Transferable and high-quality adversarial example generation leveraging diffusion model

Kangze Xu, Ziqiang He, Xiangui Kang, Z. Jane Wang

Abstract: In recent years, adversarial example methods in deep learning have proliferated. Meanwhile diffusion models have gained wide applications across various tasks due to their superior distribution reconstruction capability. By leveraging the design experience from prior adversarial examples, combining it with the modeling proficiency of diffusion models, and employing a cost function to evaluate image smoothness for regulating the regional distribution of adversarial noise, we propose a novel adversarial example design method. Experiments demonstrate that our generated adversarial examples exhibit both high attack success rate and superior image quality. The controlled distribution region of adversarial noises significantly enhances the subjective visual quality of our generated images.