recognition models on the CelebA-HQ and LADN datasets. Furthermore, evaluation results for commercial APIs have confirmed its effectiveness in real-world applications. The code is released at https://github.com/JLMWang/Flux-Guard.

Jie Wang, Tao Wang, Ru Zhang +1

School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, 100876, China · Nanjing University of Aeronautics and Astronautics, NanJing, China

Adversarial Attacks Diffusion-Based Image Editing

Jun 16, 2026cs.LG

MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defense

Time-series forecasting models remain vulnerable to gradient-based adversarial attacks while existing defense mechanisms typically incur a trade-off in robustness for bounded response and compute cost. The problem is pronounced in Moving Target Defense where maintaining multiple randomized model instances substantially exacerbates the training overhead. In this work, we introduce MorphStrata, a student generation strategy with selective, layer-specific stochastic noise injection that extends the traditional Morphence defense. MorphStrata uses a Transformer backbone as the teacher and perturbs randomly selected architectural blocks to create structured heterogeneity across student models in response to varied data distributions and threat models. We evaluate against vanilla Transformer and Morphence backbones on a suite of benchmarks including the Jena Climate, Electricity Load Diagrams, and Appliances Energy Prediction using FGSM, BIM and PGD attacks across multiple attack strengths. Across datasets and attack regimes, the proposed ensemble maintains comparable adversarial RMSE. Specifically, for high entropy, periodic datasets as in the case of the AEP data, MorphStrata achieves the lowest RMSE across all attacks and perturbation budgets, improving over the static baseline by up to 24.11% and 97.97% under FGSM and BIM respectively at an epsilon value of 0.5 over 30 randomized trials. Targeting the layers to generate MorphStrata students accounts for less than 1% increase in train-times over the Morphence MTD baseline for most of the experiments, while accounting for double digit gains in adversarial RMSE reduction. We also observe a positive correlation between higher pairwise L2 distance (among generated students) and overall defense effectiveness. In summary, MorphStrata maintains adversarial robustness as an MTD defense at marginal cost deltas when compared to existing baselines.

Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan +5

Department of Computer Science, San Jos´e State University, San Jos´e, CA, USA · Department of Computer Engineering, San Jos´e State University, San Jos´e, CA, USA · Department of Applied Data Science, San Jos´e State University, San Jos´e, CA, USA +1

Adversarial Attacks Time Series Forecasting Adversarial Robustness Time Series Transformers

Jun 15, 2026cs.CV

BadWorld: Adversarial Attacks on World Models

Visual world models (VWMs) synthesize interactive, action-conditioned rollouts from a single context image. However, it remains an open question how robust these models are to adversarial perturbations. Standard adversarial attacks fail to assess this vulnerability because attackers lack ground-truth future videos and cannot predict subsequent user controls. We introduce BadWorld, a label-free adversarial framework tailored for autoregressive VWMs that systematically overcomes both constraints. First, to bypass the need for future supervision, we propose a self-supervised velocity attack that directly disrupts the early denoising dynamics of the model. Second, to ensure the attack generalizes across unpredictable user actions, we formulate a trajectory-adaptive bi-level optimization that actively mines hard control sequences to forge control-agnostic perturbations. Evaluated on representative VWMs with continuous and discrete controls, BadWorld exposes severe structural fragility. Visually indistinguishable adversarial images reliably trigger catastrophic degradation in future rollouts, leading to incomplete denoising, structural collapse, and control inconsistency. These findings reveal critical risks for deploying VWMs in safety-critical systems while highlighting a practical mechanism for privacy protection.

Linghui Shen, Mingyue Cui, Xingyi Yang

The Hong Kong Polytechnic University

Adversarial Attacks World Models Action-Conditioned World Models Adversarial Perturbations Video World Models

Jun 14, 2026cs.LG

Greedy Coordinate Diffusion: Effective and Semantically Coherent Adversarial Attacks via Diffusion Guidance

Adversarial attacks on large language models have limited practical impact despite extensive research. Optimization-based attacks such as Greedy Coordinate Gradient (GCG) (Zou et al., 2023) produce high-perplexity, incoherent suffixes that existing defenses easily detect (Bengio et al., 2024). Moreover, attempting to enforce coherence constraints during optimization often prevents the attack from successfully eliciting the specific targeted response, resulting in low success rates against robust models. Conversely, attacks that maintain coherence often alter the semantic intent of queries; when the model complies with these altered queries, responses fail to address the adversary's original goal. In this work, we introduce Greedy Coordinate Diffusion (GCD), a novel framework that efficiently generates adversarial attacks against safety-aligned models while maintaining low perplexity and high semantic adherence to the adversary's original intent. GCD leverages the generative priors of discrete diffusion language models to guide the search for adversarial suffixes that achieve semantic coherence and adherence. Unlike GCG, GCD does not require direct gradient access, allowing it to operate in a gray-box setting. We show GCD achieves highest ASR while remaining competitive on response-quality scores, and that the constructed adversarial prompts are detected at lower rates than other methods by perplexity-based and guard-model filters.

Bohdan Turbal, Blossom Metevier, Max Springer +1

Princeton University, Princeton, NJ, USA.

