Unbridled Icarus: A Survey of the Potential Perils of Image Inputs in Multimodal Large Language Model Security

arXiv:2404.05264v1 Announce Type: cross
Abstract: Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities that increasingly influence various aspects of our daily lives, constantly defining the new boundary of Artificial General Intelligence (AGI). Image modalities, enriched with profound semantic information and a more continuous mathematical nature compared to other modalities, greatly enhance the functionalities of MLLMs when integrated. However, this integration serves as a double-edged sword, providing attackers with expansive vulnerabilities to exploit for highly covert and harmful attacks. The pursuit …

abstract agi artificial artificial general intelligence arxiv capabilities continuous cs.cr cs.cv daily general image influence information inputs intelligence language language model language models large language large language model large language models mllms multimodal multimodal large language model security semantic survey type