| Fedprompt: Communication-efficient and privacy-preserving prompt tuning in federated learning H Zhao, W Du, F Li, P Li, G Liu ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and …, 2023 | 58 | 2023 |
| PPT: Backdoor Attacks on Pre-trained Models via Poisoned Prompt Tuning. W Du, Y Zhao, B Li, G Liu, S Wang IJCAI, 680-686, 2022 | 51 | 2022 |
| Plmmark: a secure and robust black-box watermarking framework for pre-trained language models P Li, P Cheng, F Li, W Du, H Zhao, G Liu Proceedings of the AAAI Conference on Artificial Intelligence 37 (12), 14991 …, 2023 | 43 | 2023 |
| TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Models P Cheng, Y Ding, T Ju, Z Wu, W Du, P Yi, Z Zhang, G Liu arXiv preprint arXiv:2405.13401, 2024 | 22 | 2024 |
| Backdoor attacks and countermeasures in natural language processing models: A comprehensive security review P Cheng, Z Wu, W Du, H Zhao, W Lu, G Liu arXiv preprint arXiv:2309.06055, 2023 | 21 | 2023 |
| Reduce communication costs and preserve privacy: Prompt tuning method in federated learning GL Haodong Zhao, Wei Du, Fangqi Li, Peixuan Li arXiv preprint arXiv 2208, 2022 | 20* | 2022 |
| Uor: Universal backdoor attacks on pre-trained language models W Du, P Li, B Li, H Zhao, G Liu arXiv preprint arXiv:2305.09574, 2023 | 19 | 2023 |
| How large language models encode context knowledge? a layer-wise probing study T Ju, W Sun, W Du, X Yuan, Z Ren, G Liu arXiv preprint arXiv:2402.16061, 2024 | 14 | 2024 |
| Investigating Multi-Hop Factual Shortcuts in Knowledge Editing of Large Language Models T Ju, Y Chen, X Yuan, Z Zhang, W Du, Y Zheng, G Liu arXiv preprint arXiv:2402.11900, 2024 | 9 | 2024 |
| Transferring backdoors between large language models by knowledge distillation P Cheng, Z Wu, T Ju, W Du, ZZG Liu arXiv preprint arXiv:2408.09878, 2024 | 4 | 2024 |
| NWS: Natural Textual Backdoor Attacks Via Word Substitution W Du, TX Yuan, HD Zhao, GS Liu ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 4 | 2024 |
| Revisiting the Information Capacity of Neural Network Watermarks: Upper Bound Estimation and Beyond F Li, H Zhao, W Du, S Wang Proceedings of the AAAI Conference on Artificial Intelligence 38 (19), 21331 …, 2024 | 3 | 2024 |
| A Universal Identity Backdoor Attack against Speaker Verification based on Siamese Network H Zhao, W Du, J Guo, G Liu arXiv preprint arXiv:2303.16031, 2023 | 3 | 2023 |
| SynGhost: Imperceptible and Universal Task-agnostic Backdoor Attack in Pre-trained Language Models P Cheng, W Du, Z Wu, F Zhang, L Chen, G Liu arXiv preprint arXiv:2402.18945, 2024 | 2 | 2024 |
| A Semi-shared Hierarchical Joint Model for Sequence Labeling G LIU, W DU, J ZHOU, J LI, J CHENG Chinese Journal of Electronics 32 (2), 1-12, 2023 | 2* | 2023 |
| 深度学习中的后门攻击综述 杜巍， 刘功申 Journal of Cyber Security 7 (3), 1-16, 2022 | 2 | 2022 |
| Backdoor NLP Models via AI-Generated Text W Du, T Ju, G Ren, GL Li, G Liu Proceedings of the 2024 Joint International Conference on Computational …, 2024 | 1 | 2024 |
Haodong ZhaoShanghai Jiao Tong UniversityDirección de correo verificada de sjtu.edu.cn