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

May 16, 2026cs.CY

Adversarial Fragility and Language Vulnerability in Clinical AI: A Systematic Audit of Diagnostic Collapse Under Imperceptible Perturbations and Cross-Lingual Drift in Low-Resource Healthcare Settings

Current clinical artificial intelligence (AI) systems are evaluated almost exclusively on clean, standardised, English-language inputs, conditions that do not reflect the realities of healthcare delivery in low-resource settings. This study presents the first systematic dual audit of two orthogonal safety vulnerabilities in clinical AI: adversarial image fragility and cross-lingual diagnostic drift. Using DenseNet121, the architecture underlying CheXNet, fine-tuned on the COVID-QU-Ex chest X-ray dataset (85,318 images; COVID-19, Non-COVID Pneumonia, Normal), we demonstrate that diagnostic accuracy collapses from 89.3% to 62.0% under a Fast Gradient Method (FGM) perturbation of epsilon=0.021, a magnitude imperceptible to the human eye. Standard defensive strategies including Gaussian smoothing and ensemble voting failed to restore clinical safety. In a parallel language fragility experiment, we tested Llama3.1:8b and NatLAS (N-ATLAS) on 20 COVID-19 clinical cases presented in Standard English, Nigerian Pidgin (Naija), and Yoruba-inflected English. Both models exhibited significant accuracy degradation: Llama3.1:8b dropped from 80.0% to 65.0% on Pidgin; NatLAS, an African-context model, collapsed from 85.0% to 55.0%, with diagnosis consistency falling to 50%. These findings establish a quantitative failure envelope for clinical AI under conditions representative of Primary Health Centre (PHC) deployment in Nigeria, and motivate urgent calls for adversarially hardened, linguistically inclusive clinical AI architectures.

Anthonio Oladimeji Gabriel, Ahmad Rufai Yusuf

Centre for Clinical Intelligence & Safety, Ìyàwó, Nigeria · Tomorrow University of Applied Sciences, Germany

Multilingual Language Model Evaluation Healthcare Adversarial Attacks Adversarial Robustness Clinical Language Model Evaluation

May 15, 2026cs.CV

Right Predictions, Misleading Explanations: On the Vulnerability of Vision-Language Model Explanations

Explanation mechanisms are increasingly used to support transparency and trust in vision-language models (VLMs), particularly in settings where model decisions require human oversight. However, the robustness of these explanations remains insufficiently understood. In this work, we investigate whether explanation heatmaps in VLMs, particularly CLIP-based models, faithfully reflect model reasoning under adversarial conditions. We show that explanation maps can be systematically manipulated while preserving the model's original prediction, revealing a disconnect between predictive behavior and explanation faithfulness. To study this vulnerability, we introduce X-Shift, a novel grey-box attack that perturbs patch-level visual representations to redirect explanation heatmaps toward semantically irrelevant regions without altering the predicted output. Unlike conventional adversarial attacks that aim to induce misclassification, X-Shift specifically targets the integrity of the explanation process itself. The attack operates without modifying model parameters and generalizes across multiple CLIP architectures and explanation methods. We evaluate the proposed approach on ImageNet-1k, MS-COCO, and Flickr30K, demonstrating consistent degradation in explanation alignment under imperceptible perturbations while maintaining prediction stability. Furthermore, standard prediction-oriented adversarial attacks fail to reproduce the same explanation-shifting behavior even under substantially larger perturbation budgets. Our findings highlight a fundamental limitation of current explanation mechanisms in VLMs and raise concerns about their use as reliable indicators of model trustworthiness in high-impact applications.

Narges Babadi, Hadis Karimipour

Department of Electrical and Software Engineering, University of Calgary, Calgary, Canada.

VLM Robustness Adversarial Attacks on VLMs Adversarial Attacks VLM Interpretability

May 15, 2026cs.CR

SLEIGHT-Bench: A Benchmark of Evasion Attacks Against Agent Monitors

Since autonomous coding agents generate complex behaviors at high-volume, we may want to use other LLMs to monitor actions to reduce the risk from dangerous misaligned behavior. To better understand the limitations of such monitors against the diverse attack strategies that a coding agent could use, we present SLEIGHT-Bench (Subtle Low-itEration Insight-Guided Harmful Transcripts), a benchmark of synthetic transcripts containing 40 attacks across 11 categories, each showing a coding agent covertly pursuing a harmful objective (e.g. weight exfiltration, credential theft, unmonitored rogue deployment). We find that 20 of 40 attacks are never caught by an Opus 4.6 monitor with extended thinking across 10 trials at a 1% false-positive rate, while the overall catch rate is 32%. We identify several evasion strategies such as exploiting model priors, user instruction ambiguity, and state manipulation, which facilitate creating attacks that evade frontier monitors. We also elicit stronger monitor performance using coding agents as monitors versus regular prompted monitors, and for some evasion strategies show improved catch rates with targeted monitor prompts. Our dataset and evaluation framework are available at https://github.com/safety-research/sleight-bench and https://huggingface.co/datasets/sleightbench/SLEIGHT-Bench.

