On the Robustness of Bayesian Neural Networks to Adversarial Attacks. (arXiv:2207.06154v1 [cs.LG])

Vulnerability to adversarial attacks is one of the principal hurdles to the
adoption of deep learning in safety-critical applications. Despite significant
efforts, both practical and theoretical, training deep learning models robust
to adversarial attacks is still an open problem. In this paper, we analyse the
geometry of adversarial attacks in the large-data, overparameterized limit for
Bayesian Neural Networks (BNNs). We show that, in the limit, vulnerability to
gradient-based attacks arises as a result of degeneracy in the data
distribution, i.e., …

adversarial attacks lg networks neural networks robustness