Boosting Barely Robust Learners: A New Perspective on Adversarial Robustness
Not on the map. Why?
Abstract (arXiv)
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 β 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.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 12 of its 39 references that are in the map. First posted on arXiv 11 Feb 2022.
Builds on
12 of 39 references.
References · 12
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
- 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
- 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
- 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
- 2019VC Classes are Adversarially Robustly Learnable, but Only Improperlycited by 83
- 2020Reducing Adversarially Robust Learning to Non-Robust PAC Learningcited by 28
- 2020Efficiently Learning Adversarially Robust Halfspaces with Noisecited by 22
- 2020Black-box Certification and Learning under Adversarial Perturbationscited by 13
- 2021A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustnesscited by 6
Built on by
Citing papers per year: 2022: 2; 2023: 0; 2024: 1.
3 papers.