Elle Najt, Colin Toft, Tyler Tracy +2

1Anthropic Fellows Program · University of Waterloo · 3Redwood Research +1

Software Engineering Agents Adversarial Attacks AI Agent Security AI Agent Security Benchmarks AI Agent Monitoring

May 15, 2026cs.CV

Semantic Smoothing via Novel View Synthesis for Robust SAR Image Classification

Deep neural networks are vulnerable to adversarial perturbations, limiting deployment in safety-critical applications such as synthetic aperture radar (SAR) automatic target recognition (ATR). Randomized smoothing improves robustness by averaging predictions over noisy inputs, but isotropic noise often fails to preserve the semantic structure of SAR imagery. We propose semantic smoothing, a defense that replaces noised-based perturbations with structured randomized transformations generated by a novel view synthesis model. For SAR, we condition on acquisition geometry to synthesize multiple plausible radar views. Predictions across generated randomized views are aggregated to form a robust classifier. Experiments show that semantic smoothing improves robustness against standard attacks, such as FGSM and PGD, and SAR-specific attacks, such as OTSA and SMGAA, while also increasing clean classification accuracy. These results demonstrate that randomized smoothing via semantically preserving geometric transformations is a promising alternative to isotropic noise for adversarial defense in structured sensing domains.

Daniel Brignac, Fengwei Tian, Banafsheh Latibari +2

The University of Arizona Tucson, Arizona, United States

Randomized Smoothing Adversarial Attacks Neural Network Robustness Adversarial Robustness Synthetic Aperture Radar Image Classification

May 14, 2026cs.LG

Fast Adversarial Attacks with Gradient Prediction

Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even "fast" attacks such as FGSM remain throughput-limited by the cost of a backward pass. We introduce a family of attacks that eliminates the backward pass by predicting the input gradient from forward-pass hidden states via a lightweight linear regression. Theoretically, we derive exact affine conditional gradient means, showing optimality in the (idealized) NTK regime. Empirically, our methods work when applied to practical finite-width models; we recover much of FGSM's attack performance while using only a small fraction of the time, corresponding to a

532\%

increase in throughput. These results suggest gradient prediction as a simple and general route to significantly faster adversarial generation under realistic wall-clock constraints.

Kamil Ciosek, Aleksandr V. Petrov, Nicolò Felicioni +1

Spotify

Adversarial Attacks Neural Network Robustness Adversarial Examples

May 14, 2026cs.CR

Enabling Adversarial Robustness in AI Models through Kubeflow MLOps

AI models are increasingly deployed in cloud-native environments to support scalable and automated services. However, while platforms such as Kubernetes provide strong infrastructure orchestration, security mechanisms specifically designed to protect deployed AI models remain limited. This paper presents security measures for AI models deployed in Kubernetes clusters. The proposed architecture integrates Kubeflow-based MLOps to automatically detect adversarial attacks during the inference phase and trigger defense mechanisms that preserve the model's accuracy and reliability. Specifically, a Fast Gradient Sign Method (FGSM) attack is applied at inference time, and a Projected Gradient Descent (PGD)-based adversarial training defense is automatically deployed when a degradation in accuracy is detected. The experimental results indicate that the deployed defense robustifies the model, significantly recovering accuracy relative to the degradation caused by the attack.

Stavros Bouras, Ioannis Korontanis, Antonios Makris +1

School of Electrical and Computer Engineering, National Technical University of Athens, Greece · Department of Informatics and Telematics, Harokopio University of Athens, Greece

Adversarial Attacks Adversarial Robustness Adversarial Example Detection

May 14, 2026cs.CV

Systematic Discovery of Semantic Attacks in Online Map Construction through Conditional Diffusion

Autonomous vehicles depend on online HD map construction to perceive lane boundaries, dividers, and pedestrian crossings -- safety-critical road elements that directly govern motion planning. While existing pixel perturbation attacks can disrupt the mapping, they can be neutralized by standard adversarial defenses. We present MIRAGE, a framework for systematic discovery of semantic attacks that bypass adversarial defenses and degrade mapping predictions by finding plausible environmental variation (e.g. shadows, wet roads). MIRAGE exploits the latent manifold of real-world data learned by diffusion models, and searches for semantically mutated scenes neighboring the ground truth with the same road topology yet mislead the mapping predictions. We evaluate MIRAGE on nuScenes and demonstrate two attacks: (1) boundary removal, suppressing 57.7% of detections and corrupting 96% of planned trajectories; and (2) boundary injection, the only method that successfully injects fictitious boundaries, while pixel PGD and AdvPatch fail entirely. Both attacks remain potent under various adversarial defenses. We use two independent VLM judges to quantify realism, where MIRAGE passes as realistic 80--84% of the time (vs. 97--99% for clean nuScenes), while AdvPatch only 0--9%. Our findings expose a categorical gap in current adversarial defenses: semantic-level perturbations that manifest as legitimate environmental variation are substantially harder to mitigate than pixel-level perturbations.

Chenyi Wang, Ruoyu Song, Raymond Muller +5

University of Arizona · Purdue University · Lawrence Livermore National Laboratory +2

HD Map Construction Adversarial Attacks Autonomous Driving Perception

May 13, 2026cs.CV

Backbone is All You Need: Assessing Vulnerabilities of Frozen Foundation Models in Synthetic Image Forensics

As AI-generated synthetic images become increasingly realistic, Vision Transformers (ViTs) have emerged as a cornerstone of modern deepfake detection. However, the prevailing reliance on frozen, pre-trained backbones introduces a subtle yet critical vulnerability. In this work, we present the Surrogate Iterative Adversarial Attack (SIAA), a gray-box attack that exploits knowledge of the detector's ViT backbone alone and operates entirely within the target detector's feature space to craft highly effective adversarial examples. Through our experiments, involving multiple ViT-based detectors and diverse gray-box scenarios, including few-shot learning, complete training misalignment and attack transferability tests, we demonstrate that this vulnerability consistently yields high attack success rates, often approaching white-box performance. By doing so, we reveal that backbone knowledge alone is sufficient to undermine detector reliability, highlighting the urgent need for more resilient defenses in adversarial multimedia forensics.

