A First Look at the Security of EEG-based Systems and Intelligent Algorithms under Physical Signal Injections
A First Look at the Security of EEG-based Systems and Intelligent Algorithms under Physical Signal Injections
复制标题
DOI：
10.1145/3591197.3591304
复制
发表时间：
2023-07
期刊：
影响因子：
--
通讯作者：
Md. Imran Hossen;Yazhou Tu;X. Hei
中科院分区：
文献类型：
--
作者：
Md. Imran Hossen;Yazhou Tu;X. Hei
基于脑电图（EEG）的系统在各种应用中利用机器学习（ML）和深度学习（DL）模型，例如癫痫发作检测、情感识别、认知工作负荷估计和脑机接口（BCI）。然而，在模拟域的威胁下，这种智能系统的安全性和鲁棒性受到了有限的关注。本文首次演示了利用EEG数据对ML和DL模型进行物理信号注入攻击。我们研究了对手如何通过非侵入性地将信号注入EEG记录来降低不同模型的性能。我们表明，攻击可以误导或操纵的模型，并降低基于EEG的系统的可靠性。总的来说，这项研究揭示了医疗保健领域对更值得信赖的基于生理信号的智能系统的需求，并为未来的工作开辟了道路。
Electroencephalography (EEG) based systems utilize machine learning (ML) and deep learning (DL) models in various applications such as seizure detection, emotion recognition, cognitive workload estimation, and brain-computer interface (BCI). However, the security and robustness of such intelligent systems under analog-domain threats have received limited attention. This paper presents the first demonstration of physical signal injection attacks on ML and DL models utilizing EEG data. We investigate how an adversary can degrade the performance of different models by non-invasively injecting signals into EEG recordings. We show that the attacks can mislead or manipulate the models and diminish the reliability of EEG-based systems. Overall, this research sheds light on the need for more trustworthy physiological-signal-based intelligent systems in the healthcare field and opens up avenues for future work.