Adversarial Attacks on VLMs

VLM: Vision-Language Model

Follow this topic Ask about this topic

Momentum

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

Jul 13Week of Sep 28

Latest papers 106

All topics

Detecting Adversarial Images through Response Profiles of Vision-Language Models
Oct 7, 2026Arash Vashagh, Roozbeh Razavi-FarAdversarial Example Detection VLM Robustness
Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Canada
Understanding and Mitigating Token-Pruning-Induced Vulnerabilities in VLMs
Oct 7, 2026Shuailong Wang, Xinyu Lyu, Shengming Yuan +3Visual Token Pruning VLM Robustness
University of Electronic Science and Technology of China, Chengdu, China · Southwestern University of Finance and Economics, Chengdu, China · Tongji University, Shanghai, China +1
Adversarial Images Hijack Web Agents from Visual Grounding to Browser Execution
Oct 7, 2026Wanjing Han, Levi Taiji Li, Mu Zhang +2AI Agent Security Tool-Using Vision-Language Agents
University of Utah
Visual Memory Attacks Can Persist Through The KV Cache
Oct 6, 2026David Dobre, Leo Schwinn, Gauthier Gidel +3Adversarial Attacks on VLMs Backdoor Attacks on VLMs
ServiceNow AI Research · Université de Montréal · Mila +2
Transferable Spatial Temporal Coherence Adversarial Attack on Black-Box Vision Language Models for Autonomous Driving
Oct 6, 2026Heyam Bin Jahlan Areej Alhothali Abeer AlhothaliAdversarial Attacks on VLMs VLMs for Autonomous Driving
Walking the Embedding Space: Datastore Extraction from Multimodal RAG
Oct 1, 2026Maria Carmen Jica, Ali Satvaty, Suzan Verberne +1Multimodal RAG Adversarial Attacks on VLMs
University of Groningen Groningen, The Netherlands
Typographic Attack Against VLM-based AI-generated Image Detection
Sep 30, 2026Eunmin Lee, Jungwoo Kim, Jong-Seok LeeVLM Evaluation VLM Robustness
School of Integrated Technology, Yonsei University
Feature-Aware Token Attack for Compression-Triggered Stealthy Failures in Large Vision-Language Models
Sep 30, 2026Shilinlu Yan, Bowen Chen, Yuechen Zhang +3VLM Robustness Adversarial Attacks on VLMs
Beijing University of Posts and Telecommunications · Jiangnan University · Nanyang Technological University +1
It Takes Little to Rewrite Perception: Targeted Semantic Substitution in Vision-Language Models at $ε\leq 4/255$
Sep 29, 2026Binchi Zhang, Atrisha Sarkar, Apurva NarayanVLM Robustness Adversarial Attacks on VLMs
University of Western Ontario
Still There, No Longer Seen: Exposing Compression-Induced Risk in Large Vision-Language Models
Sep 28, 2026Qiankun Li, Yuechen Zhang, Bowen Chen +4VLM Robustness Adversarial Attacks on VLMs
Nanyang Technological University · Beijing University of Posts and Telecommunications
One Attack to Fool Them All: Highly Transferable Black-Box Adversarial Attacks on Frontier MLLMs
Sep 27, 2026Sen Nie, Jie Zhang, Zhongqi Wang +2Adversarial Attacks on VLMs Adversarial Attacks on LLMs
State Key Laboratory of AI Safety, Institute of Computing Technology, Chinese Academy of Sciences, and the University of Chinese Academy of Sciences.
Hiding in Plain Sight: A Diffusion-based Mitigation of Geolocation Privacy Leakage in Vision-Language Models
Sep 18, 2026Yining Wang, Xi Li, Mi Zhang +4Privacy Protection in VLMs Adversarial Attacks on VLMs
Fudan University · East China University of Science and Technology · Shanghai University of Electric Power
Do Input-Level Defenses Transfer to Observation-Level Attacks on VideoLLMs?
Sep 8, 2026Bangshuo Zhu, Wei Song, Yuxin Cao +4VLM Robustness Adversarial Attacks on VLMs
School of Computer Science and Engineering, University of New South Wales, New South Wales 2052, Australia · School of Information and Communication Technology, Griffith University, Queensland 4111, Australia · School of Computing, National University of Singapore, Singapore 117417, Singapore +2
MM-IFEval-Pro: A Multilingual and Attack-Resistant Benchmark for Instruction-Following in Vision-Language Models
Sep 4, 2026Changming Xiao, Zhenliang Ni, Jinhui He +2VLM Robustness Adversarial Attacks on VLMs
Huawei Technologies Ltd. · Beijing, China · Shenzhen, China +1
Jailbreaking Text-to-Image Models Through Cracks: Navigating Heterogeneous Safety Filters via Multi-Agent Debate
Sep 1, 2026Kaiyan Wen, Shijie Zhang, Lu Yu +1Adversarial Attacks on VLMs Multi-Agent Debate
College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China · Shenzhen MSU-BIT University, Shenzhen, China · City University of Hong Kong, Hong Kong, China
Forbid Your Attention: Fooling Multimodal Large Language Models by Selectively Removing Intrinsic Focus in Spectral Domain
Sep 1, 2026Daizong Liu, Junhao Dong, Zhiyuan Ma +6Adversarial Attacks on VLMs Adversarial Attacks
Institute for Math & AI, Wuhan University, Wuhan, 430072, China · College of Computing and Data Science, Nanyang Technological University, Singapore · School of Computer Science and Technology, Huazhong University of Science and Technology, Wuhan, 430074, China +3
Fully Unleashing the Multimodal Attacker: Meta-Adaptive Jailbreaking of Vision-Language Models
Aug 27, 2026Benlei Cui, Shen Pang, Yuke Wang +7VLM Robustness Adversarial Attacks on VLMs
1Yuvion Team, Alibaba Group · Laboratory for Statistical Monitoring and Intelligent Governance of Common Prosperity, School of Statistics and Data Science, Zhejiang Gongshang University
QuISE: Defense against Typographic Attacks on VLMs via Query-Irrelevant Semantic Editing
Aug 13, 2026Shubin Lu, Jiaqi Yin, Yihao HuangVLM Robustness Adversarial Attacks on VLMs
School of Software, Northwestern Polytechnical University, Xi’an, China · Software Engineering Institute, East China Normal University, Shanghai, China
Once Poisoned, Arbitrarily Controlled: A Programmable Backdoor in VLMs
Aug 11, 2026Tao Lin, Gaojie Jin, Zongxin Liu +2Adversarial Attacks on VLMs Vision-Language Models
Key Laboratory of System Software (Chinese Academy of Sciences), Beijing, China · Institute of Software, Chinese Academy of Sciences, Beijing, China · University of Chinese Academy of Sciences, Beijing, China +2
SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning
Aug 11, 2026Caoyuan Ma, Wenpu Liu, Weichu Xie +12VLM Robustness Adversarial Attacks on VLMs
The University of Tokyo · Peking University · Wuhan University +4
Adversarial Attacks on Deep OCR Systems
Aug 7, 2026Wenbo Sun, Hongzong LI, Yanyun Wang +5Adversarial Attacks on VLMs Adversarial Attacks
Nanjing University of Aeronautics and Astronautics · Northwestern Polytechnical University · The Chinese University of Hong Kong +4
Vision-Language Model Confidence Is Not a Property of the Answer
Aug 6, 2026Reza Khanmohammadi, Erfan Miahi, Ivan Brugere +4VLM Robustness Adversarial Attacks on VLMs
Michigan State University · JPMorgan AI Research · Henry Ford Health
Hijacking Robots with a Piece of Paper: A Systematic Study of Physical Prompt Injection in VLM-Controlled Robots
Aug 6, 2026S. M . Bhagya P. Samarakoon, M. A. Viraj J. Muthugala, W. K. R. Sachinthana +1VLM Robustness Adversarial Attacks on VLMs
Engineering Product Development Pillar · Singapore University of Technology and Design · Somapah Rd, Singapore 487372
MissClick: Execution-Aware Adversarial Attacks on Coordinate Generation in GUI Grounding Models
Aug 4, 2026Yu Ran, Wentao ZhaoAdversarial Attacks on VLMs Adversarial Attacks
National University of Defense Technology
Two Sides of the Same Coin: Co-Evolving Search for Cross-Task Attacks on Vision-Language Models
Aug 3, 2026Xuanhui Lin, Junhao Dong, Mingrong Gong +3VLM Robustness Adversarial Attacks on VLMs
College of Computing and Data Science, Nanyang Technological University, Singapore
Fighting Fire with Fire: On the Feasibility of Protecting Exercises Against AI Cheating
Aug 2, 2026Tobias Braun, Jonas Grebe, Louis Rethfeld +1Adversarial Attacks on VLMs AI in Education
TU Darmstadt & hessian.AI, Germany
ReACT-CLIP: Response-Aware Test-Time Defense for Vision--Language Models
Aug 2, 2026Hashmat Shadab Malik, Toluwani Aremu, Samuele Poppi +2VLM Robustness Adversarial Attacks on VLMs
Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), UAE · Khalifa University, UAE · University of Western Australia, Australia +1
Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks
Aug 2, 2026Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2VLM Robustness Adversarial Attacks on VLMs
QR-Structured Thermal Triggers for Targeted Semantic Attacks on Infrared Vision-Language Models
Jul 31, 2026Xiang Chen, Yingying Zhao, Chao Li +7VLM Robustness Adversarial Attacks on VLMs
A Cross-Architecture Audit of Direction-Based Inference-Time Defences in Vision-Language Models
Jul 30, 2026Xiangyu Yin, Tora Bodin, Rohan Menon +1VLM Robustness Adversarial Attacks on VLMs
Chalmers University of Technology, Gothenburg, Sweden · Carl von Ossietzky University of Oldenburg, Oldenburg, Germany

