Active poisoning:efficient backdoor attacks on transfer learning-based brain-computer interfaces  

作　　者：Xue JIANG Lubin MENG Siyang LI Dongrui WU 

机构地区：[1]School of Artificial Intel ligence and Automation,Huazhong University of Science and Technology,Wuhan 430074,China [2]Zhejiang Lab,Hangzhou 311121,China

出　　处：《Science China(Information Sciences)》2023年第8期207-228,共22页中国科学（信息科学）（英文版）

基　　金：supported by Open Research Projects of Zhejiang Lab(Grnat No.2021KE0AB04);Technology Innovation Project of Hubei Province of China(Grnat No.2019AEA171);Hubei Province Funds for Distinguished Young Scholars(Grnat No.2020CFA050)。

摘　　要：Transfer learning(TL)has been widely used in electroencephalogram(EEG)-based braincomputer interfaces(BCIs)for reducing calibration efforts.However,backdoor attacks could be introduced through TL.In such attacks,an attacker embeds a backdoor with a specific pattern into the machine learning model.As a result,the model will misclassify a test sample with the backdoor trigger into a prespecified class while still maintaining good performance on benign samples.Accordingly,this study explores backdoor attacks in the TL of EEG-based BCIs,where source-domain data are poisoned by a backdoor trigger and then used in TL.We propose several active poisoning approaches to select source-domain samples,which are most effective in embedding the backdoor pattern,to improve the attack success rate and efficiency.Experiments on four EEG datasets and three deep learning models demonstrate the effectiveness of the approaches.To our knowledge,this is the first study about backdoor attacks on TL models in EEG-based BCIs.It exposes a serious security risk in BCIs,which should be immediately addressed.

关 键 词：brain-computer interface ELECTROENCEPHALOGRAM transfer learning poisoning attack backdoor attack 

分 类 号：R318[医药卫生—生物医学工程] TN911.7[医药卫生—基础医学] TP309[电子电信—通信与信息系统]