Overparametrization improves robustness against adversarial attacks: A replication study

20 February 2022

Papers citing "Overparametrization improves robustness against adversarial attacks: A replication study"

12 / 12 papers shown

Title
The curse of overparametrization in adversarial training: Precise analysis of robust generalization for random features regression Hamed Hassani Adel Javanmard AAML 26 36 0 13 Jan 2022
A Universal Law of Robustness via Isoperimetry Sébastien Bubeck Mark Sellke 38 218 0 26 May 2021
Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples Sven Gowal Chongli Qin J. Uesato Timothy A. Mann Pushmeet Kohli AAML 47 331 0 07 Oct 2020
A law of robustness for two-layers neural networks Sébastien Bubeck Yuanzhi Li Dheeraj M. Nagaraj 62 57 0 30 Sep 2020
Deep Double Descent: Where Bigger Models and More Data Hurt Preetum Nakkiran Gal Kaplun Yamini Bansal Tristan Yang Boaz Barak Ilya Sutskever 119 940 0 04 Dec 2019
Intriguing properties of adversarial training at scale Cihang Xie Alan Yuille AAML 46 68 0 10 Jun 2019
Do ImageNet Classifiers Generalize to ImageNet? Benjamin Recht Rebecca Roelofs Ludwig Schmidt Vaishaal Shankar OOD SSeg VLM 111 1,714 0 13 Feb 2019
Reconciling modern machine learning practice and the bias-variance trade-off M. Belkin Daniel J. Hsu Siyuan Ma Soumik Mandal 227 1,644 0 28 Dec 2018
ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness Robert Geirhos Patricia Rubisch Claudio Michaelis Matthias Bethge Felix Wichmann Wieland Brendel 100 2,666 0 29 Nov 2018
Sensitivity and Generalization in Neural Networks: an Empirical Study Roman Novak Yasaman Bahri Daniel A. Abolafia Jeffrey Pennington Jascha Narain Sohl-Dickstein AAML 93 439 0 23 Feb 2018
Towards Deep Learning Models Resistant to Adversarial Attacks Aleksander Madry Aleksandar Makelov Ludwig Schmidt Dimitris Tsipras Adrian Vladu SILM OOD 292 12,060 0 19 Jun 2017
Explaining and Harnessing Adversarial Examples Ian Goodfellow Jonathon Shlens Christian Szegedy AAML GAN 259 19,045 0 20 Dec 2014