Oct 7, 2026, cs.CVJ/K move · Enter open · S save

Detecting Adversarial Images through Response Profiles of Vision-Language Models

Arash Vashagh, Roozbeh Razavi-Far

Trustworthy and Secure AI (TSAI) Lab, Faculty of Computer Science, University of New Brunswick, Canada

Adversarial Example Detection VLM Robustness Adversarial Attacks on VLMs

Open paper AskPDF arXiv

Adversarial perturbations can alter the predictions of frozen vision-language models (VLMs) while leaving their confidence and image--text similarity patterns seemingly plausible. We investigate whether we can identify adversarial inputs based on the broader way an image interacts with a collection of general semantic prompts. Our detector summarizes these responses using category-level statistics, relationships among prompts, deviations from clean reference distributions, and stability under weak image transformations, producing a compact response profile that is classified by a lightweight model while the VLM remains fixed. We evaluate the approach on multiple public image datasets, several CLIP-style visual backbones, and a range of gradient-based, optimization-based, automated, and spatial attacks. The detector achieves strong discrimination in attack-specific settings and retains substantial performance when evaluated on attacks not seen during training. Under a controlled detector-specific protocol, the response-profile representation outperforms the evaluated embedding-geometry baselines. Additional analyses show that the feature groups provide complementary information and that the method remains effective under variations in the prompt configuration. We also examine inference cost and performance against detector-aware adaptive attacks. Overall, the results indicate that response patterns across semantic prompts provide a useful complementary signal for adversarial image detection in frozen VLMs.

Momentum

Related topics

Latest papers 106