首页|DLP:towards active defense against backdoor attacks with decoupled learning process
DLP:towards active defense against backdoor attacks with decoupled learning process
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
万方数据
维普
Deep learning models are well known to be susceptible to backdoor attack,where the attacker only needs to provide a tampered dataset on which the triggers are injected.Models trained on the dataset will passively implant the backdoor,and triggers on the input can mislead the models during testing.Our study shows that the model shows different learning behaviors in clean and poisoned subsets during training.Based on this observation,we propose a general training pipeline to defend against backdoor attacks actively.Benign models can be trained from the unreli-able dataset by decoupling the learning process into three stages,i.e.,supervised learning,active unlearning,and active semi-supervised fine-tuning.The effectiveness of our approach has been shown in numerous experiments across various backdoor attacks and datasets.
Deep learningBackdoor attackActive defense
Zonghao Ying、Bin Wu
展开 >
State Key Laboratory of Information Security,Institute of Information Engineering,Chinese Academy of Sciences,Beijing,China
School of Cyber Security,University of Chinese Academy of Sciences,Beijing,China
National Nature Science Foundation of ChinaNational Nature Science Foundation of ChinaMajor Technology Program of Hainan,China
万方数据
维普
