Rethinking the Backdoor Attacks’ Triggers: A Frequency PerspectiveYi Zeng * 1 , Won Park * 2 , Z. Morley Mao 2 and Ruoxi Jia 11 Virginia Tech, Blacksburg, VA 24061, USA2 University of Michigan, Ann Arbor, MI 48109, USAAbstractBackdoor attacks have been considered a severe securitythreat...
Rethinking the Trigger of Backdoor AttackYiming LiTongqing ZhaiBaoyuan WuYong JiangZhifeng LiShu-Tao Xia
Backdoor attacks have been considered a severe security threat to deep learning. Such attacks can make models perform abnormally on inputs with predefined triggers and still retain state-of-the-art performance on clean data. While backdoor attacks have been thoroughly investigated in the image doma...
Code for the paperRethinking Stealthiness of Backdoor Attack against NLP Models(ACL-IJCNLP 2021) [pdf] In this work, we first give a systematic rethinking about the stealthiness of current backdoor attacking approaches, and point out current methods either make the triggers easily exposed to sys...