DLP: towards active defense against backdoor attacks with decoupled learning process

被引:0
作者
Zonghao Ying
Bin Wu
机构
[1] State Key Laboratory of Information Security,School of Cyber Security
[2] Institute of Information Engineering,undefined
[3] Chinese Academy of Sciences,undefined
[4] University of Chinese Academy of Sciences,undefined
来源
Cybersecurity | / 6卷
关键词
Deep learning; Backdoor attack; Active defense;
D O I
暂无
中图分类号
学科分类号
摘要
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 unreliable 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.
引用
收藏
相关论文
共 25 条
[1]  
Garcia-Garcia A(2018)A survey on deep learning techniques for image and video semantic segmentation Appl Soft Comput 70 41-65
[2]  
Orts-Escolano S(2019)Survey on semantic segmentation using deep learning techniques Neurocomputing 338 321-348
[3]  
Oprea S(2019)Virtual adversarial training: a regularization method for supervised and semi-supervised learning IEEE Trans Pattern Anal Mach Intell 41 1979-1993
[4]  
Lateef F(2022)A survey of deep active learning ACM Comput Surv 54 1801-18040
[5]  
Ruichek Y(2015)Large-margin multi-modal deep learning for RGB-D object recognition IEEE Trans Multim 17 1887-1898
[6]  
Miyato T(2015)Multi-class active learning by uncertainty sampling with diversity maximization Int J Comput Vis 113 113-127
[7]  
Maeda S(2018)Dep learning for environmentally robust speech recognition: an overview of recent developments ACM Trans Intell Syst Technol 9 491-4928
[8]  
Koyama M(undefined)undefined undefined undefined undefined-undefined
[9]  
Ishii S(undefined)undefined undefined undefined undefined-undefined
[10]  
Ren P(undefined)undefined undefined undefined undefined-undefined