Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms Paper • 2604.23775 • Published 3 days ago • 38
AutoMIA: Improved Baselines for Membership Inference Attack via Agentic Self-Exploration Paper • 2604.01014 • Published 27 days ago • 11
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models Paper • 2603.15557 • Published Mar 16 • 29
Anatomy of a Lie: A Multi-Stage Diagnostic Framework for Tracing Hallucinations in Vision-Language Models Paper • 2603.15557 • Published Mar 16 • 29
Vid-SME: Membership Inference Attacks against Large Video Understanding Models Paper • 2506.03179 • Published May 29, 2025