Black-Box Adversarial Attacks

Follow this topic Ask about this topic

Momentum

8 papers in the last four weeks, up 60% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 115

Oct 6, 2026cs.LG

Breaking Adversarial Transferability in Fine-Tuned Speech Recognition

Many organizations fine-tune publicly available pretrained Automatic Speech Recognition (ASR) models and deploy them in black-box settings, assuming limited access provides protection. We show this assumption is fragile: adversarial perturbations crafted on the public base model transfer effectively to fine-tuned target models, severely degrading performance and posing concerns for safety-critical applications. We propose TransferBreaker, a unified fine-tuning framework that suppresses adversarial transfer by integrating Base Adversarial Fine-Tuning, which restricts adversarial training to base-effective perturbations; Latent Jacobian Regularization, which enforces latent-space invariance by suppressing adversarially sensitive directions; and HybridGrad-AFT, which improves robustness against adaptive attacks by interpolating transferable perturbations from base and target gradients. We theoretically justify all components and evaluate TransferBreaker across three languages and four large ASR models, reducing adversarial WER from 92.6 to 27.8. Our code is publicly available at https://github.com/rohban-lab/TransferBreaker.

Mojtaba Nafez, Aref Mousavi, Mohammad Ebrahim Mahdavi +3

Department of Computer Engineering Sharif University of Technology · Department of Computer Engineering University of Isfahan

Adversarial Transferability Automatic Speech Recognition Adversarial Training Black-Box Adversarial Attacks

Oct 5, 2026cs.LG

ATLAS-AL: Adaptive Trust-Region for Latent Adversarial Searches via Active Learning

Security evaluation of learning-based systems requires more than just testing the system against a fixed collection of attacks. It requires adaptive mechanisms that can efficiently discover \textit{sets} of inputs that induce model failure. We introduce ATLAS (Adaptive Trust-Regions for Latent Adversarial Searches), which is a query-based framework that discovers adversarial input sets for black-box learning systems. ATLAS casts attack generation as an active learning level set estimation problem then combines calibrated approximations with a local-global sampling architecture to find regions of the input space that contain adversarial examples. Once discovered, ATLAS is designed to sample points within these adversarial regions to build adversarial sets that accurately represent the state of robustness of the target model. When applied on toy experiments, we find that ATLAS is able to recover more of the adversarial region under a limited query budget than does previous work. When applied to standard and adversarially trained MNIST, CIFAR, and ImageNet model targets, ATLAS produces better representative attacks than other query-based black-box attacks (NES, SignHunter, BayesOpt). ATLAS represents an automated red-teaming framework that can be used for both analyzing the robustness of learning-based systems under development and continuous auditing to see how the robustness of a system changes over time.

Marsalis Gibson, Claire Tomlin, Shankar Sastry

Department of Electrical Engineering and Computer Sciences University of California, Berkeley

Adversarial Robustness Active Learning Black-Box Adversarial Attacks

Oct 5, 2026cs.LG

Boosting Transferable Adversarial Attacks against Deep Reinforcement Learning

Most adversarial attacks on deep reinforcement learning (DRL) assume white-box access to the victim policy, which rarely holds in practice. This paper studies transfer-based black-box attacks on DRL: the attacker crafts observation perturbations on a white-box surrogate agent and feeds them to an unknown victim. We formulate the attack as return minimization under a per-step perturbation budget. We first show that transplanting transferable image-classification attacks (FGSM, MI-FGSM, and NI-FGSM) with a per-step objective yields perturbations that transfer but are no stronger than random noise of the same budget. We then propose a trajectory-level attack that optimizes a sequence of perturbations over a receding horizon through a differentiable model of the environment and a temperature-smoothed surrogate policy, with the same optimizers. On CartPole-v1 with ten DQN and DDQN agents and 100 surrogate--victim pairs, the trajectory-level attack outperforms per-step attacks and random noise in the white-box, cross-model, and cross-algorithm settings.

Zexin Li, Ruili Yao, Yiming Zeng +1

Nanyang Technological University · University of California, Riverside · University of Connecticut +1

Adversarial Attacks Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks Adversarial Transferability

Sep 29, 2026cs.CR

VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents

Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems (LLM-ARS) instantiate users and items as autonomous agents, whose semantic states are dynamically refined through a recurrent process known as collaborative reflection. While this mechanism improves recommendation quality, it simultaneously introduces a systemic vulnerability: adversarial evidence injected into a single agent can be rationalised into a legitimate preference narrative, written back into memory, and propagated to other agents through interaction contexts. We term the local rationalisation process reflection laundering, and its system-wide escalation through collaborative reflection collaborative-reflection hijacking. Existing attacks on recommender systems, whether based on interaction-level data poisoning or text-level adversarial perturbations, assume static pipelines and thus cannot exploit this recurrent, multi-agent amplification pathway. To bridge this gap, we first conduct a controlled vulnerability analysis that establishes two exploitable properties underlying collaborative-reflection hijacking: reflective persistence and cross-agent propagation. Then building on these findings, we propose VirusCascade, the first black-box targeted promotion attack that jointly shapes semantic and structural attack surfaces: the former ensures the target item is naturally rationalised as satisfying broad user preferences, the latter positions it for system-wide propagation. Extensive experiments on four real-world datasets across diverse LLM-ARS architectures demonstrate that VirusCascade consistently achieves state-of-the-art targeted exposure under evaluated stealth constraints, reaching a mean E@20 of 0.384 and surpassing the strongest baseline by an absolute margin of +0.185.

