DeCE
- [[Defending Code Language Models against Backdoor Attacks with Deceptive Cross-Entropy Loss]]
Signature in code backdoor detection, how far are we?
- 谱特征检测后门触发器
ABM
- [[Anti-backdoor model:A novel algorithm to remove backdoors in a non-invasive way.]]
- #CV 分类任务的针对后门攻击的防御
- 训练一个外部模型来识别并抵消后门行为,而不用修改原模型
%% kanban:settings
1 | |
%%