Ilyas, Andrew

Adversarial Examples Are Not Bugs, They Are Features

Ilyas, A., Santurkar, S., Tsipras, D., Engstrom, L., Tran, B., & Madry, A. (2019) · arXiv

Adversarial Robustness in Machine LearningMachine Learning and Data Classification

Cited by 971

Black-box Adversarial Attacks with Limited Queries and Information

Ilyas, A., Engstrom, L., Athalye, A., & Lin, J. (2018) · arXiv

Adversarial Robustness in Machine LearningSecurity and Verification in Computing

Cited by 806

Noise or Signal: The Role of Image Backgrounds in Object Recognition

Xiao, K., Engstrom, L., Ilyas, A., & Madry, A. (2020) · arXiv

Adversarial Robustness in Machine LearningAdvanced Neural Network Applications

Cited by 161

Implementation Matters in Deep Policy Gradients: A Case Study on PPO and TRPO

Engstrom, L., Ilyas, A., Santurkar, S., Tsipras, D., Janoos, F., Rudolph, L., & Madry, A. (2020) · arXiv

Reinforcement Learning in RoboticsAdaptive Dynamic Programming Control

Cited by 146

Optimizing ML Training with Metagradient Descent

Engstrom, L., Ilyas, A., Chen, B., Feldmann, A., Moses, W., & Madry, A. (2025) · arXiv

Machine Learning and Data ClassificationStochastic Gradient Optimization Techniques

Cited by 0