Yurong Hao, Wen Zhou, Guowei Guan +3

College of Computing and Data Science, Nanyang Technological University

Adversarial Attacks Agent Memory Poisoning Large Language Model-Based Recommendation Black-Box Adversarial Attacks Multi-Agent System Security

Sep 27, 2026cs.CV

One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs

Adversarial attacks have long posed a fundamental threat to machine learning systems. As multimodal large language models (MLLMs) rapidly evolve and become widely deployed, assessing their vulnerability to such attacks is essential for their safe use. In this work, we investigate whether a single adversarial image can consistently mislead diverse frontier MLLMs in black-box settings. We propose O-Attack, a highly transferable black-box attack framework. This framework builds on our insight that surrogate models contain a broad, high-level, cross-modally aligned semantic space. This space extends beyond final-layer outputs and provides multiple semantically consistent representations that remain underexploited by existing attacks. Within this space, O-Attack anchors aligned representations, progressively broadens semantic conditions, and optimizes perturbations through semantic consensus to promote consistent target alignment. By fully exploiting this space with the same surrogate models as M-Attack, O-Attack raises attack success rates on GPT-5.4 (29.1% to 77.2%), Claude-4.6 (42.8% to 81.6%), and Gemini-3.1 (38.2% to 80.9%). Extensive experiments across 24 MLLMs show that O-Attack outperforms six state-of-the-art methods in black-box transferability, with consistent effectiveness across prompts and improved efficiency and imperceptibility. This work exposes the practical safety risks posed by black-box adversarial attacks against frontier MLLMs, underscoring the need for more rigorous robustness evaluation and more effective defenses.

Sen Nie, Jie Zhang, Zhongqi Wang +2

State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, and the University of Chinese Academy of Sciences.

Adversarial Attacks on VLMs Adversarial Attacks on LLMs Multimodal Large Language Models Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks Consistent Adversarial Attacks

Sep 22, 2026cs.CR

A2M: Trace-Optimized Agent Hijacking in the MCP Ecosystem

Agents using the Model Context Protocol (MCP) rely on semantic matching to select tools from third-party servers, exposing a semantic supply-chain risk through attacker-controlled metadata and outputs. We introduce A2M (Attraction-to-Manipulation), a two-stage black-box framework for hijacking MCP agents. The Attraction phase optimizes tool metadata to increase invocation probability; the Manipulation phase uses execution traces to refine adversarial tool returns that steer agents toward attacker-desired outcomes. On LiveMCPBench, direct attacks optimized and evaluated on GLM-4.6 achieve a macro-average malicious tool invocation rate of 93.6% across four scenarios, increase weighted token costs to 32.4

\times

the benign baseline under Cognitive Denial of Service, and attain a mean attack success rate of 74.4% across Information Exfiltration, Environment Integrity Compromise, and Reasoning Derailment. Transfer to four other models without re-optimization yields corresponding macro-averages of 63.6%, 2.7

\times

, and 24.5%. These findings motivate stronger tool vetting and runtime isolation in MCP ecosystems. Code is publicly available at https://github.com/Lilaizhen/A2M.

Laizhen Li, Xuan Wang, Peicheng Zhao +4

Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences · Nanyang Technological University +3

MCP Security AI Agent Security Black-Box Adversarial Attacks

Sep 21, 2026cs.LG

Reinforcement Learning Inspired Black-box Adversarial Attacks for Computer Vision

Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small perturbations, almost imperceptible to humans, which significantly alter the model's prediction. These adversarial attacks are often considered to be a significant threat to the implementation of neural networks in safety-critical applications. Most attacks utilize the white-box threat model and therefore require full access to the target model, making them unrealistic to use in practice. We propose a novel approach under the more realistic black-box threat model that utilizes concepts from reinforcement learning to optimize perturbations with a non-differentiable target model. Reinforcement learning algorithms have already been optimized to be query efficient, making them an ideal starting point when designing black-box adversarial attacks. We show the success of our reinforcement learning inspired black-box adversarial attack (RIBA) in generating adversarial perturbations using only a small number of queries to the target model, by comparing it to state of the art attacks on different models on the Cifar10 and ImageNet data sets. RIBA takes

25.4\%

fewer median queries to generate attacked images against a ResNet-18 on Cifar10 and

22.5\%

fewer median queries to fool a Vit-B/16 model on ImageNet. Additionally, we demonstrate that RIBA can match the performance of white-box attacks on an adversarially trained model.

Florian Krone, Elena Hoemann, Sven Hallerbach

Institute for AI Safety and Security German Aerospace Center (DLR) Sankt Augustin, Germany

Adversarial Attacks Adversarial Robustness Adversarial Perturbations Black-Box Adversarial Attacks

Sep 17, 2026cs.AI

Contagion on the Trading Floor: How Adversarial Signals Spread in Multi-Agent Trading Systems

Multi-agent trading systems built on large language models (LLMs) are beginning to appear in quantitative finance, yet their robustness to adversarial inputs is largely unknown. We study the vulnerability of LLM trading stacks to black-box, input-only attacks that enter solely via admissible social-media feeds. We introduce the Generic Multi-Agent Trading System (GMATS), a framework that captures modern multiagent trading architectures and instantiate a class of black-box poisoning attackers that treat an LLM as a post generator and inject budget-constrained, plausibly benign social-media content into the analyst's evidence stream. We define contagion metrics that trace how adversarial content propagates through the stack, including belief-shift scores at analyst and coordinator layers and attack-clean deltas on standard backtest metrics. Experiments on a safe offline benchmark with historical market and social data show that even simple input-only attackers can materially degrade risk-return profiles, sharply reducing Sharpe ratios. At the same time, we find that suitably designed multi-agent topologies and coordinator prompts can dampen adversarial shocks and improve average robustness under identical poisoning budgets.

