IS-Bench: Evaluating Interactive Safety of VLM-Driven Embodied Agents in Daily Household Tasks Paper • 2506.16402 • Published Jun 19 • 1
Derail Yourself: Multi-turn LLM Jailbreak Attack through Self-discovered Clues Paper • 2410.10700 • Published Oct 14, 2024 • 3
X-Boundary: Establishing Exact Safety Boundary to Shield LLMs from Multi-Turn Jailbreaks without Compromising Usability Paper • 2502.09990 • Published Feb 14 • 1