Chiara Musso, Joy Battocchio, Andrea Montibeller +1

University of Trento Trento, Italy

Adversarial Attacks Vision Transformer Deepfake Detection

May 13, 2026cs.AI

Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning

Multi-modal multi-agent systems (MM-MAS) have gained increasing attention for their capacity to enable complex reasoning and coordination across diverse modalities. As these systems continue to expand in scale and functionality, investigating their potential vulnerabilities has become increasingly important. However, existing studies on adversarial attacks in multi-agent systems primarily focus on isolated agents or unimodal settings, leaving the vulnerabilities of MM-MAS largely underexplored. To bridge this gap, we introduce HAM

^{3}

, a Hierarchical Attack framework for multi-modal multi-agent systems that decomposes attacks into three interconnected layers. Specifically, at the perception layer, HAM

^{3}

mounts attacks by perturbing visual inputs, textual inputs, and their fused visual-textual representations. At the communication layer, it performs communication-level attacks that corrupt message content and interaction topology, such as manipulating shared context or communication links to distort collective information flow. At the reasoning layer, it conducts reasoning-level attacks that interfere with each agent's cognitive pipeline, biasing reasoning trajectories and ultimately compromising final decisions. We evaluate HAM

^{3}

on the GQA benchmark through multi-agent systems built on distinct reasoning paradigms including ReAct, Plan-and-Solve, and Reflexion. Experiments demonstrate that our framework achieves an Attack Success Rate of up to 78.3%, with reasoning-layer attacks being the most effective. More than half of the successful attacks lead multiple agents to produce consistent errors. These findings offer valuable insights for building more robust and interpretable multi-agent intelligence.

Hao Zhou, Tiru Wu, Yan Jiang +3

Multimodal Robustness Adversarial Attacks Multi-Agent Reasoning Multi-Agent System Security Multi-Agent Communication

May 13, 2026cs.LG

Finding the Weakest Link: Adversarial Attack against Multi-Agent Communications

Multi-agent systems rely on communication for information sharing and action coordination, which exposes a vulnerability to attacks. We investigate single-victim communication perturbation attacks against Multi-Agent Reinforcement Learning-trained systems and propose methods that use gradient information from the Jacobian to identify which messages, agent, and timesteps are most susceptible to attack and have the greatest impact on the system. We enhance these methods with two proposed adversarial loss functions that trade-off attack success for attack impact which also create more effective perturbations. We empirically demonstrate the effectiveness of our methods against two different multi-agent communication methods in navigation, PredatorPrey, and TrafficJunction environments. Our results show that our novel message selection method achieves a similar or greater impact than random message selection across almost all tested scenarios. Our victim selection, message selection, tempo, and loss functions improve attack effectiveness in half of the thirty scenarios we tested.

Maxwell Standen, Junae Kim, Claudia Szabo

The University of Adelaide · DST Group

Adversarial Attacks Adversarial Perturbations Multi-Agent System Security Multi-Agent Communication Multi-Agent Reinforcement Learning

May 12, 2026cs.CL

REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations

Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, making it important to systematically evaluate their reliability under realistic adversarial inputs. We formulate hallucination elicitation as a constrained optimization problem, where the goal is to find semantically coherent adversarial prompts that are equivalent to benign user prompts. Existing attack methods remain limited: discrete prompt-based attacks preserve semantic equivalence and coherence but search only over a limited set of prompt variations, while continuous latent-space attacks explore a richer space but often decode into prompts that are no longer valid rephrasings. To address these limitations, we propose REALISTA, a realistic latent-space attack framework. REALISTA constructs an input-dependent dictionary of valid editing directions, each corresponding to a semantically equivalent and coherent rephrasing, and optimizes continuous combinations of these directions in latent space. This design combines the optimization flexibility of continuous attacks with the semantic realism of discrete rephrasing-based attacks. Experiments demonstrate that REALISTA achieves superior or comparable performance to state-of-the-art realistic attacks on open-source LLMs and, crucially, succeeds in attacking large reasoning models under free-form response settings, where prior realistic attacks fail. Code is available at https://github.com/Buyun-Liang/REALISTA.

Buyun Liang, Jinqi Luo, Liangzu Peng +6

University of Pennsylvania

Adversarial Prompt Generation Adversarial Attacks Hallucination in Language Models Adversarial Attacks on LLMs LLM Reliability

May 12, 2026cs.LG

SoK: A Comprehensive Analysis of the Current Status of Neural Tangent Generalization Attacks with Research Directions

There is recently a serious issue that Deep Neural Networks (DNNs) training uses more and more unauthorized data. A clean-label generalization attack, one type of data poisoning attacks, has been suggested to address this issue. The Neural Tangent Generalization Attack (NTGA) is considered as the first well-known clean-label generalization attack under the black-box settings, which provided an unprecedented step in data protection approaches. In this paper, we conduct a comprehensive analysis on the state-of-the-art of NTGA; to the best of our knowledge, this is the first thorough analysis regarding NTGA. First, we provide a classification of attacks against DNNs with their explanations and relations to NTGA. Then, this paper presents a taxonomy of black-box attacks and demonstrate that the NTGA is the first clean-label generalization attack under the black-box setting. We further analyze the existing studies of NTGA and give a comprehensive comparisons of their findings by conducting our own experiments to verify these findings. Moreover, our extensive experiments show that NTGA is vulnerable to adversarial training and image transformations, and applying linear separability to NTGA-generated images makes them more susceptible to such vulnerablities. We present the pros and cons of NTGA and suggest ways to improve NTGA robustness based on our analysis. Our further experiments indicate that several recently proposed clean-label generalization attacks outperform NTGA on data protection. Finally, we unveil the necessity of further research with future research insights on NTGA.