Qi Rong Sua, Junhao Dong, Nguyen Duc Thai +3

Nanyang Technological University, Singapore · Centre for Frontier AI Research, IHPC, A*STAR, Singapore · National University of Singapore, Singapore

Multi-Agent LLM Systems Adversarial Robustness of Language Models Black-Box Adversarial Attacks Algorithmic Trading

Sep 15, 2026cs.CV

Investigating Adversarial Robustness of Heterogeneous Cooperative Perception

Heterogeneous cooperative perception (CP) enables connected vehicles with diverse sensor setups to share spatial awareness via compact feature maps, where receivers reconcile these maps using learned translation modules for fusion and inference. Prior attacks against CP in a homogeneous setting reveal that the data exchange introduces a critical attack surface: a single malicious agent can transmit crafted features that erase real objects from a neighbor's fused scene. Yet, it is widely hypothesized that heterogeneity naturally defends against these attacks, as the attacker lacks knowledge of the victim's detector and the translation module scrambles adversarial gradients. We demonstrate that this protection is largely an illusion. Using a matched-objective harness to standardize the perturbation budget, objective, and forward path, we show that properly tuned iterative attacks close or reverse the apparent robustness gap. However, these optimization-based attacks require ground-truth labels and iterative backpropagation, meaning they do not represent a practical field threat running in real-time. To bridge this gap, we introduce HetPoison, a learned generator that crafts a removal perturbation in a single, label-free forward pass. HetPoison transfers across major heterogeneous designs without requiring access to the victim's detector, matching or exceeding the effectiveness of expensive optimizer-based attacks. Since heterogeneity itself is not a defense, we propose HetShield, a lightweight trust layer that validates the spatiotemporal consistency across features, recovering 83--95% of the accuracy degraded by attacks, outperforming prior art.

Chenyi Wang, Yutong Liu, Qingzhao Zhang +1

School of Electrical, Computing, and Software Engineering University of Arizona Tucson, AZ 85721 USA

Adversarial Attacks Adversarial Robustness Black-Box Adversarial Attacks Cooperative Perception Heterogeneous Collaborative Perception

Sep 9, 2026cs.CV

What Makes Adversarial Examples Transfer Across Deepfake Detectors?

Deepfake detectors remain vulnerable to transfer-based black-box attacks, in which adversarial examples are generated on a source surrogate model and transferred to a target model, unknown to the attacker. Yet how source--target compatibility shapes attack success remains poorly understood. Prior studies evaluate limited detector pools and rarely disentangle architectural from training factors. We conduct a controlled evaluation of adversarial transferability across 60 detectors spanning six backbones, two pretraining regimes, and five training-data configurations, using two attack procedures: AutoAttack (AA) and the Carlini--Wagner attack with Expectation over Transformation (CW--EOT). Matched comparisons reveal significantly higher transfer when source and target share an exact backbone, architecture family, pretraining regime, or training data. This compatibility structure is attack-dependent: exact backbone compatibility has the largest effect under AA, whereas shared pretraining and training data have the largest effects under CW--EOT. When transfer is averaged across non-target sources, mean attack success rate (ASR) is

7.21\%

under AA and

19.52\%

under CW--EOT. By contrast, a multi-source oracle combining both attacks attains a

64.48\%

mean ASR after excluding exact backbone and training-data matches, showing that source averaging can substantially understate target vulnerability. We release 240,000 adversarially perturbed images, complete pairwise transfer results, detector configurations, and evaluation code. These findings establish source--target compatibility and source-model selection as central dimensions of credible transfer-based black-box robustness evaluation.

Rafael M. Mamede, Pedro C. Neto, Ana F. Sequeira

INESC TEC, Porto, Portugal · Faculty of Engineering, University of Porto (FEUP), Porto, Portugal · Unilabs, Porto, Portugal

Adversarial Robustness Deepfake Detection Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks Adversarial Transferability

Sep 7, 2026cs.CV

A Black-Box Adversarial Attack on Human Pose Estimation and Keypoint-Based Action Recognition Models

Human pose estimation and keypoint-based action recognition models are increasingly deployed as components of video understanding pipelines, yet their vulnerability to adversarial attacks remains insufficiently studied. Temporally coherent black-box attacks have been previously studied in visual object tracking, where the attack feedback can be defined using bounding-box overlap measures such as Intersection over Union (IoU). However, human pose estimation produces keypoint configurations rather than enclosing boxes, making box-level similarity poorly suited for measuring pose degradation. We propose OKS Attack, a decision-based black-box attack that uses Object Keypoint Similarity (OKS) as the attack feedback signal, directly targeting the spatial structure of human poses rather than their enclosing boxes. Experiments on the Penn Action dataset show that OKS Attack consistently reduces pose quality across evaluated pose estimators, with mean OKS decreases ranging from 0.0802 to 0.1494. In a downstream cross-dataset action-recognition evaluation, the attack reduces accuracy by 6.18 to 13.86 percentage points and outperforms query-matched random-noise perturbations. The attack is effective across both top-down and single-stage pose estimation models. The source code will be made publicly available at https://github.com/KacperM33/OKS_attack

Kacper Mroczek, Michal Kepski

University of Rzeszów, 35-959 Rzeszów, Poland

Human Pose Estimation Black-Box Adversarial Attacks

Aug 31, 2026cs.CR

SIR: Self-improving Red-teaming for Compute Use Agents

Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate everyday digital tasks. Because they can be exposed to untrusted content while operating, they are vulnerable to indirect prompt injection (IPI), in which an adversary plants instructions in content the agent will read and redirects it toward actions that violate the user's intent. Existing CUA safety benchmarks evaluate fixed injections written by hand, which may underestimate the risk posed by an adaptive adversary. We present SIR, a black box IPI attack that (i) composes stealthy injections from a small library of reusable principles stated in plain language and (ii) wraps composition in an iterative feedback loop that diagnoses the victim's failed trajectories and distills the bypasses into new, named strategies that are reapplied across tasks. Unlike prior red teaming of web agents, we target CUAs at the operating system level and score attacks with a fully deterministic oracle, using checks on filesystem, service, and permission state rather than an LLM judge. On experiment, we evaluate three frontier CUAs. Composing principles with feedback raises the attack success rate over a baseline written by hand, for example from 4% to 24% on Claude Opus 4.8 and from 0% to 28% on Gemini 3.5 Flash, while the benign task still completes. Principles discovered against one model further transfer to a different architecture with no additional feedback.

