Adversarial Artifact Detection in EEG-Based Brain-Computer Interfaces

TL;DR

This paper investigates the vulnerability of EEG-based brain-computer interfaces to adversarial attacks and proposes detection methods to identify such malicious perturbations, enhancing the security of BCI systems.

Contribution

It is the first study to explore adversarial detection in EEG-based BCIs, demonstrating detection capabilities against both white-box and black-box attacks.

Findings

White-box attacks are easier to detect than black-box attacks.

Multiple detection approaches effectively identify adversarial examples.

Detection methods work across different EEG datasets and CNN architectures.

Abstract

Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI research focused on improving its accuracy, but few had considered its security. Recent studies, however, have shown that EEG-based BCIs are vulnerable to adversarial attacks, where small perturbations added to the input can cause misclassification. Detection of adversarial examples is crucial to both the understanding of this phenomenon and the defense. This paper, for the first time, explores adversarial detection in EEG-based BCIs. Experiments on two EEG datasets using three convolutional neural networks were performed to verify the performances of multiple detection approaches. We showed that both white-box and black-box attacks can be detected, and the former are easier to detect.