Simpler Certified Radius Maximization by Propagating Covariances.

ABSTRACT: One strategy for adversarially training a robust model is to maximize its certified radius - the neighborhood around a given training sample for which the model's prediction remains unchanged. The scheme typically involves analyzing a "smoothed" classifier where one estimates the prediction corresponding to Gaussian samples in the neighborhood of each sample in the mini-batch, accomplished in practice by Monte Carlo sampling. In this paper, we investigate the hypothesis that this sampling bottleneck can potentially be mitigated by identifying ways to directly propagate the covariance matrix of the smoothed distribution through the network. To this end, we find that other than certain adjustments to the network, propagating the covariances must also be accompanied by additional accounting t

SUBMITTER: Zhen X 

PROVIDER: S-EPMC8579953 | biostudies-literature | 2021 Jun

REPOSITORIES: biostudies-literature