VisualDAN: Exposing Vulnerabilities in VLMs with Visual-Driven DAN Commands

Vision-Language Models VLMs have garnered significant attention for their remarkable ability to interpret and generate multimodal content. However, securing these models against jailbreak attacks continues to be a substantial challenge. Unlike text-only models, VLMs integrate additional modalitie...

MAI-2024-0059

Multimodal Large Language Models MLLMs operating within multi-agent environments are susceptible to a sophisticated attack known as "infectious jailbreak." This vulnerability is triggered by the introduction of a single adversarial image into the memory of one agent, which can rapidly propagate...