Purifier$^{+}$ : Plug-and-play Backdoor Mitigation for Pre-trained Models Via Activation Alignment
IEEE Transactions on Multimedia（2025）
关键词
Backdoor attack and defense,Pre-trained model,Activation pattern alignment
AI 理解论文
溯源树
样例
生成溯源树，研究论文发展脉络
Chat Paper
正在生成论文摘要