Thushari Hapuarachchi, Kaiqi Xiong

University of South Florida Tampa, USA

Adversarial Attacks Adversarial Robustness Black-Box Adversarial Attacks Data Poisoning Attacks

May 12, 2026cs.CR

Still Camouflage, Moving Illusion: View-Induced Trajectory Manipulation in Autonomous Driving

Existing physical adversarial attacks on vision-based autonomous driving induce time-evolving perception errors, including biased object tracking or trajectory prediction, through (i) sophisticated physical patch inducing detection box drift when entering the view distance, or (ii) dynamically changing patches that cause different perception errors at different time. In both cases, viewing-angle variation is treated as a challenge, requiring adversarial patches to remain effective across frames under varying views, leading to complex multi-view optimization. In contrast, we show that viewing-angle variation itself can be turned into an attack tool. We design a new attack paradigm where a static, passive adversarial camouflage is mounted on a vehicle whose view-dependent appearance naturally evolves with relative motion, inducing consistent feature drift across frames. This causes the system to infer a physically plausible but incorrect trajectory, such as a false cut-in, which propagates to downstream decision-making and triggers unnecessary braking. Unlike prior approaches that require multi-view robustness or active intervention, our attack emerges from normal driving dynamics and is easy to deploy: a parked vehicle with a natural camouflage can induce hard braking in passing autonomous vehicles. We demonstrate the novel attack on nuScenes dataset, showing the effectiveness with an end-to-end success rate of up to 87.5%, measured by hard-braking events, and robustness across different scene backgrounds, victim vehicle speeds, and perception models.

Shuo Ju, Qingzhao Zhang, Huashan Chen +6

Institute of Information Engineering, Chinese Academy of Sciences · The University of Arizona · Beijing Jiaotong University +1

Adversarial Attacks Autonomous Driving Perception Physical Adversarial Attacks

May 12, 2026cs.LG

Quantum Adversarial Machine Learning: From Classical Adaptations to Quantum-Native Methods

Machine learning has revolutionized numerous industrial domains. Despite recent advances, machine learning models remain vulnerable to adversarial threats. Adversarial machine learning is a field that studies these vulnerabilities to build robust machine learning models. Quantum machine learning is an interdisciplinary field that bridges quantum computing and classical machine learning. While quantum machine learning shows potentials to outperform classical machine learning in complex tasks such as regression, classification, and generative modeling, it remains vulnerable to adversarial attacks. Given the recent advancements in quantum computing and machine learning, the quantum adversarial machine learning field has emerged to study the vulnerabilities of quantum machine learning, possible attacks, and novel quantum-enhanced defense strategies. In this survey, we provide a detailed overview on quantum adversarial machine learning and explore the existing attacks and countermeasures. We also review the theoretical underpinnings of this area, emerging trends, and critical challenges.

Roozbeh Razavi-Far, Mohammad Meymani, Erfan Mahmoudinia +6

Faculty of Computer Science, University of New Brunswick, Fredericton, Canada. · Department of Electrical Engineering, Amirkabir University of Technology, Tehran, Iran. · Faculty of Mathematical and Computer Science, Kharazmi University, Tehran, Iran. +4

Adversarial Attacks Adversarial Robustness Quantum Machine Learning

May 11, 2026cs.CR

Adversarial SQL Injection Generation with LLM-Based Architectures

SQL injection (SQLi) attacks are still one of the serious attacks ranked in the Open Worldwide Application Security Project (OWASP) Top 10 threats. Today, with advances in Artificial Intelligence (AI), especially in Large Language Models (LLMs), an opportunity has been created for automating adversarial attack tests to measure the defense mechanisms. In this paper, we aim to create a comprehensive evaluation of use cases that utilize LLMs for adversarial SQL injection generation. We introduce two novel LLM-based systems, Retrieval Augmented Generation for Adversarial SQLi (RADAGAS) and Reflective Chain-of-Thought SQLi (RefleXQLi), and compare them with existing baselines against 10 Web Application Firewalls (WAFs) and one execution-based MySQL validator. To perform a comprehensive test, we used six rule-based open-source WAFs (ModSecurity PL1--3, Coraza PL1--3), 2 AI/ML-based WAFs (WAF Brain, CNN-WAF), and 2 commercial WAFs (AWS WAF and Cloudflare WAF). For the LLM models, we used GPT-4o, Claude 3.7 Sonnet, and DeepSeek R1. Our tests consist of 240 experiments that generate 240,000 payloads and perform 2.2 million tests against WAFs. Our comprehensive evaluation reveals that RADAGAS-GPT4o outperforms other baseline models with a 22.73% bypass rate. The proposed RADAGAS variants are highly successful on AI/ML-based WAFs (92.49% on WAF-Brain by RADAGAS-DeepSeek, 80.48% on CNN-WAF by RADAGAS-Claude), but struggle to bypass rule-based WAFs (0--5.70% on ModSecurity and Coraza). In addition to these findings, another observation is that creating less diverse payloads achieves more bypasses, however they show poor results if the initially chosen payload is not successful. We observe that our findings provide a comprehensive view on using LLM-based approaches in security testing.

Ali Karakoc, H. Birkan Yilmaz

Department of Computer Engineering, NETLAB, Bogazici University, Istanbul, Turkey.

