| Rethinking the value of network pruning Z Liu, M Sun, T Zhou, G Huang, T Darrell International Conference on Learning Representations, 2019 | 974 | 2019 |
| Data poisoning attack against unsupervised node embedding methods M Sun, J Tang, H Li, B Li, C Xiao, Y Chen, D Song arXiv preprint arXiv:1810.12881, 2018 | 53 | 2018 |
| Denoised smoothing: A provable defense for pretrained classifiers H Salman, M Sun, G Yang, A Kapoor, JZ Kolter Advances in Neural Information Processing Systems 33, 21945-21957, 2020 | 43* | 2020 |
| Characterizing attacks on deep reinforcement learning C Xiao, X Pan, W He, J Peng, M Sun, J Yi, M Liu, B Li, D Song International Conference on Autonomous Agents and Multiagent Systems, 2022 | 38 | 2022 |
| Poisoned classifiers are not only backdoored, they are fundamentally broken M Sun, S Agarwal, JZ Kolter arXiv preprint arXiv:2010.09080, 2020 | 11 | 2020 |
| Can Shape Structure Features Improve Model Robustness under Diverse Adversarial Settings? M Sun, Z Li, C Xiao, H Qiu, B Kailkhura, M Liu, B Li Proceedings of the IEEE/CVF International Conference on Computer Vision …, 2021 | 2 | 2021 |
Trevor DarrellProfessor of Computer Science, U.C. BerkeleyVerified email at eecs.berkeley.edu
