Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey
It addresses security risks in MLLMs for researchers and practitioners, but is incremental as a survey rather than a novel method.
This survey tackles the problem of adversarial vulnerabilities in multimodal large language models (MLLMs) by providing a comprehensive analysis and taxonomy of attack techniques, linking them to underlying architectural weaknesses to inform robust system development.
Multimodal large language models (MLLMs) integrate information from multiple modalities such as text, images, audio, and video, enabling complex capabilities such as visual question answering and audio translation. While powerful, this increased expressiveness introduces new and amplified vulnerabilities to adversarial manipulation. This survey provides a comprehensive and systematic analysis of adversarial threats to MLLMs, moving beyond enumerating attack techniques to explain the underlying causes of model susceptibility. We introduce a taxonomy that organizes adversarial attacks according to attacker objectives, unifying diverse attack surfaces across modalities and deployment settings. Additionally, we also present a vulnerability-centric analysis that links integrity attacks, safety and jailbreak failures, control and instruction hijacking, and training-time poisoning to shared architectural and representational weaknesses in multimodal systems. Together, this framework provides an explanatory foundation for understanding adversarial behavior in MLLMs and informs the development of more robust and secure multimodal language systems.