Chen Xiong, Zhiyuan He, Pin-Yu Chen +2

The Chinese University of Hong Kong · IBM Research · University of Zagreb, FER & Radboud University +1

Computer-Use Agents Indirect Prompt Injection Black-Box Adversarial Attacks Automated Red Teaming Prompt Injection Attacks on AI Agents

Aug 30, 2026cs.CR

OASIS: Optimizing Attacker Sequences for Hard-Label Black-Box Text Attacks

Different attack methods follow different search trajectories, they succeed on different subsets of samples, whereas existing hard-label black-box text attacks mainly focus on improving individual attackers or manually combining them. We present OASIS, a method for optimizing attacker sequences in hard-label black-box text attacks. OASIS first performs a one-time bi-objective attack chain search over candidate sequences to balance attack success rate and perturbation, and then reuses the selected fixed global chain during attack chain execution. Experiments across multiple datasets, victim models, and large language models show that OASIS consistently outperforms strong standalone baselines and simple manually constructed chains. These results suggest that attacker composition is not merely an implementation choice, but a practical optimization target for improving hard-label black-box text attacks.

Qian Chen, Shiliang Xiao, Yuzhi Liang

School of Information Science and Technology Guangdong University of Foreign Studies, China

Adversarial Attacks Black-Box Adversarial Attacks Adversarial Text Attacks

Aug 12, 2026cs.LG

Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks

Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models. Beyond perturbation generation, transferability is fundamentally governed by the coupling of initialization, surrogate adaptation, and gradient dynamics. We revisit this challenge from a bilevel-minimax perspective and propose BMAT (Bilevel-Minimax Adversarial Transfer). The bilevel formulation captures the dependency between initialization and perturbation, while the inner minimax problem promotes surrogate robustness for cross-architecture generalization. Algorithmically, we develop an integrated bottom-up solver that combines a Soft Weight Modulator and an Implicit Gradient Approximator to enable ternary coupling among initialization, surrogate adaptation, and perturbation optimization. We further provide theoretical insights into the optimization dynamics of the proposed bilevel-minimax framework. Extensive experiments on classification and segmentation benchmarks show that BMAT outperforms more than 10 strong baselines across more than 30 victim models, improving both intra- and cross-architecture transfer and yielding up to a 2x reduction in mIoU. Code is available at https://github.com/callous-youth/BMAT.

Yaohua Liu, Yifan Guo, Jiaxin Gao

The University of Hong Kong, Hong Kong SAR, China · International School of Information Science & Engineering, Dalian University of Technology, Dalian, China · The Hong Kong Polytechnic University, Hong Kong SAR, China

Bilevel Optimization Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks Adversarial Transferability

Aug 11, 2026cs.CV

SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation

Despite the practical relevance of sparse decision-based black-box threats, they have received limited attention in semantic segmentation. To bridge this gap, we adapt the most representative decision-based black-box sparse attacks from the classification domain to serve as baselines, establishing a rigorous benchmark for this underexplored setting. In this context, we demonstrate that one of the existing methods suffers from severe query inefficiency due to its image-centric pixel accumulation, which rapidly exhausts query budgets across the vast image space. To overcome this, we propose SegPAR, a novel decision-based framework that shifts to a class-centric exploration paradigm. Furthermore, to eliminate the misleading feedback generated by standard decision rewards during pixel accumulation, we introduce a novel discrepancy reward. Extensive experiments show that SegPAR significantly outperforms black-box baselines in sparsity efficiency and MIoU reduction, while remaining competitive with white-box sparse attacks. Code is available at https://github.com/KAU-QuantumAILab/SegPAR.

Dongsu Song, DaeYun GO, Boseung Seo +1

Interdisciplinary Program in Space Systems Engineering, Korea Aerospace University, South Korea · Department of Computer Science, Korea Aerospace University, South Korea · Department of Artificial Intelligence, Korea Aerospace University, South Korea

Black-Box Adversarial Attacks Semantic Segmentation

Aug 11, 2026cs.AI

Hidden in Plain Sight: Diffusion-Based Unrestricted Robotic Attacks on Vision-Language-Action Models

Vision-Language-Action (VLA) models have shown strong capabilities in controlling robots across diverse manipulation tasks. However, their adversarial robustness remains largely underexplored, and exploiting this weakness can lead to physical-world harm. Existing attacks on VLA models often rely on pixel-space perturbations or white-box access, resulting in noticeable artifacts and limited deployability in real-world robotic systems. In this work, we propose DURA, a diffusion-based unrestricted robotic attack that generates visually natural adversarial patches for VLA models. DURA supports both white-box and black-box attack settings, where the black-box setting requires only the predicted actions of the victim model. By optimizing along the latent trajectory of a pretrained diffusion model, DURA generates visually natural patches while steering the robot toward attacker-specified target actions. Extensive experiments in both simulation and the real physical world show that DURA consistently outperforms existing methods. Our findings expose a safety risk for physically deployed VLA models and call for stronger defenses.

