Assessing the Adversarial Robustness of Monte Carlo and Distillation Methods for Deep Bayesian Neural Network Classification
This work addresses adversarial robustness for deep learning practitioners, but it is incremental as it compares existing methods without introducing new ones.
The paper tackled the problem of assessing adversarial robustness in deep Bayesian neural networks, showing that full MCMC-based inference significantly outperforms standard point estimation with excellent robustness, while BDK provides only marginal improvements.
In this paper, we consider the problem of assessing the adversarial robustness of deep neural network models under both Markov chain Monte Carlo (MCMC) and Bayesian Dark Knowledge (BDK) inference approximations. We characterize the robustness of each method to two types of adversarial attacks: the fast gradient sign method (FGSM) and projected gradient descent (PGD). We show that full MCMC-based inference has excellent robustness, significantly outperforming standard point estimation-based learning. On the other hand, BDK provides marginal improvements. As an additional contribution, we present a storage-efficient approach to computing adversarial examples for large Monte Carlo ensembles using both the FGSM and PGD attacks.