| Adversarial examples are not bugs, they are features A Ilyas, S Santurkar, D Tsipras, L Engstrom, B Tran, A Madry Advances in neural information processing systems 32, 2019 | 2595 | 2019 |
| Robustness may be at odds with accuracy D Tsipras, S Santurkar, L Engstrom, A Turner, A Madry arXiv preprint arXiv:1805.12152, 2018 | 2398 | 2018 |
| Synthesizing robust adversarial examples A Athalye, L Engstrom, A Ilyas, K Kwok arXiv preprint arXiv:1707.07397, 2017 | 2348 | 2017 |
| Black-box adversarial attacks with limited queries and information A Ilyas, L Engstrom, A Athalye, J Lin International conference on machine learning, 2137-2146, 2018 | 1719 | 2018 |
| A rotation and a translation suffice: Fooling cnns with simple transformations L Engstrom, B Tran, D Tsipras, L Schmidt, A Madry | 1001* | 2017 |
| Implementation matters in deep rl: A case study on ppo and trpo L Engstrom, A Ilyas, S Santurkar, D Tsipras, F Janoos, L Rudolph, ... International conference on learning representations, 2019 | 817* | 2019 |
| Do adversarially robust imagenet models transfer better? H Salman, A Ilyas, L Engstrom, A Kapoor, A Madry Advances in Neural Information Processing Systems 33, 3533-3545, 2020 | 576 | 2020 |
| Noise or signal: The role of image backgrounds in object recognition K Xiao, L Engstrom, A Ilyas, A Madry arXiv preprint arXiv:2006.09994, 2020 | 529 | 2020 |
| Prior convictions: Black-box adversarial attacks with bandits and priors A Ilyas, L Engstrom, A Madry arXiv preprint arXiv:1807.07978, 2018 | 497 | 2018 |
| Adversarial robustness as a prior for learned representations L Engstrom, A Ilyas, S Santurkar, D Tsipras, B Tran, A Madry arXiv preprint arXiv:1906.00945, 2019 | 305* | 2019 |
| Computer vision with a single (robust) classifier S Santurkar, D Tsipras, B Tran, A Ilyas, L Engstrom, A Madry arXiv preprint arXiv:1906.09453 4, 1, 2019 | 268* | 2019 |
| Robustness (python library), 2019 L Engstrom, A Ilyas, H Salman, S Santurkar, D Tsipras URL https://github. com/MadryLab/robustness 4 (4), 4.3, 2019 | 266 | 2019 |
| Datamodels: Predicting predictions from training data A Ilyas, SM Park, L Engstrom, G Leclerc, A Madry arXiv preprint arXiv:2202.00622, 2022 | 245 | 2022 |
| From imagenet to image classification: Contextualizing progress on benchmarks D Tsipras, S Santurkar, L Engstrom, A Ilyas, A Madry International Conference on Machine Learning, 9625-9635, 2020 | 196 | 2020 |
| A closer look at deep policy gradients A Ilyas, L Engstrom, S Santurkar, D Tsipras, F Janoos, L Rudolph, ... arXiv preprint arXiv:1811.02553, 2018 | 190* | 2018 |
| Evaluating and understanding the robustness of adversarial logit pairing L Engstrom, A Ilyas, A Athalye arXiv preprint arXiv:1807.10272, 2018 | 161 | 2018 |
| FFCV: Accelerating training by removing data bottlenecks G Leclerc, A Ilyas, L Engstrom, SM Park, H Salman, A Mądry Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2023 | 103 | 2023 |
| Dsdm: Model-aware dataset selection with datamodels L Engstrom, A Feldmann, A Madry arXiv preprint arXiv:2401.12926, 2024 | 97 | 2024 |
| Identifying statistical bias in dataset replication L Engstrom, A Ilyas, S Santurkar, D Tsipras, J Steinhardt, A Madry International Conference on Machine Learning, 2922-2932, 2020 | 72 | 2020 |
| Datamodels: Understanding predictions with data and data with predictions A Ilyas, SM Park, L Engstrom, G Leclerc, A Madry International Conference on Machine Learning, 9525-9587, 2022 | 68 | 2022 |
Andrew IlyasMassachusetts Institute of TechnologyVerified email at mit.edu