Jiahui Han, Yuhui Yao, Xin Wang +6

1Xi’an Jiaotong University · 2Shanghai AI Laboratory · University of Science and Technology of China

Adversarial Attacks Adversarial Attacks on VLA Models Black-Box Adversarial Attacks Physical Adversarial Attacks

Aug 9, 2026cs.CR

Toward Metacognitive One-Shot Indirect Prompt Injection: Strategy Abstraction Via Outcome-Conditioned Reflection

Tool-using large language model (LLM) agents are vulnerable to indirect prompt injection (IPI), in which malicious instructions embedded in external observations manipulate subsequent agent decisions and actions. Most existing adaptive attacks rely on repeatedly querying and refining against the target agent, whereas realistic attackers may have only a single opportunity to interact with an unknown target agent. We propose SAVOR (Strategy Abstraction Via Outcome-Conditioned Reflection), which shifts attack adaptation from test-time iteration to offline strategy distillation. SAVOR performs outcome-conditioned reflection over successful and failed trajectories collected from disjoint training environments, validates context-conditioned candidate strategies, and iteratively consolidates them into a reusable strategy memory. At test time, the frozen memory guides the generation of a single payload for each unseen target, requiring only one target-agent query and no target-agent feedback. Across two benchmarks and three victim models, SAVOR attains the highest average attack success rate in all six settings, leading the strongest prior attack by 2.5 to 11.8 points and the same injection channel without strategy learning by 23.1 points on Agent Security Bench, which holds out attacker tools, and 28.6 points on OpenClaw-IPI, an executable benchmark we introduce that holds out attack goals and verifies attacks through tool interactions and execution receipts. A memory learned under one defense also transfers to another.

Sihan Hou, Xinmeng Hou, Zhijun Zhang +5

1Nankai University · 2Nanyang Technological University · 3Technical Lead, R&D, Tianjin 712 Mobile Communication Co., Ltd. +1

AI Agent Security Benchmarks Indirect Prompt Injection Prompt Injection Attacks on LLMs Black-Box Adversarial Attacks Prompt Injection Attacks on AI Agents

Aug 9, 2026cs.CV

IDATA: Scalable Invertible Diffusion for Unrestricted Adversarial Transfer Attack

Unrestricted adversarial transfer attacks are important for evaluating the black-box robustness of deep visual models. Diffusion-based attacks have shown promising transferability and visual imperceptibility by optimizing adversarial perturbations along denoising trajectories in latent space. However, existing methods are limited by two challenges: memory-intensive multistep backpropagation and frequency-agnostic perturbation over intermediate latents. To address these issues, we propose IDATA, a memory-efficient diffusion framework for unrestricted adversarial transfer attack. IDATA consists of two key components: an Invertible Diffusion Module (IDM) and a Low-Frequency Constraint Module (LFCM). Specifically, IDM reformulates adversarial optimization over diffusion trajectories as an invertible process, enabling constant-memory backpropagation through on-demand reconstruction of intermediate states instead of storing the full denoising chain. Moreover, LFCM leverages Discrete Wavelet Transform (DWT) to decompose latent variables into low- and high-frequency components, restricting perturbations to semantically stable low-frequency subspaces, thereby improving transferability while preserving visual imperceptibility. Extensive experiments on multiple benchmarks and diverse model architectures demonstrate that IDATA consistently outperforms state-of-the-art baselines in attack success rate, memory efficiency, and visual imperceptibility. These results suggest that IDATA is a promising tool for black-box robustness evaluation of deep visual models. Code is available at https://github.com/colourful-pan/IDATA.

Yi Pan, Jun-Jie Huang, Tianrui Liu +3

College of Computer Science and Technology

Adversarial Attacks Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks Consistent Adversarial Attacks Adversarial Transferability Diffusion Models

Aug 8, 2026cs.AI

Query-Only Backdoor Attacks on Self-Evolving Skills via Trajectory Poisoning

Agentic skills improve large language model (LLM) agents by encoding reusable procedures for complex tasks. However, manually authored skills often adapt poorly to long-horizon tasks and changing environments. To address the limitation, self-evolving skill systems have been developed to automatically construct and update skills from execution trajectories, shifting skill acquisition from external marketplaces to a trusted evolution pipeline. By replacing external skill acquisition with trusted internal construction, self-evolving skill systems reduce exposure to skill injection attacks that rely on direct skill manipulation. However, this skill evolution pipeline may introduce a new attack surface in which an attacker can indirectly steer skill evolution by inducing compromised trajectories through agent interactions. To demonstrate the threat, we propose Trajectory Backdoor Attack (TBA), a query-only attack that steers a trusted skill-evolution pipeline toward producing a backdoored skill. Specifically, we craft attacker-submitted queries to lead the agent to perform the target action and explicitly state the corresponding activation condition in the trajectory. We repeat the same condition-action pattern across diverse triggered tasks, while leaving clean queries unchanged, encouraging the evolver to consolidate the pattern as a reusable trigger-dependent rule into the evolved skill. Experiments on three benchmarks across two skill-evolution systems using four open- and closed-source backbone models demonstrate that TBA reliably implants conditional backdoors while preserving clean-task utility, matching or even surpassing direct skill injection. The results reveal a critical vulnerability in trajectory-driven skill evolution.

Yuyang Luo, Haoran Wang, Kai Shu

1Emory University

LLM Backdoor Attacks Adversarial Attacks Agent Skill Learning Black-Box Adversarial Attacks Self-Evolving Agents

Aug 7, 2026cs.CR

Adversarial Attacks on Deep OCR Systems

Deep-OCR (DeepSeek-OCR) advances document recognition by treating the visual modality as an optical compression medium, enabling long-context OCR at low token cost. However, its increased complexity may introduce new security vulnerabilities. In this paper, we present, to the best of our knowledge, the first pure black-box adversarial attack against a generative OCR vision-language model, where only the decoded string can be queried and no gradients, logits, or model internals are available. We recast the attack as a zeroth-order optimization problem driven by a bounded scalar loss defined directly on the string output via sequence similarity, and estimate the gradient with a random-direction finite-difference scheme whose query cost is independent of the image dimension. An Adam update with ell_infinity projection yields imperceptible perturbations for both untargeted and targeted objectives. Pilot experiments on Deep-OCR validate the string-only attack and evaluation pipeline and expose severe qualitative decoder failures, including repetition, truncation, and prompt leakage. They also show that controlled targeted rewriting remains substantially harder than untargeted degradation; we avoid claiming targeted success until the pre-registered evaluation is complete.

