VLM Safety

VLM: Vision-Language Model

Ask about this topic

Latest papers

CardsList

29 papers5 papers in the last four weeks, up 67% on the four weeks before. 0.0% of all new papers.

  1. When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models

    Oct 15, 2026Wei Cai, Jian Zhao, Yuchen Yuan +1Multimodal Multi-Turn Safety AlignmentVLM Safety

    Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China. · Peking University. · School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, P. R. China.

  2. Reading, Not Manipulating: Leveraging Router Logits for Multimodal Safety in MoE Vision-Language Models

    Oct 6, 2026Ziyuan Yang, Wenxuan Ding, Shangbin Feng +1Vision-Language ModelsSafety Filtering

    University of Washington · New York University

  3. From Local Evidence to Safety Verdicts: Causal Tracing in Vision-Language Models

    Oct 5, 2026Faezeh Dehghan Tarzjani, Mevan Wijewardena, Alexander Romanus +1Cultural Safety Evaluation of VLMsVLM Safety

    Department of Electrical and Computer Engineering University of Southern California, Los Angeles, CA, USA · Department of Computer Science University of Southern California, Los Angeles, CA, USA

  4. What the Guard Misses, the Robot Executes: Implied Harm in VLA Instructions

    Oct 5, 2026Sripad Karne, Arjun BalajiLanguage Model Safety EvaluationRobot Safety

    Columbia University

  5. Visual Grounding Safety in Vision-Language Models

    Oct 5, 2026Erfan Shayegani, Kundan Krishna, Yue Dong +3VLM EvaluationVLM Safety Alignment

    University of California, Riverside · Work done during internship at Apple. · Apple

  6. Can Vision-Language Models Stay Helpful When Facing Implicit Risks? Intent-Privilege OPSD for Efficient Safety-Helpfulness Alignment

    Sep 29, 2026Haotian Deng, Wenbin Xing, Gang Xu +5VLM RobustnessVision-Language Models

    Southern University of Science and Technology · Sun Yat-sen University · Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) +5

  7. SafeRI: Recognition and Intervention for Token-Level Safety Intervention in Large Vision Language Models

    Sep 3, 2026Caoyuan Ma, Tian Gu, Wenpu Liu +11Vision-Language ModelsVLM Safety Alignment

    The University of Tokyo · Wuhan University · Shanghai AI Laboratory +4

  8. Do VLMs Share Safety Neurons Across Modalities?

    Aug 31, 2026Jiaxuan Li, Jiahao Zhang, Duc Minh Vo +3VLM EvaluationVLM Interpretability

    SB Intuitions Corp., Tokyo, Japan

  9. EviSafe: Evidence-Grounded Safety Evaluation for Vision-Language Models

    Aug 24, 2026Xuetong Li, Gaofeng LiuCultural Safety Evaluation of VLMsVLM Safety

    School of Mathematical Sciences, MOE Key Lab of Scientific and Engineering Computing, Shanghai Center for Applied Mathematics, Shanghai Jiao Tong University · Department of Automation, Shanghai Jiao Tong University

  10. SafeCap: Improving LVLM Safety with Image Captioning Reinforcement Learning

    Aug 11, 2026Caoyuan Ma, Wenpu Liu, Weichu Xie +12VLM RobustnessAdversarial Attacks on VLMs

    The University of Tokyo · Peking University · Wuhan University +4

  11. Decoy Images Amplify Caption-Mediated Defenses Against Encoded Jailbreaks

    Aug 2, 2026Haoyu Zhang, Xiangchen Guan, Shibo Zheng +2VLM RobustnessAdversarial Attacks on VLMs

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

    Jul 29, 2026Haoyu Zhang, Zhuoxi Wang, Shibo Zheng +7VLM RobustnessAdversarial Attacks on VLMs

    Northeastern University

  13. MLingualFC: Evaluating Jailbreak Vulnerabilities in Multilingual Vision-Language Models

    Jun 5, 2026Rishabh Makwana, Mamta, Deeksha Varshney +1VLM EvaluationVLM Robustness

    Dwarkadas Jivanlal Sanghvi College of Engineering, Mumbai, India · King’s College London, London, UK · Indian Institute of Technology Jodhpur, Jodhpur, India

  14. Jailbreaking Vision-Language Models Through the Visual Modality

    May 1, 2026Aharon Azulay, Jan Dubiński, Zhuoyun Li +2Adversarial Attacks on VLMsVision-Language Models

