The 6th Workshop of Adversarial Machine Learning on Computer Vision: Safety of Vision-Language Agents

Accepted papers (10)

Fetched from OpenReview (v2) on 2026-06-10.

1. ☆

   ARMs: Adaptive Red-Teaming Agent against Multimodal Models with Plug-and-Play Attacks

   Zhaorun Chen, Xun Liu, Mintong Kang, Jiawei Zhang, Minzhou Pan, Shuang Yang, Bo Li · PDF
2. ☆

   ATAC: Augmentation-Based Test-Time Adversarial Correction for CLIP

   Su Linxiang, András Balogh · PDF
3. ☆

   Auditing Traffic-Sign Robustness via DDIM Inversion: Do Diffusion Latents Preserve Shadow Attacks?

   Ashton B. McEntarffer, Amir Salarpour, Pedram MohajerAnsari, Mert D. Pesé · PDF
4. ☆

   Evaluating Vulnerabilities in Vision-Language Models: Impact of Behavior-Induced Interference

   Yuwei Chen, Shiyong Chu · PDF
5. ☆

   Interpretable Adversarial Prompt Tuning via Semantic Concepts

   Pedram MohajerAnsari, Zongxi Liu, Yi Zhu, Amir Salarpour, Mert D. Pesé · PDF
6. ☆

   MirrorCheck: Efficient Adversarial Defense for Vision-Language Models

   Samar Fares, Toluwani Aremu, Klea Ziu, Nikita Durasov, Martin Takáč, Pascal Fua, Karthik Nandakumar, Ivan Laptev · PDF
7. ☆

   Robustness of Vision Foundation Models to Common Perturbations

   Hongbin Liu, Zhengyuan Jiang, Cheng Hong, Neil Zhenqiang Gong · PDF
8. ☆

   SafeGRPO: Self-Rewarded Multimodal Safety Alignment via Rule-Governed Policy Optimization

   Xuankun Rong, Wenke Huang, Tingfeng Wang, Daiguo Zhou, Bo Du, Mang Ye · PDF
9. ☆

   SASA: Sequence-Aware Shadow Attacks via Attention Alignment for Traffic Sign Recognition

   Amir Salarpour, Pedram MohajerAnsari, David Fernandez, Mert D. Pesé · PDF
10. ☆

    SkillJect: Automating Stealthy Skill-Based Prompt Injection for Coding Agents with Trace-Driven Closed-Loop Refinement

    Xiaojun Jia, Jie Liao, Simeng Qin, Jindong Gu, Wenqi Ren, Xiaochun Cao, Yang Liu, Philip Torr · PDF