Wenbo Sun, Hongzong LI, Yanyun Wang +5

Nanjing University of Aeronautics and Astronautics · Northwestern Polytechnical University · The Chinese University of Hong Kong +4

Adversarial Attacks on VLMs Adversarial Attacks Black-Box Adversarial Attacks Optical Character Recognition

Aug 7, 2026cs.CR

Casting the Net! Revisiting MasterFace Impersonation Attacks

Impersonation is a fundamental security threat in face recognition systems (FRSs). While the security of FRSs has been challenged by various attack vectors, under realistic adversarial capabilities, e.g., a limited number of decision-only authentication trials and no internal system knowledge, most attack techniques become infeasible. As a result, impersonation by zero-effort impostors, characterized by false match rate (FMR), is commonly regarded as a standalone baseline. A few years ago, impersonation attacks based on MasterFaces emerged as a notable security threat that could break the barrier of the FMR-based baseline under such realistic constraints. However, they were believed not to yield impersonation above the standard FMR in modern FRSs, as discussed by multiple follow-up studies. In this paper, we demonstrate that even legitimate access to public commercial APIs allows an adversary to amplify impersonation rates through MasterFaces, resulting in a non-trivial impersonation attack beyond FMR on downstream applications built on top of these APIs. We observe that several real-world FRS deployments are implemented using commercial APIs, and that the backend service provider is publicly disclosed or trivially inferable. As a result, the adversary can purchase these pay-as-you-go API services without requiring any additional privilege over the target FRS. From this observation, we formalize the MasterFaces attack as a maximum coverage problem over the biometric representation space, which we call a NET, and show that the adversary can construct an API-tailored NET by leveraging the geometric structure of the representation space. We demonstrate that our attack amplifies the impersonation rates of several open-source and commercial API-based FRSs by up to 9.5

\times

within at most 30 authentication trials, compared to those expected from the standard FMR.

Seunghun Paik, Sunpill Kim, Chanwoo Hwang +1

Hanyang University Seoul, Republic of Korea

Biometric Identification Adversarial Attacks Black-Box Adversarial Attacks Face Recognition

Aug 5, 2026cs.CV

ColorFD: A Finite-Difference Guided Black-Box Physical Adversarial Attack for Remote Sensing Object Detection

Although deep neural network-based remote sensing object detectors have achieved strong performance, they remain vulnerable to adversarial perturbations. Existing studies mainly focus on digital or white-box settings, whereas black-box physical attacks remain underexplored. These attacks are often constrained by limited physical feasibility and inefficient optimization in high-dimensional search spaces. To address these challenges, this paper proposes ColorFD, a black-box physical attack based on multiple pure-color patches. The patch positions and color parameters are jointly optimized using Differential Evolution (DE). A target-wise fitness and selection mechanism evaluates the attack state of each target and preserves target-specific improvements during evolution. Two guidance strategies further constrain the patch search space. Key-region localization identifies sensitive regions through finite-difference color probing. Common-feature extraction provides category-level spatial priors and avoids repeated localization. Although evaluated on aircraft, the formulation is not inherently restricted to this category. Experiments on YOLOv3u, YOLOv5u, and Faster R-CNN show that ColorFD outperforms the tested black-box patch method across all evaluated detectors and remains competitive with strong white-box baselines. Physical-world experiments further demonstrate that the optimized pure-color patches can be transferred from the digital domain to real imaging conditions.

Tiannuo Guo, Guhang Qiu, Yuzhen Xie +3

College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China

Remote Sensing Image Understanding Adversarial Patch Attacks Remote Sensing Small Object Detection Black-Box Adversarial Attacks Physical Adversarial Attacks

Aug 5, 2026cs.CV

Season: Spectrum-Aware Orthogonal Gradient Refinement for Transfer-Based Adversarial Attacks

Transfer-based adversarial attacks often transfer poorly across heterogeneous architectures because CNNs favor local textures while Vision Transformers (ViTs) rely on global shapes. We propose Season, a spectrum-aware orthogonal gradient refinement framework for L-infinity transfer attacks against black-box target models on ImageNet, using a white-box surrogate. Season decomposes each update into a low-frequency branch capturing structural cues and a high-frequency branch capturing textures. A low-saliency guidance scheme reallocates high-frequency energy to background regions, preserving foreground structures that ViTs depend on. An orthogonal projection then forces the textural update to lie in the orthogonal complement of the structural direction, mitigating feature interference. As a training-free plug-and-play wrapper, Season enhances eight gradient-stabilization and input-enhancement attacks without modifying their cores. Across eight CNN, ViT, and MLP targets, Season improves transfer success rate by 6.6 percentage points on average and up to 16.0 points over strong baselines under a unified protocol.

