Adversarial-Guided Diffusion for Multimodal LLM Attacks

Abstract

This paper addresses the challenge of generating adversarial image using a diffusion model to deceive multimodal large language models (MLLMs) into generating the targeted responses, while avoiding significant distortion of the clean image. To address the above challenges, we propose an adversarial-guided diffusion (AGD) approach for adversarial attack MLLMs. We introduce adversarial-guided noise to ensure attack efficacy. A key observation in our design is that, unlike most traditional adversarial attacks which embed high-frequency perturbations directly into the clean image, AGD injects target semantics into the noise component of the reverse diffusion. Since the added noise in a diffusion model spans the entire frequency spectrum, the adversarial signal embedded within it also inherits this full-spectrum property. Importantly, during reverse diffusion, the adversarial image is formed as a linear combination of the clean image and the noise. Thus, when applying defenses such as a simple low-pass filtering, which act independently on each component, the adversarial image within the noise component is less likely to be suppressed, as it is not confined to the high-frequency band. This makes AGD inherently robust to variety defenses. Extensive experiments demonstrate that our AGD outperforms state-of-the-art methods in attack performance as well as in model robustness to some defenses.