Adversarial Attacks on Multimodal Large Language Models: A Comprehensive Survey

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.

Key Contributions

Introduces goal-driven taxonomy organizing MLLM adversarial attacks by attacker objectives across modalities
Provides vulnerability-centric analysis linking attack families to shared architectural and representational weaknesses
Systematically covers cross-modal prompt injection, fusion mechanism attacks, adversarial illusions, and training-time poisoning

🛡️ Threat Analysis

Input Manipulation Attack

Survey covers adversarial perturbations and adversarial illusions designed to cause misclassification or erroneous outputs at inference time across multimodal inputs.