The Wolf Within: Covert Injection of Malice into MLLM Societies via an MLLM Operative

arXiv:2402.14859v1 Announce Type: cross
Abstract: Due to their unprecedented ability to process and respond to various types of data, Multimodal Large Language Models (MLLMs) are constantly defining the new boundary of Artificial General Intelligence (AGI). As these advanced generative models increasingly form collaborative networks for complex tasks, the integrity and security of these systems are crucial. Our paper, ``The Wolf Within'', explores a novel vulnerability in MLLM societies - the indirect propagation of malicious content. Unlike direct harmful output generation …

arxiv cs.ai cs.cr cs.cy cs.lg mllm type via