Analysis of Random Perturbations for Robust Convolutional Neural Networks
Recent work has extensively shown that randomized perturbations of neural networks can improve robustness to adversarial attacks. The literature is, however, lacking a detailed compare-and-contrast of the latest proposals to understand what classes of perturbations work, when they work, and why they work. We contribute a detailed evaluation that elucidates these questions and benchmarks perturbation based defenses consistently. In particular, we show five main results: (1) all input perturbation defenses, whether random or deterministic, are equivalent in their efficacy, (2) attacks transfer between perturbation defenses so the attackers need not know the specific type of defense -- only that it involves perturbations, (3) a tuned sequence of noise layers across a network provides the best empirical robustness, (4) perturbation based defenses offer almost no robustness to adaptive attacks unless these perturbations are observed during training, and (5) adversarial examples in a close neighborhood of original inputs show an elevated sensitivity to perturbations in first and second-order analyses.
PDF Abstract