Retrieval-Augmented Generation Adversarial Attacks Cybersecurity LLMs for Cybersecurity

May 11, 2026cs.CV

Break the Brake, Not the Wheel: Untargeted Jailbreak via Entropy Maximization

Recent studies show that gradient-based universal image jailbreaks on vision-language models (VLMs) exhibit little or no cross-model transferability, casting doubt on the feasibility of transferable multimodal jailbreaks. We revisit this conclusion under a strictly untargeted threat model without enforcing a fixed prefix or response pattern. Our preliminary experiment reveals that refusal behavior concentrates at high-entropy tokens during autoregressive decoding, and non-refusal tokens already carry substantial probability mass among the top-ranked candidates before attack. Motivated by this finding, we propose Untargeted Jailbreak via Entropy Maximization(UJEM)-KL, a lightweight attack that maximizes entropy at these decision tokens to flip refusal outcomes, while stabilizing the remaining low-entropy positions to preserve output quality. Across three VLMs and two safety benchmarks, UJEM-KL achieves competitive white-box attack success rates and consistently improves transferability, while remaining effective under representative defenses. Our experimental results indicate that the limited transferability primarily stems from overly constrained optimization objectives.

Mengqi He, Xinyu Tian, Xin Shen +6

Australian National University, ACT, Australia · The University Of Queensland, Brisbane, Queensland, Australia · GE research, Niskayuna, New York, USA +2

Adversarial Attacks on VLMs Adversarial Attacks Multimodal Jailbreak Attacks Transfer-Based Adversarial Attacks Adversarial Transferability

May 11, 2026cs.MA

Skill Description Deception Attack against Task Routing in Internet of Agents

A new paradigm, Internet of Agents (IoA), is transforming networked systems into LLM-driven service networks, where heterogeneous agents collaborate through task routing based on their self-declared skill descriptions. Although this promising paradigm enables agentic, distributed, and advanced intelligence, it also exposes a new and overlooked attack surface. In particular, malicious agents can strategically manipulate their skill descriptions to bias routing decisions and increase their probability of being selected for task execution, thereby disrupting user tasks and degrading system reliability. To characterize this threat, we propose and formalize a new attack model, termed \emph{Skill Description Deception} (SDD) attack. We further design an LLM-enabled SDD attack framework that automatically generates deceptive skill descriptions, enabling systematic vulnerability assessment of IoA systems. Experimental results on nine representative domains show that the proposed attack can achieve up to 98% attack success rate, demonstrating the severity and generality of the attack. Our paper reveals a new security vulnerability in IoA and calls for secure and trustworthy semantic routing mechanisms for future IoA systems.

Jiayi He, Xiaofeng Luo, Jiawen Kang +3

School of Automation Guangdong University of Technology Guangzhou, China · College of Computing and Data Science Nanyang Technological University Singapore, Singapore · The State Key Laboratory of Public Big Data Guizhou University Guiyang, China +1

Adversarial Attacks AI Agent Security LLM Agent Routing

May 9, 2026cs.LG

AESOP: Adversarial Execution-path Selection to Overload Deep Learning Pipelines

Modern machine learning deployments increasingly compose specialized models into dynamic inference pipelines, where upstream components produce intermediate predictions that determine the workload and inputs of downstream components. The cost of processing an input is therefore not determined by any single model, but by two coupled factors: the per-inference cost of each invoked component and its workload volume. Because these pipelines run under hard real-time constraints, efficiency is a fundamental requirement for system availability. We show that this structure creates an efficiency-attack surface that existing methods targeting single models cannot exploit: on identical inputs and budgets, path-aware targeting inflates FLOPs by

2,407\times

while the strongest single-model baseline achieves

117\times

-- a

20\times

gap attributable entirely to where the attack is directed. We formalize this as the adversarial path-selection problem and present AESOP, a framework combining vulnerability-guided path ranking with adaptive loss weighting. We evaluate AESOP on five pipelines plus a production-realistic deployment variant with batching, bounded buffering, and confidence-threshold defenses. AESOP achieves up to

2,407\times

FLOPs and

419\times

latency inflation in white-box setting and 58

\times

FLOPs / 17

\times

latency in gray-box settings. Under system-level defenses, the attack is not neutralized but redirected: pipelines are forced to choose between throughput collapse (

0.578 \to 0.006

input/s) and

96.7\%

data loss to sustain throughput.

Tingxi Li, Mingfang Ji, Ravishka Shemal Rathnasuriya +3

The University of Texas at Dallas · Tianjin University

Efficient Neural Network Inference Adversarial Attacks

May 9, 2026cs.CV

Control Your View: High-Resolution Global Semantic Manipulation in Learned Image Compression

Learned image compression (LIC) integrates deep neural networks (DNNs) to map high-dimensional images into compact latent representations, reducing redundancy and achieving superior rate-distortion (RD) performance in benign settings. Unfortunately, due to inherent vulnerabilities in DNNs, LIC systems are susceptible to adversarial perturbations that lead to downstream deterioration, compression rate degradation, untargeted distortion, and both local semantic manipulation (LSM) and low-resolution (

3\times28\times28

) global semantic manipulation (GSM). However, high-resolution GSM remains unexplored due to its intractability. Notably, the existing project gradient descent (PGD) method achieves near-perfect white-box attacks for classification, segmentation, and other tasks, yet fails to generalize to high-resolution GSM. Our theoretical and empirical analyses reveal that well-performing GSM drives adversarial examples from the Identity Region to the Amplification Region through the Lazying-Oscillating-Refining stages. General

\ell_{\infty}

-bounded attacks fail on high-resolution GSM because their step-size schedules cannot accommodate both the Oscillating and Refining stages. Based on this, we propose the Periodic Geometric Decay schedule that enables

\ell_{\infty}

-bounded high-resolution GSM. To verify our approach, we integrate it with PGD, yielding a minimal variant, PGD

^{2}

-GSM. Extensive experiments on the Kodak

(3\times768\times512)

demonstrate that our PGD

^{2}

-GSM is the first to stably achieve high-resolution GSM, thereby exposing a novel threat to LIC systems. Code is available at https://github.com/chinaliangjiaming/PGD2-GSM.

