Diversity-enhanced Reconstruction as Plug-in Defenders against Adversarial Perturbations

Zeshan PangXuehu YanShasha Guo^*Yuliang Lu^*

• National University of Defense Technology College of Electronic Engineering, Changsha, China

Deep learning models are susceptible to adversarial examples. In large-scale deployed services, plug-in defenders efficiently defend against such attacks. Plug-in defenders take two approaches to mitigate adversarial effects: input reconstruction and random transformations. Existing plug-in defense lacks diversity in transformation formulation due to the inherent feature preservation nature, which leads to vulnerability under adaptive attacks. To address this issue, we propose a novel plug-in defense named Diversity-enhanced Reconstruction (DeR). DeR counters adversarial attacks by frequency-aware reconstructors with enhanced diversity. Specifically, we design the reconstructors as a U-Net backbone with additional frequency components. The reconstructors are trained on the proposed DeR loss, which optimizes the reconstruction and diversity objectives jointly. Once trained, DeR can produce heterogeneous gradients and be applied as a plug-in defense. We conduct extensive experiments on three datasets and four classifier architectures under strict adversarial settings. The results demonstrate the superior robustness of DeR compared to state-of-the-art plug-in defense and the efficiency of DeR in real-time processing.