Adversarial Prompt Generation Adversarial Attacks Adversarial Attacks on LLMs Adversarial Text Attacks

Jun 13, 2026cs.AI

Attribute Inference from Interactive Targeted Ads

Targeted advertising systems can pair audiences selected by advertisers with ad units that expose visible user actions. When an interaction remains linked to the campaign that elicited it, the advertiser may receive an observation tied to a user rather than only an aggregate report. We model that channel as a noisy oracle for attribute inference. The model separates targeting predicates, exposure, interaction, and disclosure. These boundaries capture the gap between eligibility and delivery, and the gap between interaction and advertiser visibility. We build a reproducible benchmark using synthetic populations calibrated with public data, each with known sensitive labels. A generated campaign semantics layer provides topic variants and response priors. The simulator generates the ground truth, event traces, disclosed observations, and metrics. The evaluation compares Bayesian, supervised, positive and unlabeled, and adaptive attacks under common campaign and disclosure definitions. The final evaluation uses four topic variants, seven simulator seeds, and two interaction settings. Repeated campaigns with identity exposure produce measurable but bounded inference signal. At

160

campaigns, Bayesian and supervised attacks reach about

0.64

AUC in the main setting and about

0.65

AUC in the higher interaction setting. Disclosure policy is the strongest control. Aggregate reporting removes the evaluated oracle input tied to users. Type filtering and randomized disclosure reduce the released signal. The result is a model, artifact, and defense evaluation method for privacy in interactive targeted advertising. The code is available at https://github.com/P-HOW/Interactive-Ad-Oracle.

Peihao Li

Privacy Auditing Adversarial Attacks Online Advertising

Jun 12, 2026cs.CV

Giving AI a Headache: Acoustic Adversarial Attacks to Computer Vision Applications

Artificial Intelligence (AI) is increasingly used to automate a variety of real-world computer vision (CV) applications, such as autonomous vehicle control, facial recognition, and security cameras. Recent research has shown that acoustic vibration can induce real physical motion in cameras, interfering with their internal stabilization mechanisms. Because the motion falls outside the conditions the stabilization system was designed to handle, the system introduces artifacts into the frame, causing AI-based CV models to misclassify, miss targets, or hallucinate objects. Previous work used ultrasonic frequencies (>20 kHz) to perform short-range attacks, which limits them to short distances due to the attenuation exhibited by high frequencies. In this work, we investigate acoustic attacks using lower frequencies in the audible range (<20 kHz), and we further expand our analysis to include how various image and object features are affected by the attacks. Specifically, we performed physical experiments to demonstrate the viability of our attacks on an off-the-shelf object detection model (YOLO11) by resonating a commercially available camera with various frequencies. Based on our results, we provide insights into several factors that make an AI CV system more vulnerable to these attacks, which could help inform the development of future mitigation strategies.

Nicole Villavicencio-Garduño, Maksim Ekin Eren, Milo Prisbrey +2

Carnegie Mellon University, Pittsburgh, USA · Los Alamos National Laboratory, Los Alamos, USA

Adversarial Attacks Adversarial Robustness Physical Adversarial Attacks

Jun 12, 2026cs.SD

The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard

L_p

metrics, we introduce a psychoacoustic framework that optimizes inaudible perturbations to decouple model attributions from final classifications. We evaluate this vulnerability across state-of-the-art architectures under strict prediction-preserving constraints. By evaluating the manipulation cost through domain-specific perceptual audio quality metrics alongside explanation alignment criteria, our framework demonstrates that an adversary can systematically distort automated explanation heatmaps while preserving the predicted deepfake label. Full code available at: https://github.com/cncPomper/Audio-XAI

Piotr Kitłowski, Dominik Wiącek, Mateusz Modrzejewski

Faculty of Electronics and Information Technology, Warsaw University of Technology, Warsaw, Poland.

Audio Deepfake Detection Adversarial Attacks Explainable Deepfake Detection Adversarial Examples Explainability Evaluation

Jun 11, 2026cs.CL

No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions

As AI-generated reviews move from experimental tools into peer-review infrastructure, most robustness concerns have focused on explicit attacks such as hidden instructions and prompt injection. We study a harder and more policy-relevant failure mode: no hidden text, no prompt injection, and no changes to methods, experiments, figures, equations, proofs, or numerical results. The attacker modifies only presentation-level content, such as the abstract, contribution framing, related work, discussion, and narrative structure. We introduce adversarial repackaging: a closed-loop attack that uses AI-reviewer feedback to search for presentation-level revisions while keeping the scientific evidence fixed. Across three mainstream AI reviewers, adversarial repackaging achieves a 75.1% attack success rate and a mean score gain of +1.21/10. The effect is not explained by ordinary prose polishing. We also reveal that strategies that change how the reviewer interprets the paper, such as related-work repositioning and analytical discussion expansion, substantially outperform surface edits such as local polishing, table formatting, and algorithm boxes. Our analysis reveals two deeper structural failure modes. First, AI reviewers are easier to impress than to convince: highlighting strengths reliably increases perceived merit, while attempts to dissolve weaknesses frequently backfire. Second, AI reviewers can confuse the appearance of addressing a limitation with actually resolving it, allowing unchanged evidence to be reinterpreted as stronger scientific contribution. These results show that the deployment risk is not only malicious hidden instructions, but the emergence of paper presentation itself as an optimization surface. We release a contamination-free rolling benchmark and attack framework for testing whether AI reviewers remain anchored to scientific content under presentation-only edits.

Xu Yang, Zhizhou Sha, Junbo Li +10

University of Texas at Austin · University of Illinois Urbana-Champaign · University of Texas at Dallas +1

Adversarial Attacks Automated Peer Review Adversarial Text Attacks