    Independent · NASK National Research Institute, Warsaw, Poland · Warsaw University of Technology, Warsaw, Poland +3

  15. Prompt-Induced Score Variance in Zero-Shot Binary Vision-Language Safety Classification

    May 1, 2026Charles Weng, Dingwen Li, Alexander MartinVLM EvaluationConfidence Estimation for VLMs

    Johns Hopkins University · Independent

  16. One Perturbation, Two Failure Modes: Probing VLM Safety via Embedding-Guided Typographic Perturbations

    Apr 28, 2026Ravikumar Balakrishnan, Sanket MendaparaVLM EvaluationVLM Robustness

    Cisco Systems

  17. RedVLA: Physical Red Teaming for Vision-Language-Action Models

    Apr 24, 2026Yuhao Zhang, Borong Zhang, Jiaming Fan +4RoboticsAdversarial Attacks on VLA Models

    Institute for AI, Peking University · State Key Laboratory of General Artificial Intelligence, Peking University

  18. 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

  19. 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

  20. Diagnosing and Repairing Unsafe Channels in Vision-Language Models via Causal Discovery and Dual-Modal Safety Subspace Projection

    Mar 28, 2026Jinhu Fu, Yihang Lou, Qingyi Si +3VLM SafetyVision-Language Models

    Beijing University of Posts and Telecommunications · Huawei Technologies Ltd. · Peking University +1

  21. Understanding and Defending VLM Jailbreaks via Jailbreak-Related Representation Shift

    Mar 18, 2026Zhihua Wei, Qiang Li, Jian Ruan +4VLM SafetyAdversarial Attacks on VLMs

    School of Computer Science and Technology, Tongji University · Shanghai Artificial Intelligence Laboratory

  22. Directional Embedding Smoothing for Robust Vision Language Models

    Mar 16, 2026Ye Wang, Jing Liu, Toshiaki Koike-AkinoVLM SafetyVLM Robustness

    Mitsubishi Electric Research Laboratories, Cambridge, MA 02139, USA

  23. Two Birds, One Projection: Harmonizing Safety and Utility in LVLMs via Inference-time Feature Projection

    Mar 16, 2026Yewon Han, Yumin Seol, EunGyung Kong +2VLM SafetyVLM Robustness

    Graduate School of Data Science, Seoul National University · Mobilint

  24. Safety-Potential Pruning for Enhancing Safety Prompts Against VLM Jailbreaking Without Retraining

    Mar 15, 2026Chongxin Li, Hanzhang Wang, Lian DuanVLM SafetyVLM Robustness

    School of Computer Engineering and Science, Shanghai University

  25. Visual Self-Fulfilling Alignment: Shaping Safety-Oriented Personas via Threat-Related Images

    Mar 9, 2026Qishun Yang, Shu Yang, Lijie Hu +1VLM Safety AlignmentVLM Safety

    King Abdullah University of Science and Technology · Provable Responsible AI and Data Analytics Lab · China University of Petroleum-Beijing at Karamay +1

  26. Models as Lego Builders: Assembling Malice from Benign Blocks via Semantic Blueprints

    Mar 8, 2026Chenxi Li, Xianggan Liu, Dake Shen +9Adversarial Attacks on VLMsVLM Safety

    DAIL Tech · NLP & KG Lab, Huazhong University of Science and Technology

  27. SaFeR-ToolKit: Structured Reasoning via Virtual Tool Calling for Multimodal Safety

    Mar 3, 2026Zixuan Xu, Tiancheng He, Huahui Yi +7Cultural Safety Evaluation of VLMsVLM Safety

    Huazhong University of Science and Technology · Beijing University of Posts and Telecommunications · West China Hospital, Sichuan University +1

  28. GuardAlign: Test-time Safety Alignment in Multimodal Large Language Models

    Feb 27, 2026Xingyu Zhu, Beier Zhu, Junfeng Fang +4VLM Safety AlignmentVLM Safety

    MoE Key Lab of BIPC, University of Science and Technology of China · Nanyang Technological University · National University of Singapore +1

  29. VISOR: Visual Input-based Steering for Output Redirection in Vision-Language Models

    Aug 11, 2025Mansi Phute, Ravikumar BalakrishnanVLM RobustnessAdversarial Attacks on VLMs

    Georgia Institute of Technology · HiddenLayer, Inc