UOR: Universal Backdoor Attacks on Pre-trained Language Models

no code implementations • 16 May 2023 • Wei Du, Peixuan Li, Boqun Li, Haodong Zhao, Gongshen Liu

In this paper, we first summarize the requirements that a more threatening backdoor attack against PLMs should satisfy, and then propose a new backdoor attack method called UOR, which breaks the bottleneck of the previous approach by turning manual selection into automatic optimization.

Backdoor Attack Contrastive Learning +2