How Does Mixup Help With Robustness and Generalization?
Authors: Linjun Zhang, Zhun Deng, Kenji Kawaguchi, Amirata Ghorbani, James Zou | Published: 2020-10-09 | Updated: 2021-03-17
Poisoning
Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples
Authors: Sven Gowal, Chongli Qin, Jonathan Uesato, Timothy Mann, Pushmeet Kohli | Published: 2020-10-07 | Updated: 2021-03-30
Understanding Catastrophic Overfitting in Single-step Adversarial Training
Authors: Hoki Kim, Woojin Lee, Jaewook Lee | Published: 2020-10-05 | Updated: 2020-12-15
Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks
Authors: Uday Shankar Shanthamallu, Jayaraman J. Thiagarajan, Andreas Spanias | Published: 2020-09-30
Adversarial Robustness of Stabilized NeuralODEs Might be from Obfuscated Gradients
Authors: Yifei Huang, Yaodong Yu, Hongyang Zhang, Yi Ma, Yuan Yao | Published: 2020-09-28 | Updated: 2021-06-02
A Robust graph attention network with dynamic adjusted Graph
Authors: Xianchen Zhou, Yaoyun Zeng, Hongxia Wang | Published: 2020-09-28 | Updated: 2022-08-04
Semantics-Preserving Adversarial Training
Authors: Wonseok Lee, Hanbit Lee, Sang-goo Lee | Published: 2020-09-23
Crafting Adversarial Examples for Deep Learning Based Prognostics (Extended Version)
Authors: Gautam Raj Mode, Khaza Anuarul Hoque | Published: 2020-09-21 | Updated: 2020-09-28
Adversarial Concept Drift Detection under Poisoning Attacks for Robust Data Stream Mining
Authors: Łukasz Korycki, Bartosz Krawczyk | Published: 2020-09-20
Data Poisoning Attacks on Regression Learning and Corresponding Defenses
Authors: Nicolas Michael Müller, Daniel Kowatsch, Konstantin Böttinger | Published: 2020-09-15