4.7 Article

EEG-Based Brain-Computer Interfaces are Vulnerable to Backdoor Attacks

出版社

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNSRE.2023.3273214

关键词

Electroencephalography; Brain modeling; Training; Perturbation methods; Security; Convolution; Data models; Brain--computer interfaces; machine learning; adversarial attack; backdoor attack

向作者/读者索取更多资源

This paper proposes a narrow period pulse-based poisoning attack on EEG-based BCIs, which makes adversarial attacks easier to implement. By injecting poisoning samples into the training set, dangerous backdoors can be created in the machine learning model. Test samples with the backdoor key will be classified into the target class specified by the attacker. The distinguishing feature of this approach is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, raising a critical security concern for EEG-based BCIs and calling for urgent attention to address it.
Research and development of electroencephalogram (EEG) based brain-computer interfaces (BCIs) have advanced rapidly, partly due to deeper understanding of the brain and wide adoption of sophisticated machine learning approaches for decoding the EEG signals. However, recent studies have shown that machine learning algorithms are vulnerable to adversarial attacks. This paper proposes to use narrow period pulse for poisoning attack of EEG-based BCIs, which makes adversarial attacks much easier to implement. One can create dangerous backdoors in the machine learning model by injecting poisoning samples into the training set. Test samples with the backdoor key will then be classified into the target class specified by the attacker. What most distinguishes our approach from previous ones is that the backdoor key does not need to be synchronized with the EEG trials, making it very easy to implement. The effectiveness and robustness of the backdoor attack approach is demonstrated, highlighting a critical security concern for EEG-based BCIs and calling for urgent attention to address it.

作者

我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。

评论

主要评分

4.7
评分不足

次要评分

新颖性
-
重要性
-
科学严谨性
-
评价这篇论文

推荐

暂无数据
暂无数据