Tianyi Wang, Zhenghao Gao, Shengjie Xu

Tongji University Shanghai, China · Huazhong University of Science and Technology · Wuhan LightRead Intelligent Technology Co., Ltd. Wuhan, China

Adversarial Attacks Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks Adversarial Transferability

Aug 4, 2026cs.CL

ICO: Enhancing Semantic-Shift Jailbreaks via Iterative Context Optimization

Foundation models have achieved remarkable success across diverse tasks, but they remain vulnerable. To investigate such vulnerabilities, semantic-shift jailbreaks have recently emerged as a promising attack paradigm. They bypass explicit safety mechanisms by replacing harmful terms in original harmful questions with benign alternatives and leveraging contextual information to induce the target model to reinterpret these alternatives as their corresponding harmful concepts. However, existing semantic-shift jailbreaks often achieve limited effectiveness. In this work, we reveal that this limitation arises from overlooking the semantic-shift capability of contexts. Through systematic analysis, we find that contexts exhibit substantially different abilities in inducing semantic shifts: contexts with stronger semantic-shift capabilities are more likely to guide models toward recovering harmful meanings and achieving successful jailbreaks. Based on this finding, we systematically identify and distill the characteristics of effective contexts and propose a black-box context-aware semantic-shift jailbreak framework with Iterative Context Optimization (ICO). In each iteration, ICO leverages these characteristics and feedback from the target model to optimize contexts. Extensive experiments on three datasets and eight target foundation models demonstrate that ICO consistently outperforms eight state-of-the-art baselines, achieving an average attack success rate of 74.6%.

Hujian Zhu, Yihao Huang, Felix Juefei-Xu +5

East China Normal University, Shanghai, China · New York University, New York, USA · The Hong Kong Polytechnic University, Hong Kong, China +2

Adversarial Attacks on LLMs Jailbreak Attacks LLM Jailbreak Attacks Black-Box Adversarial Attacks

Aug 2, 2026cs.CR

Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks

We report a counter-intuitive interaction between image inputs and existing black-box defenses on Vision--Language Models (VLMs): pairing an encoded jailbreak prompt with an unrelated decoy image can sharply lower attack success rate (ASR). The operative change is in the defense pipeline, not in the image. Across five frontier VLMs, two encoded-attack families, and three black-box defenses, a caption-mediated defense (ECSO) that leaves ASR essentially unchanged on text-only encoded input drops it by up to

73

pp once a content-free decoy is attached; every non-saturated contrast is significant under exact McNemar tests. We advance two hypotheses for this pattern, supported by indirect evidence rather than pipeline introspection, since a black-box threat model precludes inspecting vendor internals: caption-mediated defenses branch on image presence, and intrinsic image-side safety engages on image-resident content. Three controls constrain the explanation. Blank-canvas and natural-photograph decoys reproduce the effect on every model, implicating image presence rather than content; the effect replicates on three open-weight VLMs served with no moderation layer, so it is not a vendor-filtering artifact; and a non-symbolic, meaning-based encoder reproduces it, so it is not specific to symbolic obfuscation. Attaching a decoy unconditionally is not deployable --- it raises benign refusal to

20

--

79\%

, an inflation of

+10

to

+67

pp --- but gating attachment on a lightweight encoded-input detector returns benign refusal to the text baseline while preserving the safety gain wherever the detector fires, making detector recall the binding constraint. Under adaptive attacks that target the caption-mediated re-check, the effect degrades but holds. We frame this as an observation about pipeline interaction, not as a robust defense.

Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2

VLM Robustness Adversarial Attacks on VLMs Vision-Language Models Black-Box Adversarial Attacks

Aug 2, 2026cs.CL

Mind the Gap: Zero-Query Jailbreaks via Filter-Generator Discrepancy in Text-to-Image Systems

Text-to-image (T2I) systems typically have prompt-level safety filters before the generator to block unsafe requests, yet such systems remain vulnerable to malicious jailbreak prompts. Transfer-based attacks construct adversarial prompts offline without querying the target, but they tend to overfit to a single surrogate. Moreover, they explore a large search space in which semantic or perceptual similarity alone cannot guarantee both filter evasion and preservation of the unsafe generation intent, wasting effort on low-potential candidates. We observe that the filter and the generator process the same prompt under different objectives and representations, and term this gap the Filter-Generator Discrepancy (FGD), which allows a perturbation to reduce a prompt's perceived risk to the filter while preserving the visual concept needed by the generator. Building on FGD, we propose a zero-query jailbreak framework that screens perturbations into a high-potential candidate set via observable discrepancy rules at the tokenization and semantic stages, and then performs a surrogate-ensemble evolutionary search that requires no access to the target. Experiments on six black-box pipelines and a commercial online service show that our method consistently outperforms representative baselines, raising the average attack success rate to 29.2% (MHSC) and 33.3% (Q16) across the six pipelines and improving over the strongest baseline by about 8 and 12 percentage points, respectively.

Wanguang Li, Zhaoxin Wang, Handing Wang

School of Artificial Intelligence, Xidian University, Shaanxi, China

Adversarial Prompt Generation T2I Generation Safety Filtering Multimodal Jailbreak Attacks Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks

Jul 30, 2026cs.AI

Old Tricks, New Models: How Simple Image Transformations Break Modern AI-based Content Moderation

While automated content-moderation systems have become essential for screening harmful content at scale, conventional task-specific classifiers often provide limited policy cov- erage and contextual understanding. Recently, commercial multimodal moderation APIs built on large foundation models have been introduced with the promise of providing broader and more capable safety filters. In this work, we analyze whether this shift also yields more robust image moderation. We conduct a large-scale black-box evaluation on three established commercial image-moderation services and compare their robustness. By evaluating seven simple, model-agnostic image transformations across multiple providers, datasets, harm categories, perceptual-similarity constraints, and transformation intensities, we find that: (1) all three commercial services can be bypassed using inexpensive image transformations that require no gradients, surrogate models, or knowledge of the target system; (2) even fixed transformations such as color inversion and grayscale conversion induce unsafe-to-safe decision changes while preserving content that remains recognizable to humans; (3) their robustness varies substantially across datasets and harm categories, with multimodal content and self-harm exhibiting pronounced vulnerabilities. This yields the conclusion that replacing conventional moderation classifiers with foundation-model-based APIs does not, by itself, provide a reliable security boundary. Such systems must be evaluated under realistic transformations and deployed as one component of a layered moderation pipeline rather than as standalone safety filters.

