Images are Achilles' Heel of Alignment: Exploiting Visual Vulnerabilities for Jailbreaking Multimodal Large Language Models
arxiv(2024)
摘要
In this paper, we study the harmlessness alignment problem of multimodal
large language models (MLLMs). We conduct a systematic empirical analysis of
the harmlessness performance of representative MLLMs and reveal that the image
input poses the alignment vulnerability of MLLMs. Inspired by this, we propose
a novel jailbreak method named HADES, which hides and amplifies the harmfulness
of the malicious intent within the text input, using meticulously crafted
images. Experimental results show that HADES can effectively jailbreak existing
MLLMs, which achieves an average Attack Success Rate (ASR) of 90.26
LLaVA-1.5 and 71.60
released.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要