Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference

Byung-Kwan Lee, Youngjoon Yu, Yong Man Ro

Abstract: Recent works have applied Bayesian Neural Network (BNN) to adversarial training, and shown the improvement of adversarial robustness via the BNN's strength of stochastic gradient defense. However, we have found that in general, the BNN loses its stochasticity after its training with the BNN's posterior. As a result, the lack of the stochasticity leads to weak regularization effect to the BNN, which increases KL divergence in ELBO from variational inference. In this paper, we propose an enhanced Bayesian regularizer through hierarchical variational inference in order to boost adversarial robustness against gradient-based attack. Furthermore, we also prove that the proposed method allows the BNN's stochasticity to be elevated with the reduced KL divergence. Exhaustive experiment results demonstrate the effectiveness of the proposed method by showing the improvement of adversarial robustness, compared with adversarial training (Madry et al., 2018) and adversarial-BNN (Liu et al., 2019) under PGD attack and EOT-PGD attack to the $L_{\infty}$ perturbation on CIFAR-10/100, STL-10, and Tiny-ImageNet.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=5SJ0aogyNp