Adversarial Attacks on VLMs

VLM: Vision-Language Model

Ask about this topic

Overview

This field studies how image perturbations, embedded text, physical patches, poisoned training data, and multi-turn prompts can make models misread scenes, follow malicious instructions, leak information, or fail in agent tasks. Approaches include gradient-based and transferable attacks, typographic and visual prompt injection, jailbreak red-teaming, and backdoors, evaluated across tasks such as visual question answering, captioning, document understanding, video, and robotics. Defenses range from adversarial training and robust encoders to test-time transformations, token or attention interventions, prompt screening, and response monitoring. A central challenge is improving safety and robustness without sacrificing clean accuracy, utility, or latency, while accounting for uneven transfer across models, modalities, languages, and deployment settings.

Latest papers

CardsList

183 papers23 papers in the last four weeks, up 77% on the four weeks before. 0.1% of all new papers.

  1. Cross-Modal Attention Analysis and Optimization in Vision-Language Models: A Study on Visual Reliability

    Apr 19, 2026Lijie ZhouCross-Modal LearningVLM Robustness

    School of Computer Science University of Nottingham Ningbo China Ningbo, China

  2. Penny Wise, Pixel Foolish: Bypassing Price Constraints in Multimodal Agents via Visual Adversarial Perturbations

    Apr 15, 2026Jiachen Qian, Zhaolu KangVLM RobustnessAdversarial Attacks on VLMs

    City University of Hong Kong · Peking University

  3. Challenging Vision-Language Models with Physically Deployable Multimodal Semantic Lighting Attacks

    Apr 14, 2026Yingying Zhao, Chengyin Hu, Qike Zhang +7Adversarial Attacks on VLMsVLM Robustness

  4. Every Picture Tells a Dangerous Story: Memory-Augmented Multi-Agent Jailbreak Attacks on VLMs

    Apr 14, 2026Jianhao Chen, Shiqin Wang, Haoyang Chen +4Adversarial Attacks on VLMsVLM Evaluation

    School of Computer Science, Wuhan University, Wuhan, China · Zhongguancun Academy, Beijing, China · Tianjin University, Tianjin, China +1

  5. HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models

    Apr 14, 2026Han Liu, Jiaqi Li, Zhi Xu +5Adversarial Attacks on VLMsBlack-Box Adversarial Attacks

    Dalian University of Technology, Dalian, China · The Pennsylvania State University, Pennsylvania, USA · Shenzhen University, Shenzhen, China

  6. Reading Between the Pixels: Linking Text-Image Embedding Alignment to Typographic Attack Success on Vision-Language Models

    Apr 14, 2026Ravikumar Balakrishnan, Sanket Mendapara, Ankit GargAdversarial Attacks on VLMsVLM Robustness

    Cisco Systems

  7. Seeing No Evil: Blinding Large Vision-Language Models to Safety Instructions via Adversarial Attention Hijacking

    Apr 11, 2026Jingru Li, Wei Ren, Tianqing ZhuJailbreak AttacksAdversarial Attacks on VLMs

    China University of Geosciences, Wuhan · City University of Macau

  8. Mosaic: Multimodal Jailbreak against Closed-Source VLMs via Multi-View Ensemble Optimization

    Apr 10, 2026Yuqin Lan, Gen Li, Yuanze Hu +6Adversarial Attacks on VLMsTransfer-Based Adversarial Attacks

    Beihang University Beijing, China · Huazhong University of Science and Technology Wuhan, China

  9. Leave My Images Alone: Preventing Multi-Modal Large Language Models from Analyzing Images via Visual Prompt Injection

    Apr 10, 2026Zedian Shao, Hongbin Liu, Yuepeng Hu +1Privacy Protection in VLMsAdversarial Attacks on VLMs

    Georgia Institute of Technology · Duke University

  10. Preference Redirection via Attention Concentration: An Attack on Computer Use Agents

    Apr 9, 2026Dominik Seip, Matthias HeinAdversarial AttacksAdversarial Attacks on VLMs

    Tübingen AI Center, University of Tübingen

  11. Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation

    Apr 8, 2026Zhiheng Li, Zongyang Ma, Yuntong Pan +8Multimodal Content ModerationAdversarial Attacks on VLMs

    State Key Laboratory of Multimodal Artificial Intelligence Systems, CASIA · School of Artificial Intelligence, University of Chinese Academy of Sciences · Beijing Key Laboratory of Super Intelligent Security of Multi-Modal Information +4

  12. VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts

    Apr 7, 2026Peigui Qi, Kunsheng Tang, Yanpu Yu +7VLM SafetyVLM Robustness

    University of Science and Technology of China · Ant Group · University of Washington

  13. Reading Between the Pixels: An Inscriptive Jailbreak Attack on Text-to-Image Models

    Apr 7, 2026Zonghao Ying, Haowen Dai, Lianyu Hu +5Black-Box Adversarial AttacksSafe T2I Generation

    Beihang University Beijing, China · University of Nottingham Ningbo China Ningbo, China · Nanyang Technological University Singapore +2

  14. Harnessing Hyperbolic Geometry for Harmful Prompt Detection and Sanitization

    Apr 7, 2026Igor Maljkovic, Maria Rosaria Briglia, Iacopo Masi +2VLM RobustnessAdversarial Attacks on VLMs

    University of Genoa, Italy · Sapienza University of Rome, Italy · University of Cagliari, Italy

