training-time-defense

This paper proposes a training-time backdoor defense called Trapping and Removing (TR), which introduces a lightweight shortcut branch as a honeypot to trap backdoor knowledge and then discards it, enhanced by a knowledge decoupling strategy with entropy-based weight assignment.

HARVEY 通过学习一个带有后门的参考模型来准确识别有毒样本，实现近乎完美的后门移除，同时仅带来极小的准确率损失。