Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness
Machine Learning
2022-02-15 v1 Machine Learning
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 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.
Cite
@article{arxiv.2202.05920,
title = {Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness},
author = {Avrim Blum and Omar Montasser and Greg Shakhnarovich and Hongyang Zhang},
journal= {arXiv preprint arXiv:2202.05920},
year = {2022}
}