FRIB: Low-poisoning Rate Invisible Backdoor Attack based on Feature Repair

no code implementations • 26 Jul 2022 • Hui Xia, Xiugui Yang, Xiangyun Qian, Rui Zhang

To solve the above problems, we propose the idea of feature repair for the first time and introduce the blind watermark technique to repair the poisoned features lost during the generation of poisoned data.

Backdoor Attack