| Mitigating Hallucinations in Large Language Models via Self-Refinement-Enhanced Knowledge Retrieval M Niu, H Li, J Shi, H Haddadi, F Mo arXiv preprint arXiv:2405.06545, 2024 | | 2024 |
| Advsv: An over-the-air adversarial attack dataset for speaker verification L Wang, J Li, Y Luo, J Zheng, L Wang, H Li, K Xu, C Fang, J Shi, Z Wu ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | 1 | 2024 |
| QUDA: query-limited data-free model extraction Z Lin, K Xu, C Fang, H Zheng, A Ahmed Jaheezuddin, J Shi Proceedings of the 2023 ACM Asia Conference on Computer and Communications …, 2023 | 5 | 2023 |
| 3dfed: Adaptive and extensible framework for covert backdoor attack in federated learning H Li, Q Ye, H Hu, J Li, L Wang, C Fang, J Shi 2023 IEEE Symposium on Security and Privacy (SP), 1893-1907, 2023 | 18 | 2023 |
| Differential aggregation against general colluding attackers R Du, Q Ye, Y Fu, H Hu, J Li, C Fang, J Shi 2023 IEEE 39th International Conference on Data Engineering (ICDE), 2180-2193, 2023 | 4 | 2023 |
| Mexmi: Pool-based active model extraction crossover membership inference Y Xiao, Q Ye, H Hu, H Zheng, C Fang, J Shi Advances in Neural Information Processing Systems 35, 10203-10216, 2022 | 2 | 2022 |
| TransPatch: a transformer-based generator for accelerating transferable patch generation in adversarial attacks against object detection models J Wang, C Cui, X Wen, J Shi European Conference on Computer Vision, 317-331, 2022 | 1 | 2022 |
| Repairing Adversarial Texts through Perturbation G Dong, J Wang, J Sun, S Chattopadhyay, X Wang, T Dai, J Shi, JS Dong International Symposium on Theoretical Aspects of Software Engineering, 29-48, 2022 | 1 | 2022 |
| Data theft prevention method and related product H Hu, H Zheng, YE Qingqing, F Chengfang, J Shi US Patent App. 17/698,619, 2022 | | 2022 |
| Causality-based neural network repair B Sun, J Sun, LH Pham, J Shi Proceedings of the 44th International Conference on Software Engineering …, 2022 | 51 | 2022 |
| Smartphones based vehicle access Y Yanjiang, Z Wei, CK Chu, J Shi US Patent 11,258,598, 2022 | 1 | 2022 |
| 深度学习模型鲁棒性研究综述 纪守领， 杜天宇， 邓水光， 程鹏， 时杰， 杨珉， 李博 计算机学报 45 (1), 190-206, 2022 | 6 | 2022 |
| Cert-RNN: Towards Certifying the Robustness of Recurrent Neural Networks. T Du, S Ji, L Shen, Y Zhang, J Li, J Shi, C Fang, J Yin, R Beyah, T Wang CCS 21 (2021), 15-19, 2021 | 29 | 2021 |
| Backdoor pre-trained models can transfer to all L Shen, S Ji, X Zhang, J Li, J Chen, J Shi, C Fang, J Yin, T Wang arXiv preprint arXiv:2111.00197, 2021 | 93 | 2021 |
| Towards certifying the asymmetric robustness for neural networks: quantification and applications C Li, S Ji, H Weng, B Li, J Shi, R Beyah, S Guo, Z Wang, T Wang IEEE Transactions on Dependable and Secure Computing 19 (6), 3987-4001, 2021 | 8 | 2021 |
| PrivKVM*: Revisiting key-value statistics estimation with local differential privacy Q Ye, H Hu, X Meng, H Zheng, K Huang, C Fang, J Shi IEEE Transactions on Dependable and Secure Computing 20 (1), 17-35, 2021 | 29 | 2021 |
| Information Processing Method, Terminal Device, and Network System CK Chu, D Naccache, J Shi, F Chengfang, F Xiwen US Patent App. 17/149,923, 2021 | | 2021 |
| Thief, beware of what get you there: Towards understanding model extraction attack X Zhang, C Fang, J Shi arXiv preprint arXiv:2104.05921, 2021 | 11 | 2021 |
| A-fmi: Learning attributions from deep networks via feature map importance A Zhang, X Wang, C Fang, J Shi, T Chua, Z Chen arXiv preprint arXiv:2104.05527, 2021 | 5 | 2021 |
| DAFAR: Defending against adversaries by feedback-autoencoder reconstruction H Liu, P Yi, HY Lin, J Shi, W Qiu arXiv preprint arXiv:2103.06487, 2021 | 2 | 2021 |
Chengfang FangPrincipal Researcher, Huawei International在 huawei.com 的电子邮件经过验证
