LIRA: Learnable, Imperceptible and Robust Backdoor Attacks
( 2021.10.17       ICCV 21 )
Khoa Doan, Yingjie Lao, Weijie Zhao, Ping Li
Cognitive Computing Lab
Baidu Research
10900 NE 8th St. Bellevue, WA 98004, USA
文章链接:View PDF
         工程链接:未开源
所属类别:Dirty-Label  |  Sample-Specific  |  Digital Attack  |  Single Trigger Attack
推荐阅读指数:❤❤❤❤