Marco Alecci, Francesco Marchiori, Iyiola Emmanuel Olatunji +2

Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, Luxembourg · Department of Mathematics, University of Padua, Padua, Italy

Multimodal Robustness Adversarial Attacks Content Moderation Safety Filtering Black-Box Adversarial Attacks Multimodal Foundation Models

Jul 29, 2026cs.CR

Attack Ensembles Expose a Safety-Utility Trade-off in Black-Box Guard Defenses Against Encoded VLM Jailbreaks

Safety classifiers ("guards") are the dominant black-box defense for vision-language models, yet a guard judges an input's surface form, not its meaning: a harmful request re-encoded as set theory, formal logic, a classical language, code, or text rendered inside an image slips past a guard that would block it in plain language - the decode gap. The standard fix is a preprocessor that recovers image content and decodes the encoding before the guard. We build one and evaluate it against an ensemble of eleven published encoding attacks, counting a behavior as broken if any attack succeeds. That metric separates two mechanisms such defenses conflate. Restoring a view the guard never had improves it on both axes at once: it blocks far more attacks, and, measured on a category-balanced benign set, it blocks fewer benign requests, because restating a request normalizes the borderline phrasing a classifier over-flags. It still does not make the system safer: against an attacker free to choose among eleven encodings, closing one channel relocates the success rather than removing it, and no ensemble contrast survives multiple-comparison correction. What does lower ensemble attack success is re-screening the recovered pre-decode surface, and that step is where the entire benign cost falls. The safety-utility trade-off is therefore not a property of recovery; it is localized to one step. Across the full guard x target x condition factorial, no configuration reaches an ensemble attack-success rate at or below 40% while holding benign over-refusal under 70%. The per-attack averages usually reported understate the attacker roughly fourfold, which is why this frontier is easy to miss. Composing across defense families is the one lever that moved the safety axis, beating every configuration we measured, and still landing far outside any deployable refusal budget.

Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +7

Northeastern University

VLM Robustness Adversarial Attacks on VLMs Safety Filtering Black-Box Adversarial Attacks

Jul 28, 2026cs.CV

TIGA: Trajectory-Injected Generative Attack against Black-box AIGC Detectors

Recent diffusion models have achieved remarkable realism in facial image synthesis, posing growing challenges to artificial intelligence-generated content (AIGC) forensic detectors.Existing evasion methods typically perturb pre-generated images or require detector-aware training, which may introduce visible or statistical artifacts and limit applicability when the diffusion model must remain frozen and the target detector is accessible only through black-box queries. We propose Trajectory-Injected Generative Attack (TIGA), a source-image-free and training free framework that generates detector-evasive images within a single diffusion sampling trajectory. TIGA steers the latent Denoising Diffusion Implicit Model (DDIM) trajectory so that adversarial properties emerge during generation rather than being added afterward. TIGA first aggregates gradients from multiple white-box surrogate detectors to form a transferable, sign-aware prior, and then performs anisotropic directional search with symmetric finite-difference queries to estimate the black-box target response. The estimated directions are stabilized by decayed momentum and injected according to the DDIM noise schedule, with frequency-domain reshaping to suppress high frequency artifacts. Experiments on surrogate and unseen specialized forensic detectors show that TIGA achieves strong blackbox attack performance, transferability, and high robustness under common post-processing operations without source images or diffusion-model retraining, while preserving high perceptual quality.

Xia Du, Zhuosen Bao, Zheng Lin +4

School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, 361000, China · Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg, L-1855 Luxembourg, Luxembourg · School of Computer Science, Engineering Research Center of Machine Learning and Industry Intelligence, Sichuan University, Chengdu, China, 610020, China +2

Adversarial Attacks Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks

Jul 23, 2026cs.CV

GeoThreat: Transferable Targeted Adversarial Attacks on Large Vision-Language Models for Remote Sensing Image Interpretation

Adversarial attacks against large vision-language models (LVLMs) serve as an effective means of assessing their robustness in cross-modal semantic understanding. Existing studies mainly focus on corrupting visual inputs to induce predefined erroneous responses in general vision-language tasks, whereas corresponding investigations in remote sensing fields remain largely underexplored. Compared with natural image understanding, remote sensing image interpretation requires joint reasoning over local discriminative cues and global scene context. This poses additional challenges to achieving transferable semantic manipulation toward specified responses under black-box settings. To tackle these challenges, we propose GeoThreat, a transferable targeted adversarial attack method against LVLMs for remote sensing image interpretation. Specifically, GeoThreat modulates adversarial representations in accordance with the target content at both conceptual and perceptual levels. The class tokens from surrogate image encoders are employed as conceptual representations, while perceptual representations are distilled from patch tokens of the adversarial example through collaborative importance estimation. Beyond merely rolling out attention scores across layers, we incorporate adversarial-target similarity gradients to more faithfully characterize the relevance of local visual cues to the intended semantic manipulation. The perceptual representations are then dynamically aligned with target patch tokens in a cross-attentive manner, facilitating the adaptation of local cues toward designated semantic details. Finally, adversarial perturbations are iteratively updated via ensemble-based joint optimization of conceptual calibration and perceptual adaptation. Extensive experiments across diverse LVLMs demonstrate the superiority of GeoThreat in both transferability and controllability.

Yimin Fu, Yuefeng Bai, Baicheng Pan +2

Department of Mathematics, Hong Kong Baptist University, Hong Kong, China · School of Automation, Northwestern Polytechnical University, Xi’an, 710072, China

Remote Sensing Image Understanding Adversarial Attacks on VLMs Large Vision-Language Models Transfer-Based Adversarial Attacks Black-Box Adversarial Attacks