CMU Artificial Intelligence Seminar Series ^{sponsored by}

Tuesday, March 28, 2023

Time: 12:00 - 01:00 PM ET

Rattana Pukdee -- Nash Equilibria and Pitfalls of Adversarial Training in Adversarial Robustness Games

Relevant Paper(s):

• N/A

Abstract: In this talk, we will look at the problem of learning adversarially robust models from the perspective of a 2-player zero-sum game. We will show 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 (which resembles adversarial training) of such a game may not converge. On the other hand, a unique pure Nash equilibrium of the game exists and is provably robust. We support our theoretical results with experiments, showing the non-convergence of adversarial training and the robustness of Nash equilibrium.