팔로우
Shangxi Wu
Shangxi Wu
Computer Vision, Beijing Jiaotong University
bjtu.edu.cn의 이메일 확인됨 - 홈페이지
제목
인용
인용
연도
Are you copying my model? protecting the copyright of large language models for EaaS via backdoor watermark
W Peng, J Yi, F Wu, ...
ACL 2023 (Area Chair Award) 1, 7653-7668, 2024
52*2024
Robust CAPTCHAs towards malicious OCR
J Zhang, J Sang, K Xu, S Wu, X Zhao, Y Sun, Y Hu, J Yu
IEEE Transactions on Multimedia 23, 2575-2587, 2020
252020
Butterfly detection and classification based on integrated YOLO algorithm
B Liang, S Wu, K Xu, J Hao
Genetic and Evolutionary Computing: Proceedings of the Thirteenth …, 2020
182020
Attention, please! adversarial defense via activation rectification and preservation
S Wu, J Sang, K Xu, J Zhang, J Yu
ACM Transactions on Multimedia Computing, Communications and Applications 19 …, 2023
7*2023
o1-coder: an o1 replication for coding
Y Zhang, S Wu, Y Yang, J Shu, J Xiao, C Kong, J Sang
arXiv preprint arXiv:2412.00154, 2024
62024
Adaptive adversarial logits pairing
S Wu, J Sang, K Xu, G Zheng, C Xu
ACM Transactions on Multimedia Computing, Communications and Applications 20 …, 2023
42023
Debiasing backdoor attack: A benign application of backdoor attack in eliminating data bias
S Wu, Q He, Y Zhang, D Lu, J Sang
Information Sciences 643, 119171, 2023
32023
Backdoor for Debias: Mitigating Model Bias with Backdoor Attack-based Artificial Bias
S Wu, Q He, J Yu, J Sang
arXiv preprint arXiv:2303.01504, 2023
22023
An experimental study of semantic continuity for deep learning models
S Wu, D Lu, X Zhao, L Chen, J Sang
arXiv preprint arXiv:2011.09789, 2020
12020
A Disguised Wolf Is More Harmful Than a Toothless Tiger: Adaptive Malicious Code Injection Backdoor Attack Leveraging User Behavior as Triggers
S Wu, J Sang
arXiv preprint arXiv:2408.10334, 2024
2024
基于奇异值分解的隐式后门攻击方法
吴尚锡， 尹雨阳， 宋思清， 陈观浩， 桑基韬， 于剑
软件学报 35 (5), 2400-2413, 2023
2023
현재 시스템이 작동되지 않습니다. 나중에 다시 시도해 주세요.
학술자료 1–11