AI RESEARCH
TreeTeaming: Autonomous Red-Teaming of Vision-Language Models via Hierarchical Strategy Exploration
arXiv CS.LG
•
ArXi:2603.22882v1 Announce Type: new The rapid advancement of Vision-Language Models (VLMs) has brought their safety vulnerabilities into sharp focus. However, existing red teaming methods are fundamentally constrained by an inherent linear exploration paradigm, confining them to optimizing within a predefined strategy set and preventing the discovery of novel, diverse exploits. To transcend this limitation, we