The Curious Case of Adversarially Robust Models: More Data Can Help,
Double Descend, or Hurt Generalization

The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization

25 February 2020

Papers citing "The Curious Case of Adversarially Robust Models: More Data Can Help, Double Descend, or Hurt Generalization"

13 / 13 papers shown

Title
Efficient Optimization Algorithms for Linear Adversarial Training Antônio H. Ribeiro Thomas B. Schon Dave Zahariah Francis Bach AAML 39 1 0 16 Oct 2024
Investigating the Impact of Model Complexity in Large Language Models Jing Luo Huiyuan Wang Weiran Huang 34 0 0 01 Oct 2024
Recent Advances in Attack and Defense Approaches of Large Language Models Jing Cui Yishi Xu Zhewei Huang Shuchang Zhou Jianbin Jiao Junge Zhang PILM AAML 52 1 0 05 Sep 2024
CUDA: Convolution-based Unlearnable Datasets Vinu Sankar Sadasivan Mahdi Soltanolkotabi S. Feizi MU 29 23 0 07 Mar 2023
Beyond the Universal Law of Robustness: Sharper Laws for Random Features and Neural Tangent Kernels Simone Bombari Shayan Kiyani Marco Mondelli AAML 18 10 0 03 Feb 2023
Data Augmentation Alone Can Improve Adversarial Training Lin Li Michael W. Spratling 16 49 0 24 Jan 2023
The Effects of Regularization and Data Augmentation are Class Dependent Randall Balestriero Léon Bottou Yann LeCun 28 94 0 07 Apr 2022
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes Elvis Dohmatob A. Bietti AAML 18 13 0 22 Mar 2022
Adversarial robustness of sparse local Lipschitz predictors Ramchandran Muthukumar Jeremias Sulam AAML 29 13 0 26 Feb 2022
Precise Statistical Analysis of Classification Accuracies for Adversarial Training Adel Javanmard Mahdi Soltanolkotabi AAML 24 62 0 21 Oct 2020
Multiple Descent: Design Your Own Generalization Curve Lin Chen Yifei Min M. Belkin Amin Karbasi DRL 18 61 0 03 Aug 2020
Disentangling Adversarial Robustness and Generalization David Stutz Matthias Hein Bernt Schiele AAML OOD 186 272 0 03 Dec 2018
Adversarial examples from computational constraints Sébastien Bubeck Eric Price Ilya P. Razenshteyn AAML 60 230 0 25 May 2018