| Deep partition aggregation: Provable defense against general poisoning attacks A Levine, S Feizi International Conference on Learning Representations 2021; arXiv preprint …, 2020 | 158 | 2020 |
| Robustness certificates for sparse adversarial attacks by randomized ablation A Levine, S Feizi Proceedings of the AAAI Conference on Artificial Intelligence 34 (04), 4585-4593, 2020 | 114 | 2020 |
| Curse of dimensionality on randomized smoothing for certifiable robustness A Kumar, A Levine, T Goldstein, S Feizi International Conference on Machine Learning, 5458-5467, 2020 | 104 | 2020 |
| Segment and complete: Defending object detectors against adversarial patch attacks with robust patch detection J Liu, A Levine, CP Lau, R Chellappa, S Feizi Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern …, 2022 | 102 | 2022 |
| Dual manifold adversarial robustness: Defense against lp and non-lp adversarial attacks WA Lin, CP Lau, A Levine, R Chellappa, S Feizi Advances in Neural Information Processing Systems 33, 3487-3498, 2020 | 69 | 2020 |
| Improved certified defenses against data poisoning with (deterministic) finite aggregation W Wang, AJ Levine, S Feizi International Conference on Machine Learning, 22769-22783, 2022 | 68 | 2022 |
| Certifiably robust interpretation in deep learning A Levine, S Singla, S Feizi arXiv preprint arXiv:1905.12105, 2019 | 62 | 2019 |
| Wasserstein smoothing: Certified robustness against wasserstein adversarial attacks A Levine, S Feizi International Conference on Artificial Intelligence and Statistics, 3938-3947, 2020 | 61 | 2020 |
| (De) randomized smoothing for certifiable defense against patch attacks A Levine, S Feizi Advances in Neural Information Processing Systems 33, 6465-6475, 2020 | 61 | 2020 |
| Policy smoothing for provably robust reinforcement learning A Kumar, A Levine, S Feizi International Conference on Learning Representations 2022; arXiv preprint …, 2021 | 60 | 2021 |
| Improved, deterministic smoothing for l_1 certified robustness AJ Levine, S Feizi International Conference on Machine Learning, 6254-6264, 2021 | 47 | 2021 |
| Certifying confidence via randomized smoothing A Kumar, A Levine, S Feizi, T Goldstein Advances in Neural Information Processing Systems 33, 5165-5177, 2020 | 44 | 2020 |
| Provable Robustness against Wasserstein Distribution Shifts via Input Randomization A Kumar, A Levine, T Goldstein, S Feizi ICLR 2023, 2023 | 18* | 2023 |
| Tight second-order certificates for randomized smoothing A Levine, A Kumar, T Goldstein, S Feizi arXiv preprint arXiv:2010.10549, 2020 | 15 | 2020 |
| Lethal dose conjecture on data poisoning W Wang, A Levine, S Feizi Advances in neural information processing systems 35, 1776-1789, 2022 | 12 | 2022 |
| Invariant learning via diffusion dreamed distribution shifts P Kattakinda, A Levine, S Feizi arXiv preprint arXiv:2211.10370, 2022 | 11 | 2022 |
| Provable adversarial robustness for fractional lp threat models AJ Levine, S Feizi International Conference on Artificial Intelligence and Statistics, 9908-9942, 2022 | 5 | 2022 |
| Goal-conditioned Q-learning as knowledge distillation A Levine, S Feizi Proceedings of the AAAI Conference on Artificial Intelligence 37 (7), 8500-8509, 2023 | 4 | 2023 |
| Learning a Fast Mixing Exogenous Block MDP using a Single Trajectory A Levine, P Stone, A Zhang arXiv preprint arXiv:2410.03016, 2024 | | 2024 |
| Multistep Inverse Is Not All You Need A Levine, P Stone, A Zhang Reinforcement Learning Conference 2024; arXiv preprint arXiv:2403.11940, 2024 | | 2024 |
