标签
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.
本文研究了模型输出可能引发模仿的蒸馏攻击，提出了一个极小极大博弈框架和一种名为Product-of-Experts的仅前向传递防御方法，结果表明自适应学生模型能恢复的能力远超被动评估所显示的水平。