Verifying in the Dark: Verifiable Machine Unlearning by Using Invisible Backdoor Triggers - researchr publication related

researchr

You are not signed in
Sign in
Sign up

Yu Guo 0003, Yu Zhao, Saihui Hou, Cong Wang 0001, Xiaohua Jia. Verifying in the Dark: Verifiable Machine Unlearning by Using Invisible Backdoor Triggers. IEEE Transactions on Information Forensics and Security, 19:708-721, 2024. [doi]

The following publications are possibly variants of this publication:

Backdoor Defense with Machine UnlearningYang Liu, Mingyuan Fan, Cen Chen, Ximeng Liu, Zhuo Ma, Li Wang, Jianfeng Ma 0001. infocom 2022: 280-289 [doi]

Backdoor Attack With Sparse and Invisible TriggerYinghua Gao, Yiming Li 0004, Xueluan Gong, Zhifeng Li 0001, Shu-Tao Xia, Qian Wang 0002. tifs, 19:6364-6376, 2024. [doi]

Backdoor Attacks via Machine UnlearningZihao Liu, Tianhao Wang 0001, Mengdi Huai, Chenglin Miao. AAAI 2024: 14115-14123 [doi]

Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic TriggerFanchao Qi, Mukai Li, Yangyi Chen, Zhengyan Zhang, Zhiyuan Liu 0001, Yasheng Wang, Maosong Sun. acl 2021: 443-453 [doi]

Invisible Backdoor Attack With Dynamic Triggers Against Person Re-IdentificationWenli Sun, Xinyang Jiang, Shuguang Dou, Dongsheng Li 0002, Duoqian Miao, Cheng Deng, Cairong Zhao. tifs, 19:307-319, 2024. [doi]

ICT: Invisible Computable Trigger Backdoor Attacks in Transfer LearningXiang Chen, Bo Liu 0057, Shaofeng Zhao, Ming Liu 0028, Hui Xu, Zhanbo Li, Zhigao Zheng 0001. tce, 70(4):6747-6758, November 2024. [doi]

runs on WebDSL