Jiaming Liang, Chi-Man Pun, Weisi Lin +1

University of Macau Macau, China · Nanyang Technological University Singapore

Learned Image Compression Adversarial Attacks Gradient Descent Adversarial Examples

May 9, 2026cs.RO

ATAAT: Adaptive Threat-Aware Adversarial Tuning Framework against Backdoor Attacks on Vision-Language-Action Models

Addressing the escalating security vulnerabilities in Vision-Language-Action (VLA) models, this study investigates backdoor attacks targeting the visual pathway. We identify a core obstacle causing the failure of traditional attack paradigms: "Gradient Interference." This phenomenon represents an optimization failure triggered by conflicting strategies during end-to-end training. To resolve this, we propose an Adaptive Threat-Aware Adversarial Tuning (ATAAT) framework. Through its core "Threat-Method Adaptive Mapping" mechanism, ATAAT intelligently selects the optimal gradient decoupling strategy based on the adversary's capabilities. Extensive experiments demonstrate that ATAAT exhibits significant advantages, achieving a highly robust Targeted Attack Success Rate (TASR > 80%) while maintaining extreme stealthiness with merely a 5% poisoning rate. It efficiently handles complex semantic-level triggers and achieves implicit decoupled attacks in data poisoning scenarios for the first time. This work reveals a critical security vulnerability in VLAs and provides theoretical and methodological support for future defense architectures.

Kewei Chen, Yayu Long, Shuai Li +1

Chongqing Institute of Green and Intelligent Technology, Chinese Academy of Sciences · Chongqing School, University of Chinese Academy of Sciences · Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland

Adversarial Attacks Adversarial Attacks on VLA Models Vision-Language-Action Models Backdoor Attacks on VLMs Data Poisoning Attacks

May 7, 2026cs.LG

Hybrid Quantum-Classical GANs for the Generation of Adversarial Network Flows

Classical generative adversarial networks (GANs) have been applied to generate adversarial network traffic capable of attacking intrusion detection systems, but they suffer from shortcomings such as the need for large amounts of high-dimensional datasets, mode collapse, and high computational overhead. In this work, we propose a hybrid quantum-classical GAN (QC-GAN) framework where a variational quantum generator is used to generate synthetic network traffic flows mimicking malicious traffic using latent representations. Instead of sampling classical noise vectors, we encode the latent vector (the hidden features) as a quantum state, which is the basis for claiming more expressive latent representations and reducing computational overhead. A classical discriminator will be trained on real-world datasets (UNSW-NB15) and the proposed QC-GAN-generated fake network flows. In this configuration, the generator aims to minimize the discriminator's ability to distinguish real from fake traffic, while the discriminator aims to maximize its classification accuracy, in an iterative manner. In our attack model, we assume that the attacker is a state actor with access to limited quantum computing power, whereas the discriminator is chosen to be classical, as will likely be the case for most end users and organizations. We test the generated flows using classical intrusion detection system (IDS) models, such as a random forest classifier and a convolutional neural network-based classifier, for their ability to bypass the detection process. This work aims to highlight the possibilities of quantum machine learning as a means of generating advanced attack flows and stress testing classical IDS. Lastly, we further evaluate how hardware-based noise affects these attacks to offer a new perspective on IDS, highlighting the need for a quantum resilient defense system.

Prateek Paudel, Nitin Jha, Abhishek Parakh +1

Kennesaw State University, Marietta, GA, USA · University of Nebraska Omaha, Omaha, NE, USA

Adversarial Attacks Network Intrusion Detection Hybrid Quantum-Classical ML Generative Adversarial Networks

May 7, 2026cs.LG

Adversarial Graph Neural Network Benchmarks: Towards Practical and Fair Evaluation

Adversarial learning and the robustness of Graph Neural Networks (GNNs) are topics of widespread interest in the machine learning community, as documented by the number of adversarial attacks and defenses designed for these purposes. While a rigorous evaluation of these adversarial methods is necessary to understand the robustness of GNNs in real-world applications, we posit that many works in the literature do not share the same experimental settings, leading to ambiguous and potentially contradictory scientific conclusions. In this benchmark, we demonstrate the importance of adopting fair, robust, and standardized evaluation protocols in adversarial GNN research. We perform a comprehensive re-evaluation of seven widely used attacks and eight recent defenses under both poisoning and evasion scenarios, across six popular graph datasets. Our study spans over 453,000 experiments conducted within a unified framework. We observe substantial differences in adversarial attack performance when evaluated under a fair and robust procedure. Our findings reveal that previously overlooked factors, such as target node selection and the training process of the attacked model, have a profound impact on attack effectiveness, to the extent of completely distorting performance insights. These results underscore the urgent need for standardized evaluations in adversarial graph machine learning.

Tran Gia Bao Ngo, Zulfikar Alom, Federico Errica +2

Department of Computer Science, University of Manitoba · University of Toledo · NEC Laboratories Europe +2

Graph Neural Networks Adversarial Attacks Adversarial Robustness

May 5, 2026cs.CR

MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents

Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing safety alignment evaluates overt requests in isolation, leaving models blind to malicious end-states that emerge from sequenced compliance with innocuous-looking requests. We introduce MOSAIC-Bench (Malicious Objectives Sequenced As Innocuous Compliance), a benchmark of 199 three-stage attack chains paired with deterministic exploit oracles on deployed software substrates (10 web-application substrates, 31 CWE classes, 5 programming languages) that treats both exploit ground truth and downstream reviewer protocol as first-class evaluation axes. On this benchmark, nine production coding agents from Anthropic, OpenAI, Google, Moonshot, Zhipu, and Minimax compose innocuous tickets at 53-86% end-to-end ASR with only two refusals across all staged runs. In a matched direct-prompt experiment over four frontier Claude/Codex agents, vulnerable-output rates fall to 0-20.4%: Claude primarily refuses, while Codex primarily hardens rather than emitting the vulnerable implementation - ticket staging silences both defense modes simultaneously. Downstream, code reviewer agents approve 25.8% of these confirmed-vulnerable cumulative diffs as routine PRs, and a full-context implementation protocol closes only 50% of the staged/direct gap, ruling out context fragmentation as the sole explanation. As a deployable but non-adaptive mitigation, reframing the reviewer as an adversarial pentester reduces evasion across the evaluated reviewer subset; pentester framed evasion ranges from 3.0% to 17.6%, and an open-weight Gemma-4-E4B-it reviewer under this framing detects 88.4% of attacks on the dataset with a 4.6% false-positive rate measured on 608 real-world GitHub PRs.

