| Text-to-image diffusion models can be easily backdoored through multimodal data poisoning S Zhai, Y Dong, Q Shen, S Pu, Y Fang, H Su Proceedings of the 31st ACM International Conference on Multimedia, 1577-1587, 2023 | 22 | 2023 |
| Kallima: A Clean-Label Framework for Textual Backdoor Attacks X Chen, Y Dong, Z Sun, S Zhai, Q Shen, Z Wu European Symposium on Research in Computer Security, 447-466, 2022 | 16 | 2022 |
| NCL: Textual Backdoor Defense Using Noise-Augmented Contrastive Learning S Zhai, Q Shen, X Chen, W Wang, C Li, Y Fang, Z Wu ICASSP 2023, 1-5, 2023 | 5 | 2023 |
| Automated Extraction of ABAC Policies from Natural-Language Documents in Healthcare Systems Y Xia, S Zhai, Q Wang, H Hou, Z Wu, Q Shen 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM …, 2022 | 3 | 2022 |
| Discovering Universal Semantic Triggers for Text-to-Image Synthesis S Zhai, W Wang, J Li, Y Dong, H Su, Q Shen arXiv preprint arXiv:2402.07562, 2024 | 1 | 2024 |
| Apple of sodom: Hidden backdoors in superior sentence embeddings via contrastive learning X Chen, B Xin, S Zhai, S Ma, Q Shen, Z Wu arXiv preprint arXiv:2210.11082, 2022 | 1 | 2022 |
| Security Equivalence Assessment between Cloud Standards by Mapping of Control Items Y Wong, C Yan, S Zhai, C Li, Q Shen ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and …, 2024 | | 2024 |
| TRLS: A Time Series Representation Learning Framework via Spectrogram for Medical Signal Processing L Xie, C Li, X Zhang, S Zhai, Y Fang, Q Shen, Z Wu arXiv preprint arXiv:2401.05431, 2024 | | 2024 |
| Text-to-Image Diffusion Models can be Easily Backdoored through Multimodal Data Poisoning Shengfang Zhai, Yinpeng Dong, Qingni Shen, Shi Pu, Yuejian Fang, Hang Su, MM '23: Proceedings of the 31st ACM International Conference on Multimedia …, 2023 | | 2023 |
Yinpeng DongTsinghua UniversityE-mail megerősítve itt: mails.tsinghua.edu.cn