  15. Adjustable Text-Guided Backdoor Attacks with Natural-Word Triggers on Multimodal Pretrained Models

    Apr 7, 2026Yiyang Zhang, Chaojian Yu, Ziming Hong +4Adversarial Attacks on VLMsBackdoor Attacks on VLMs

    National Anti-Counterfeit Engineering Research Center, Huazhong University of Science and Technology · School of Electronic Information and Communications, Huazhong University of Science and Technology · Sydney AI Centre, The University of Sydney

  16. Benchmarking Vision-Language Models under Contradictory Virtual Content Attacks in Augmented Reality

    Apr 7, 2026Yanming Xiu, Zhengyuan Jiang, Neil Zhenqiang Gong +1Augmented RealityVLM Robustness

    Duke University

  17. Revealing Physical-World Semantic Vulnerabilities: Universal Adversarial Patch for Infrared Vision-Language Models

    Apr 3, 2026Chengyin Hu, Yuxian Dong, Yikun Guo +8Adversarial Attacks on VLMsVLM Robustness

    China University of Petroleum-Beijing at Karamay, No. 355 Anding Road, Karamay 834000, Xinjiang, China. · the Defense Innovation Institute, Chinese Academy of Military Science, Beijing, China. · Shenzhen University, Shenzhen, China. +1

  18. Low-Effort Jailbreak Attacks Against Text-to-Image Safety Filters

    Apr 2, 2026Ahmed B Mustafa, Zihan Ye, Yang Lu +2Adversarial Attacks on VLMsSafe T2I Generation

    School of Computer Science, University of Nottingham, Wollaton Road, NG8 1BB · Department of Intelligent Science, Xi’an Jiaotong-Liverpool University, China, 215123 · School of Informatics, Xiamen University, Xiamen, 361005, China

  19. PDA: Text-Augmented Defense Framework for Robust Vision-Language Models against Adversarial Image Attacks

    Apr 1, 2026Jingning Xu, Haochen Luo, Chen LiuVLM RobustnessVision-Language Models

    Department of Computer Science City University of Hong Kong

  20. CASA: Classification Augmented with Safety Attention for Robust Multimodal Alignment

    Mar 31, 2026Anurag Kumar, Raghuveer Peri, Jon Burnsky +4MLLM SafetyLLM Safety Alignment

    The Ohio State University · AWS

  21. Covert Visual Prompt Injection against Commercial Multimodal Large Language Models

    Mar 31, 2026Meiwen Ding, Song Xia, Chenqi Kong +1Adversarial Attacks on VLMsPrompt Injection Attacks

    Rapid-Rich Object Search Lab, School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore.

  22. XSPA: Crafting Imperceptible X-Shaped Sparse Adversarial Perturbations for Transferable Attacks on VLMs

    Mar 30, 2026Chengyin Hu, Jiaju Han, Xuemeng Sun +6Adversarial Attacks on VLMsVLM Robustness

    China University of Petroleum-Beijing at Karamay · Shenzhen Research Institute of Big Data · Shanghai Jiao Tong University +2

  23. When Surfaces Lie: Exploiting Wrinkle-Induced Attention Shift to Attack Vision-Language Models

    Mar 29, 2026Chengyin Hu, Xuemeng Sun, Jiaju Han +5Adversarial Attacks on VLMsAdversarial Attacks

  24. Hidden Ads: Behavior Triggered Semantic Backdoors for Advertisement Injection in Vision Language Models

    Mar 29, 2026Duanyi Yao, Changyue Li, Zhicong Huang +2Adversarial Attacks on VLMsBackdoor Attacks

    Hong Kong University of Science and Technology · The Chinese University of Hong Kong, Shenzhen, China · Ant Group +1

  25. Shape and Substance: Dual-Layer Side-Channel Attacks on Local Vision-Language Models

    Mar 26, 2026Eyal Hadad, Mordechai GuriPrivacy Protection in VLMsAdversarial Attacks on VLMs

    Ben-Gurion University of the Negev, Israel Faculty of Computer and Information Science

  26. TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration

    Mar 24, 2026Chunxiao Li, Lijun Li, Jing ShaoCultural Safety Evaluation of VLMsAutomated Red Teaming

    Shanghai Artificial Intelligence Laboratory

  27. Principled Steering via Null-space Projection for Jailbreak Defense in Vision-Language Models

    Mar 23, 2026Xingyu Zhu, Beier Zhu, Shuo Wang +4VLM RobustnessActivation Steering

    MoE Key Lab of BIPC, University of Science and Technology of China · National University of Singapore · Nanyang Technological University

  28. Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models

    Mar 23, 2026Rui Yang Tan, Yujia Hu, Roy Ka-Wei LeeMLLM SafetyAdversarial Attacks on VLMs

    Singapore University of Technology and Design. · University of British Colombia.

  29. JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization

    Mar 22, 2026Haolun Zheng, Yu He, Tailun Chen +6Adversarial Attacks on VLMsBlack-Box Adversarial Attacks

    The State Key Laboratory of Blockchain and Data Security, Zhejiang University · Hangzhou HighTech Zone (Binjiang) Blockchain and Data Security Research Institute, China · Alibaba Group

  30. When Minor Edits Matter: LLM-Driven Prompt Attack for Medical VLM Robustness in Ultrasound

    Mar 22, 2026Yasamin Medghalchi, Milad Yazdani, Amirhossein Dabiriaghdam +7VLM RobustnessAdversarial Attacks on VLMs

    University of British Columbia, Vancouver, Canada