Jonathan Steinberg, Oren Gal

Swarms & AI Lab (SAIL), University of Haifa

Language Model Safety Evaluation AI Coding Agents Adversarial Attacks AI Agent Security Benchmarks Automated Code Review AI Agent Safety Benchmarks

May 5, 2026cs.CV

TsallisPGD: Adaptive Gradient Weighting for Adversarial Attacks on Semantic Segmentation

Attacking semantic segmentation models is significantly harder than image classification models because an attacker must flip thousands of pixel predictions simultaneously. Standard pixel-wise cross-entropy (CE) is ill-suited to this setting: it tends to overemphasize already-misclassified pixels, which slows optimization and overstates model robustness. To address these issues, we introduce TsallisPGD, an adversarial attack built on the Tsallis cross-entropy, a generalization of CE parameterized by

q

, which adaptively reshapes the gradient landscape by controlling gradient concentration across pixels. By varying

q

, we steer the attack toward pixels at different confidence levels. We first show that no single fixed-

q

is universally optimal, as its effectiveness depends on the dataset, model architecture, and perturbation budget. Motivated by this, we propose a dynamic

q

-schedule that sweeps

q

during optimization. Extensive experiments on Cityscapes, Pascal VOC, and ADE20K show that TsallisPGD, using a single validation-selected schedule, achieves the best average attack rank across all evaluated settings and improves over CEPGD, SegPGD, CosPGD, JSPGD, and MaskedPGD in reducing accuracy and mIoU on both standard and robust models.

Alexander Matyasko, Xin Lou, Indriyati Atmosukarto +1

Singapore Institute of Technology, Singapore

Adversarial Attacks Adaptive Loss Weighting

May 3, 2026cs.CR

Repurposing and Evaluating the (In)Feasibility of Dataset Poisoning enabled Watermarking for Contrastive Learning

Contrastive learning (CL) reduces annotation cost via auto-derived supervisory signals. Since large-scale in-house CL datasets are infeasible, reliance on third-party or internet data is common. Recent studies show CL models are vulnerable to data-poisoning backdoor attacks, but their generalization and robustness are underexplored. We systematically evaluate existing data-poisoning backdoor attacks on CL, revealing limitations: poor dataset adaptability, low success rates, limited portability, and restrictive assumptions (e.g., downstream task knowledge). Interestingly, trigger samples exhibit distinguishable statistical divergence from clean samples, which inspires repurposing it as a watermark for dataset IP protection. Direct repurposing is challenging due to low success rates; we overcome this by statistical verification using a unified density metric. We further propose a multi-level watermarking scheme adapting to feature-level, soft-label, or hard-label outputs in CL. Experiments show some backdoor attacks can be repurposed as effective watermarks with trade-offs among fidelity, verifiability, and robustness. This work demonstrates weak backdoor effects become reliable signals for dataset IP protection in challenging CL settings.

Zhiyang Dai, Yansong Gao, Boyu Kuang +5

School of Cyber Science and Engineering, Nanjing University of Science and Technology, Nanjing 210094, China · University of Western Australia, Perth, Australia · College of Electronics and Information Engineering, Shenzhen University, Shenzhen, China +3

Contrastive Learning Dataset Watermarking Adversarial Attacks Robust Watermarking Data Poisoning Attacks

May 2, 2026cs.IR

Led to Mislead: Adversarial Content Injection for Attacks on Neural Ranking Models

Neural Ranking Models (NRMs) are central to modern information retrieval but remain highly vulnerable to adversarial manipulation. Existing attacks often rely on heuristics or surrogate models, limiting effectiveness and transferability. We propose CRAFT, a supervised framework for black-box adversarial rank attacks powered by large language models (LLMs). CRAFT operates in three stages: adversarial dataset generation via retrieval-augmented generation and self-refinement, supervised fine-tuning on curated adversarial examples, and preference-guided optimization to align generations with rank-promotion objectives. Extensive experiments on the MS MARCO passage dataset, TREC Deep Learning 2019, and TREC Deep Learning 2020 benchmarks show that CRAFT significantly outperforms state-of-the-art baselines, achieving higher promotion rates and rank boosts while preserving fluency and semantic fidelity. Moreover, CRAFT transfers effectively across diverse ranking architectures, including cross-encoder, embedding-based, and LLM-based rankers, underscoring vulnerabilities in real-world retrieval systems. This work provides a principled framework for studying adversarial threats in NRMs, underscores the risks of generative AI in rank manipulation, and provides a foundation for developing more robust retrieval systems. To support reproducibility, we publicly release our source code, trained models, and prompt templates.

