A single gradient step finds adversarial examples on random two-layers neural networks

8 April 2021

Sébastien Bubeck

Yeshwanth Cherapanamjeri

Gauthier Gidel

Rémi Tachet des Combes

MLT

ArXiv PDF HTML

Papers citing "A single gradient step finds adversarial examples on random two-layers neural networks"

23 / 23 papers shown

Title
Deep Neural Nets as Hamiltonians Mike Winer Boris Hanin 73 0 0 31 Mar 2025
Adversarial Training Can Provably Improve Robustness: Theoretical Analysis of Feature Learning Process Under Structured Data Binghui Li Yuanzhi Li OOD 28 2 0 11 Oct 2024
MALT Powers Up Adversarial Attacks Odelia Melamed Gilad Yehudai Adi Shamir AAML 20 0 0 02 Jul 2024
Effect of Ambient-Intrinsic Dimension Gap on Adversarial Vulnerability Rajdeep Haldar Yue Xing Qifan Song 21 3 0 06 Mar 2024
Upper and lower bounds for the Lipschitz constant of random neural networks Paul Geuchen Thomas Heindl Dominik Stöger Felix Voigtlaender AAML 24 0 0 02 Nov 2023
On the Stability of Iterative Retraining of Generative Models on their own Data Quentin Bertrand A. Bose Alexandre Duplessis Marco Jiralerspong Gauthier Gidel 22 42 0 30 Sep 2023
A Linearly Convergent GAN Inversion-based Algorithm for Reverse Engineering of Deceptions D. Thaker Paris V. Giampouras René Vidal AAML 11 0 0 07 Jun 2023
Cross-Entropy Loss Functions: Theoretical Analysis and Applications Anqi Mao M. Mohri Yutao Zhong AAML 10 270 0 14 Apr 2023
How many dimensions are required to find an adversarial example? Charles Godfrey Henry Kvinge Elise Bishoff Myles Mckay Davis Brown T. Doster E. Byler AAML 41 5 0 24 Mar 2023
The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks Spencer Frei Gal Vardi Peter L. Bartlett Nathan Srebro 27 17 0 02 Mar 2023
Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces Odelia Melamed Gilad Yehudai Gal Vardi GAN 13 1 0 01 Mar 2023
A generalizable framework for low-rank tensor completion with numerical priors Shi-Meng Yuan Kaizhu Huang 6 3 0 12 Feb 2023
Blessings and Curses of Covariate Shifts: Adversarial Learning Dynamics, Directional Convergence, and Equilibria Tengyuan Liang 13 1 0 05 Dec 2022
Evolution of Neural Tangent Kernels under Benign and Adversarial Training Noel Loo Ramin Hasani Alexander Amini Daniela Rus AAML 19 12 0 21 Oct 2022
Adversarial Robustness is at Odds with Lazy Training Yunjuan Wang Enayat Ullah Poorya Mianjy R. Arora SILM AAML 17 10 0 18 Jun 2022
Adversarial Noises Are Linearly Separable for (Nearly) Random Neural Networks Huishuai Zhang Da Yu Yiping Lu Di He AAML 12 1 0 09 Jun 2022
Adversarial Reprogramming Revisited Matthias Englert R. Lazic AAML 16 8 0 07 Jun 2022
Adversarial Examples in Random Neural Networks with General Activations Andrea Montanari Yuchen Wu GAN AAML 61 13 0 31 Mar 2022
Origins of Low-dimensional Adversarial Perturbations Elvis Dohmatob Chuan Guo Morgane Goibert AAML 26 4 0 25 Mar 2022
On the (Non-)Robustness of Two-Layer Neural Networks in Different Learning Regimes Elvis Dohmatob A. Bietti AAML 8 13 0 22 Mar 2022
Gradient Methods Provably Converge to Non-Robust Networks Gal Vardi Gilad Yehudai Ohad Shamir 22 27 0 09 Feb 2022
Adversarial Examples in Multi-Layer Random ReLU Networks Peter L. Bartlett Sébastien Bubeck Yeshwanth Cherapanamjeri AAML GAN 8 28 0 23 Jun 2021
Non-asymptotic approximations of neural networks by Gaussian processes Ronen Eldan Dan Mikulincer T. Schramm 28 24 0 17 Feb 2021