Timezone: »

Phase-aware Adversarial Defense for Improving Adversarial Robustness
Dawei Zhou · Nannan Wang · Heng Yang · Xinbo Gao · Tongliang Liu

Tue Jul 25 02:00 PM -- 04:30 PM (PDT) @ Exhibit Hall 1 #109

Deep neural networks have been found to be vulnerable to adversarial noise. Recent works show that exploring the impact of adversarial noise on intrinsic components of data can help improve adversarial robustness. However, the pattern closely related to human perception has not been deeply studied. In this paper, inspired by the cognitive science, we investigate the interference of adversarial noise from the perspective of image phase, and find ordinarily-trained models lack enough robustness against phase-level perturbations. Motivated by this, we propose a joint adversarial defense method: a phase-level adversarial training mechanism to enhance the adversarial robustness on the phase pattern; an amplitude-based pre-processing operation to mitigate the adversarial perturbation in the amplitude pattern. Experimental results show that the proposed method can significantly improve the robust accuracy against multiple attacks and even adaptive attacks. In addition, ablation studies demonstrate the effectiveness of our defense strategy.

Author Information

Dawei Zhou (Xidian University)
Nannan Wang (Xidian University)
Heng Yang (University of Cambridge)
Xinbo Gao (Chongqing University of Posts and Telecommunications)
Tongliang Liu (The University of Sydney)

More from the Same Authors