Amin Bigdeli, Amir Khosrojerdi, Radin Hamidi Rad +3

University of Waterloo, Canada · University of Toronto, Canada · Mila – Quebec AI Institute, Canada +1

Learning to Rank Adversarial Attacks Black-Box Adversarial Attacks Adversarial Text Attacks

May 2, 2026cs.CV

Asymmetric Invertible Threat: Learning Reversible Privacy Defense for Face Recognition

Face Recognition systems are widely deployed in real-world applications, but they also raise privacy concerns due to unauthorized collection and misuse of facial data. Existing adversarial privacy protection methods rely on input-space perturbations to obfuscate identity information, yet their protection can degrade when adversaries learn restoration or purification mappings that partially invert the transformation. We study this setting as an asymmetric adversarial attack, in which reverse manipulation becomes feasible because existing defense paradigms do not control reversibility. To address this problem, we propose Asymmetric Reversible Face Protection (ARFP), a restoration-aware extension of personalized face cloaking that integrates privacy protection, keyed recovery, and tamper indication in a single framework. ARFP consists of three components: Key-Conditioned Manifold Binding, which ties the protection transformation to a user-provided key; Adversarial Restoration-Aware Training, which introduces a surrogate restoration adversary during training to improve robustness against evaluated inverse purification attacks; and Authorized Reversible Restoration, which supports recovery with the correct key while providing nonce-based tamper indication. Extensive experiments under the threat models considered in this work show that ARFP improves resistance to the evaluated restoration attacks while preserving authorized recovery utility. These results provide empirical evidence of key-sensitive recovery behavior and tamper awareness in the tested settings.

Jiabei Zhang, Ziyuan Yang, Andrew Beng Jin Teoh +1

School of Cyber Science and Engineering, Sichuan University · Lee Kong Chian School of Medicine, Nanyang Technological University · School of Electrical and Electronic Engineering, Yonsei University

Adversarial Training Adversarial Attacks Adversarial Robustness Privacy-Preserving ML Face Recognition

May 1, 2026cs.CR

When Embedding-Based Defenses Fail: Rethinking Safety in LLM-Based Multi-Agent Systems

Large language model (LLM)-powered multi-agent systems (MAS) enable agents to communicate and share information, achieving strong performance on complex tasks. However, this communication also creates an attack surface where malicious agents can propagate misinformation and manipulate group decisions, undermining MAS safety. Existing embedding-based defenses aim to detect and prune suspicious agents, but their effectiveness depends on a clear separation between the text embeddings of malicious and benign messages. Attackers can circumvent such defenses by crafting messages whose embeddings lie close to benign ones. We analyze this failure mode theoretically and validate it empirically with three attacks, Slow Drift, Benign Wrapper, and Chaos Seeding. Our analysis further reveals a fundamental limitation of embedding-based defenses: because they rely solely on the text embeddings, they ignore token-level confidence signals such as logits, which can remain informative when embeddings are not distinguishable under attack. We propose using confidence scores to prune or down-weight messages during MAS communication. Experiments show improved robustness across models, datasets, and communication topologies. Moreover, we find that the effectiveness of confidence signals decays over communication rounds, highlighting the importance of early intervention. This insights can inform and inspire future work on MAS attacks and defenses.

Lingxi Zhang, Guangtao Zheng, Hanjie Chen

1Rice University · University of Virginia

Adversarial Attacks Language Model Robustness Multi-Agent System Security Multi-Agent LLMs

May 1, 2026cs.LG

Almost for Free: Crafting Adversarial Examples with Convolutional Image Filters

Adversarial examples in machine learning are typically generated using gradients, obtained either directly through access to the model or approximated via queries to it. In this paper, we propose a much simpler approach to craft adversarial examples, drawing inspiration from insights of explainable machine learning. In particular, we design \emph{adversarial image filters} that are based on classic edge detection algorithms but optimized to deceive learning models. The resulting untargeted attacks are transferable and require only a single pass over the input. Empirically, we find that 3x3 filters already enable success rates between 30% and 80% on different neural networks. Compared to related approaches using generative models for crafting adversarial examples, we reduce the number of parameters by five orders of magnitude, resulting in a very efficient attack. When investigating the parameters of the learned filters, we observe interesting properties such as a high transferability between models and structures common to classic image filters. Our results provide further insights into the vulnerability of neural networks and their fragility to malicious noise.

Alexander Warnecke, Konrad Rieck

1BIFOLD & TU Berlin

Adversarial Attacks Adversarial Examples Adversarial Perturbations Transfer-Based Adversarial Attacks

May 1, 2026cs.LG

Adaptive Equilibrium: Dynamic Weighting Framework for Generalized Interruption of DeepFake Models

The advancement of generalized deepfake disruption is constrained by the interruption imbalance, a fundamental bottleneck inherent to the generation of universal perturbations. We reveal that conventional static gradient normalization fundamentally struggles to resolve architectural conflicts, causing the optimization to bias towards susceptible models while neglecting resistant ones. We argue that achieving high and uniform effectiveness requires resolving this imbalance by reaching an adaptive equilibrium. We propose the Adaptive Equilibrium Framework (AEF), which employs a dynamic weighting mechanism that utilizes real-time loss feedback to adaptively assign greater interruption weights to the most resistant models. This approach shifts the optimization from an average-case problem to finding a dynamic balance, driving the perturbation to a uniformly effective equilibrium state. Comprehensive experiments validate that AEF achieves a more balanced interruption performance, maintaining a consistent interruption success rate across the evaluated diverse architectures.

Hongrui Zheng, Liejun Wang, Zhiqing Guo

School of Computer Science and Technology, Xinjiang University, Urumqi, China · Xinjiang Multimodal Intelligent Processing and Information Security Engineering Technology Research Center, Urumqi, China · Silk Road Multilingual Cognitive Computing International Cooperation Joint Laboratory, Xinjiang University, Urumqi, China

Adversarial Attacks Adaptive Loss Weighting Adversarial Perturbations Adversarial Transferability