Skip to content
conftrace_

red team

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

jailbreak attack (2) multi-turn interrogation (1) multimodal jailbreak (1) large language model (1) security risk (1) vulnerability identification (1) safety benchmark (1) vision-language model (1) diffusion model (1) adversarial learning (1)

Papers

Chain of Attack: Hide Your Intention through Multi-Turn Interrogation ACL 2025 IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves ICCV 2025