2025年2月4日
Proj CJI Paper Reading: Agent Smith: A Single Image Can Jailbreak One Million Multimodal LLM Agents Exponentially Fast
摘要： Abstract Background: adversarial images/prompts can jailbreak Multimodal large language model and cause unaligned behaviors 本文报告了在multi-agent + MLLM环境 阅读全文
posted @ 2025-02-04 19:02 雪溯 阅读(22) 评论(0) 推荐(0)