Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awareness
Authors: Glenn Dawson, Robi Polikar | Published: 2021-05-28 | Updated: 2021-06-05
敵対的訓練
Adversarial Information Bottleneck
Authors: Penglong Zhai, Shihua Zhang | Published: 2021-02-28 | Updated: 2021-03-03
Bridging the Gap Between Adversarial Robustness and Optimization Bias
Authors: Fartash Faghri, Sven Gowal, Cristina Vasconcelos, David J. Fleet, Fabian Pedregosa, Nicolas Le Roux | Published: 2021-02-17 | Updated: 2021-06-07
Perceptually Constrained Adversarial Attacks
Authors: Muhammad Zaid Hameed, Andras Gyorgy | Published: 2021-02-14
Efficient Certified Defenses Against Patch Attacks on Image Classifiers
Authors: Jan Hendrik Metzen, Maksym Yatsura | Published: 2021-02-08
Optimal Transport as a Defense Against Adversarial Attacks
Authors: Quentin Bouniot, Romaric Audigier, Angélique Loesch | Published: 2021-02-05 | Updated: 2021-03-30
Adversarially Robust Learning with Unknown Perturbation Sets
Authors: Omar Montasser, Steve Hanneke, Nathan Srebro | Published: 2021-02-03
Fast Training of Provably Robust Neural Networks by SingleProp
Authors: Akhilan Boopathy, Tsui-Wei Weng, Sijia Liu, Pin-Yu Chen, Gaoyuan Zhang, Luca Daniel | Published: 2021-02-01
Meta Adversarial Training against Universal Patches
Authors: Jan Hendrik Metzen, Nicole Finnie, Robin Hutmacher | Published: 2021-01-27 | Updated: 2021-06-22
Robustness, Privacy, and Generalization of Adversarial Training
Authors: Fengxiang He, Shaopeng Fu, Bohan Wang, Dacheng Tao | Published: 2020-12-25