Shortcuts Arising from Contrast: Effective and Covert Clean-Label Attacks in Prompt-Based Learning

no code implementations • 30 Mar 2024 • Xiaopeng Xie, Ming Yan, Xiwen Zhou, Chenlong Zhao, Suli Wang, Yong Zhang, Joey Tianyi Zhou

In addressing this issue, we are inspired by the notion that a backdoor acts as a shortcut and posit that this shortcut stems from the contrast between the trigger and the data utilized for poisoning.

Data Augmentation Few-Shot Text Classification +1