Content-based Unrestricted Adversarial Attack

Zhaoyu Chen, Bo Li, Shuang Wu, Kaixun Jiang, Shouhong Ding, Wenqiang Zhang

Keywords: unrestricted attack, adversarial example, diffusion model, black-box attack, adversarial transferability

TL;DR: We propose a attack framework called Content-based Unrestricted Adversarial Attack, which utilizes a low-dimensional manifold to optimize images along adversarial direction, resulting in natural and highly transferable adversarial examples.

Abstract: Unrestricted adversarial attacks typically manipulate the semantic content of an image (e.g., color or texture) to create adversarial examples that are both effective and photorealistic, demonstrating their ability to deceive human perception and deep neural networks with stealth and success. However, current works usually sacrifice unrestricted degrees and subjectively select some image content to guarantee the photorealism of unrestricted adversarial examples, which limits its attack performance. To ensure the photorealism of adversarial examples and boost attack performance, we propose a novel unrestricted attack framework called Content-based Unrestricted Adversarial Attack. By leveraging a low-dimensional manifold that represents natural images, we map the images onto the manifold and optimize them along its adversarial direction. Therefore, within this framework, we implement Adversarial Content Attack (ACA) based on Stable Diffusion and can generate high transferable unrestricted adversarial examples with various adversarial contents. Extensive experimentation and visualization demonstrate the efficacy of ACA, particularly in surpassing state-of-the-art attacks by an average of 13.3-50.4\% and 16.8-48.0\% in normally trained models and defense methods, respectively.

Submission Number: 3991