| Leveraging transferability and improved beam search in textual adversarial attacks B Zhu, Z Gu, Y Qian, F Lau, Z Tian Neurocomputing 500, 135-142, 2022 | 14 | 2022 |
| Improving robustness of language models from a geometry-aware perspective B Zhu, Z Gu, L Wang, J Chen, Q Xuan Findings of ACL 2022, 2022 | 13 | 2022 |
| TREATED: Towards universal defense against textual adversarial attacks B Zhu, Z Gu, L Wang, Z Tian arXiv preprint arXiv:2109.06176, 2021 | 4 | 2021 |
| Word-level textual adversarial attack in the embedding space B Zhu, Z Gu, Y Xie, D Wu, Y Qian, L Wang 2021 International Joint Conference on Neural Networks (IJCNN), 1-8, 2021 | 2 | 2021 |
| Exploring Robust Overfitting for Pre-trained Language Models B Zhu, Y Rao Findings of the Association for Computational Linguistics: ACL 2023, 5506-5522, 2023 | | 2023 |
