Skip to content
InfoResearchPeer-reviewedLLM-specific

Enhanced Masking-Differential Prompting (MDP): Defending Backdoor Attacks for Pre-trained Language Models Under Few-Shot Learning

Published
Record updated
View JSON

Summary

This research paper proposes two enhancements to masking-differential prompting (MDP), a defense against backdoor attacks on pre-trained language models under few-shot, prompt-based learning. The authors replace KL divergence with Jensen–Shannon divergence, which stays finite when anchor set density is low, and add an adaptive threshold method that searches automatically using a false rejection rate (FRR) allowance instead of costly manual ROC/AUC threshold selection. The authors report that the method defends better against typical backdoor attacks on text classification and generation benchmarks.