Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness

Avrim Blum · Omar Montasser · Greg Shakhnarovich · Hongyang Zhang

Hall J #1036

Keywords: [ boosting ] [ Oracle complexity ] [ Sample Complexity ] [ Adversarial Robustness ]

Abstract: We present an oracle-efficient algorithm for boosting the adversarial robustness of barely robust learners. Barely robust learning algorithms learn predictors that are adversarially robust only on a small fraction $\beta \ll 1$ of the data distribution. Our proposed notion of barely robust learning requires robustness with respect to a ``larger'' perturbation set; which we show is necessary for strongly robust learning, and that weaker relaxations are not sufficient for strongly robust learning. Our results reveal a qualitative and quantitative equivalence between two seemingly unrelated problems: strongly robust learning and barely robust learning.

Chat is not available.