Logit Pairing Methods Can Fool Gradient-Based Attacks

29 October 2018

Marius Mosbach

Maksym Andriushchenko

Matthias Hein

Papers citing "Logit Pairing Methods Can Fool Gradient-Based Attacks"

21 / 21 papers shown

Title
Standard-Deviation-Inspired Regularization for Improving Adversarial Robustness Olukorede Fakorede Modeste Atsague Jin Tian AAML 37 0 0 31 Dec 2024
Towards Unified Robustness Against Both Backdoor and Adversarial Attacks Zhenxing Niu Yuyao Sun Qiguang Miao Rong Jin Gang Hua AAML 38 6 0 28 May 2024
Sparsity Winning Twice: Better Robust Generalization from More Efficient Training Tianlong Chen Zhenyu (Allen) Zhang Pengju Wang Santosh Balachandra Haoyu Ma Zehao Wang Zhangyang Wang OOD AAML 79 46 0 20 Feb 2022
Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networks Weiran Lin Keane Lucas Lujo Bauer Michael K. Reiter Mahmood Sharif AAML 29 5 0 28 Dec 2021
Data Augmentation Can Improve Robustness Sylvestre-Alvise Rebuffi Sven Gowal D. A. Calian Florian Stimberg Olivia Wiles Timothy A. Mann AAML 17 269 0 09 Nov 2021
Improving Robustness using Generated Data Sven Gowal Sylvestre-Alvise Rebuffi Olivia Wiles Florian Stimberg D. A. Calian Timothy A. Mann 30 293 0 18 Oct 2021
Understanding the Logit Distributions of Adversarially-Trained Deep Neural Networks Landan Seguin A. Ndirango Neeli Mishra SueYeon Chung Tyler Lee OOD 25 2 0 26 Aug 2021
Fixing Data Augmentation to Improve Adversarial Robustness Sylvestre-Alvise Rebuffi Sven Gowal D. A. Calian Florian Stimberg Olivia Wiles Timothy A. Mann AAML 30 268 0 02 Mar 2021
Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples Sven Gowal Chongli Qin J. Uesato Timothy A. Mann Pushmeet Kohli AAML 17 323 0 07 Oct 2020
Label Smoothing and Adversarial Robustness Chaohao Fu Hongbin Chen Na Ruan Weijia Jia AAML 8 12 0 17 Sep 2020
Witches' Brew: Industrial Scale Data Poisoning via Gradient Matching Jonas Geiping Liam H. Fowl W. R. Huang W. Czaja Gavin Taylor Michael Moeller Tom Goldstein AAML 19 215 0 04 Sep 2020
Adversarial Training against Location-Optimized Adversarial Patches Sukrut Rao David Stutz Bernt Schiele AAML 11 91 0 05 May 2020
Adversarial Robustness on In- and Out-Distribution Improves Explainability Maximilian Augustin Alexander Meinke Matthias Hein OOD 75 98 0 20 Mar 2020
Overfitting in adversarially robust deep learning Leslie Rice Eric Wong Zico Kolter 30 785 0 26 Feb 2020
Fast is better than free: Revisiting adversarial training Eric Wong Leslie Rice J. Zico Kolter AAML OOD 52 1,158 0 12 Jan 2020
The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey Olakunle Ibitoye Rana Abou-Khamis Mohamed el Shehaby Ashraf Matrawy M. O. Shafiq AAML 26 68 0 06 Nov 2019
Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack Francesco Croce Matthias Hein AAML 34 474 0 03 Jul 2019
Intriguing properties of adversarial training at scale Cihang Xie Alan Yuille AAML 8 68 0 10 Jun 2019
Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks Maksym Andriushchenko Matthias Hein 20 61 0 08 Jun 2019
Scaling up the randomized gradient-free adversarial attack reveals overestimation of robustness using established attacks Francesco Croce Jonas Rauber Matthias Hein AAML 20 30 0 27 Mar 2019
Using Pre-Training Can Improve Model Robustness and Uncertainty Dan Hendrycks Kimin Lee Mantas Mazeika NoLa 17 717 0 28 Jan 2019