Attacking Adversarial Defences by Smoothing the Loss Landscape. (arXiv:2208.00862v2 [cs.LG] UPDATED)

This paper investigates a family of methods for defending against adversarial
attacks that owe part of their success to creating a noisy, discontinuous, or
otherwise rugged loss landscape that adversaries find difficult to navigate. A
common, but not universal, way to achieve this effect is via the use of
stochastic neural networks. We show that this is a form of gradient
obfuscation, and propose a general extension to gradient-based adversaries
based on the Weierstrass transform, which smooths the surface of …

adversarial lg loss