| Delving into transferable adversarial examples and black-box attacks Y Liu, X Chen, C Liu, D Song arXiv preprint arXiv:1611.02770, 2016 | 1752 | 2016 |
| Targeted backdoor attacks on deep learning systems using data poisoning X Chen, C Liu, B Li, K Lu, D Song arXiv preprint arXiv:1712.05526, 2017 | 1400 | 2017 |
| Scaling instruction-finetuned language models HW Chung, L Hou, S Longpre, B Zoph, Y Tay, W Fedus, Y Li, X Wang, ... arXiv preprint arXiv:2210.11416, 2022 | 900 | 2022 |
| Competition-level code generation with alphacode Y Li, D Choi, J Chung, N Kushman, J Schrittwieser, R Leblond, T Eccles, ... Science 378 (6624), 1092-1097, 2022 | 418 | 2022 |
| Adversarial example defense: Ensembles of weak defenses are not strong W He, J Wei, X Chen, N Carlini, D Song 11th USENIX workshop on offensive technologies (WOOT 17), 2017 | 411 | 2017 |
| Learning to perform local rewriting for combinatorial optimization X Chen, Y Tian Advances in Neural Information Processing Systems 32, 2019 | 298 | 2019 |
| Tree-to-tree neural networks for program translation X Chen, C Liu, D Song Advances in neural information processing systems 31, 2018 | 243 | 2018 |
| Dataset security for machine learning: Data poisoning, backdoor attacks, and defenses M Goldblum, D Tsipras, C Xie, X Chen, A Schwarzschild, D Song, ... IEEE Transactions on Pattern Analysis and Machine Intelligence 45 (2), 1563-1580, 2022 | 210* | 2022 |
| Execution-guided neural program synthesis X Chen, C Liu, D Song International Conference on Learning Representations, 2018 | 131 | 2018 |
| Refit: a unified watermark removal framework for deep learning systems with limited data X Chen, W Wang, C Bender, Y Ding, R Jia, B Li, D Song Proceedings of the 2021 ACM Asia Conference on Computer and Communications …, 2021 | 107* | 2021 |
| Fooling vision and language models despite localization and attention mechanism X Xu, X Chen, C Liu, A Rohrbach, T Darrell, D Song Proceedings of the IEEE Conference on Computer Vision and Pattern …, 2018 | 102* | 2018 |
| Teaching large language models to self-debug X Chen, M Lin, N Schärli, D Zhou arXiv preprint arXiv:2304.05128, 2023 | 100 | 2023 |
| Neural symbolic reader: Scalable integration of distributed and symbolic representations for reading comprehension X Chen, C Liang, AW Yu, D Zhou, D Song, QV Le International Conference on Learning Representations, 2019 | 97 | 2019 |
| Latent attention for if-then program synthesis C Liu, X Chen, EC Shin, M Chen, D Song Advances in Neural Information Processing Systems 29, 2016 | 94 | 2016 |
| Compositional generalization via neural-symbolic stack machines X Chen, C Liang, AW Yu, D Song, D Zhou Advances in Neural Information Processing Systems 33, 1690-1701, 2020 | 80 | 2020 |
| Robustart: Benchmarking robustness on architecture design and training techniques S Tang, R Gong, Y Wang, A Liu, J Wang, X Chen, F Yu, X Liu, D Song, ... arXiv preprint arXiv:2109.05211, 2021 | 73 | 2021 |
| Larger language models do in-context learning differently J Wei, J Wei, Y Tay, D Tran, A Webson, Y Lu, X Chen, H Liu, D Huang, ... arXiv preprint arXiv:2303.03846, 2023 | 72 | 2023 |
| Lego: Latent execution-guided reasoning for multi-hop question answering on knowledge graphs H Ren, H Dai, B Dai, X Chen, M Yasunaga, H Sun, D Schuurmans, ... International conference on machine learning, 8959-8970, 2021 | 70 | 2021 |
| Large language models can be easily distracted by irrelevant context F Shi, X Chen, K Misra, N Scales, D Dohan, EH Chi, N Schärli, D Zhou International Conference on Machine Learning, 31210-31227, 2023 | 66* | 2023 |
| Coda: An end-to-end neural program decompiler C Fu, H Chen, H Liu, X Chen, Y Tian, F Koushanfar, J Zhao Advances in Neural Information Processing Systems 32, 2019 | 65 | 2019 |
Dawn SongProfessor of Computer Science, UC BerkeleyVerified email at cs.berkeley.edu
