| Provable defenses against adversarial examples via the convex outer adversarial polytope E Wong, JZ Kolter arXiv preprint arXiv:1711.00851, 2017 | 872 | 2017 |
| Provable defenses against adversarial examples via the convex outer adversarial polytope E Wong, J Zico Kolter arXiv preprint arXiv:1711.00851, 2017 | 872 | 2017 |
| Fast is better than free: Revisiting adversarial training E Wong, L Rice, JZ Kolter arXiv preprint arXiv:2001.03994, 2020 | 286 | 2020 |
| Scaling provable adversarial defenses E Wong, F Schmidt, JH Metzen, JZ Kolter Advances in Neural Information Processing Systems, 8400-8409, 2018 | 272 | 2018 |
| Overfitting in adversarially robust deep learning L Rice, E Wong, Z Kolter International Conference on Machine Learning, 8093-8104, 2020 | 145 | 2020 |
| Wasserstein adversarial examples via projected sinkhorn iterations E Wong, F Schmidt, Z Kolter International Conference on Machine Learning, 6808-6817, 2019 | 92 | 2019 |
| Adversarial robustness against the union of multiple perturbation models P Maini, E Wong, Z Kolter International Conference on Machine Learning, 6640-6650, 2020 | 39 | 2020 |
| Learning perturbation sets for robust machine learning E Wong, JZ Kolter arXiv preprint arXiv:2007.08450, 2020 | 22 | 2020 |
| A semismooth Newton method for fast, generic convex programming A Ali, E Wong, JZ Kolter Proceedings of the 34th International Conference on Machine Learning-Volume …, 2017 | 22 | 2017 |
| How many random restarts are enough? T Dick, E Wong, C Dann Google Scholar, 2014 | 8 | 2014 |
| Neural network virtual sensors for fuel injection quantities with provable performance specifications E Wong, T Schneider, J Schmitt, FR Schmidt, JZ Kolter 2020 IEEE Intelligent Vehicles Symposium (IV), 1753-1758, 2020 | 4 | 2020 |
| Leveraging Sparse Linear Layers for Debuggable Deep Networks E Wong, S Santurkar, A Mądry arXiv preprint arXiv:2105.04857, 2021 | 3 | 2021 |
| An SVD and derivative kernel approach to learning from geometric data E Wong, JZ Kolter Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015 | 2 | 2015 |
| DeepSplit: Scalable Verification of Deep Neural Networks via Operator Splitting S Chen, E Wong, JZ Kolter, M Fazlyab arXiv preprint arXiv:2106.09117, 2021 | | 2021 |
| Classification robust against multiple perturbation types E Wong, F Schmidt, JZ Kolter, P Maini US Patent App. 16/857,883, 2020 | | 2020 |
| Provable, structured, and efficient methods for robustness of deep networks to adversarial examples E Wong Carnegie Mellon University, 2020 | | 2020 |
| Method, Apparatus and Computer Program for Generating Robust Automated Learning Systems and Testing Trained Automated Learning Systems E Wong, F Schmidt, JH Metzen, JZ Kolter US Patent App. 16/173,698, 2019 | | 2019 |
| Semantic Adversarial Robustness with Differentiable Ray-Tracing R Venkatesh, E Wong, JZ Kolter | | |
| Need for Speed Tokyo Drift: Hotwheels Edition (A Drifting Control Case Study) E Wong, F Chen | | |
| CMU-ML-20-102 Provable, structured, and efficient methods for robustness of deep networks to adversarial examples E Wong | | |
