Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games. (arXiv:2210.12606v2 [cs.LG] UPDATED)

Adversarial training is a standard technique for training adversarially
robust models. In this paper, we study adversarial training as an alternating
best-response strategy in a 2-player zero-sum game. We prove that even in a
simple scenario of a linear classifier and a statistical model that abstracts
robust vs. non-robust features, the alternating best response strategy of such
game may not converge. On the other hand, a unique pure Nash equilibrium of the
game exists and is provably robust. We support …

arxiv equilibria games robustness training