Alignment-Based Adversarial Training (ABAT) for Improving the Robustness and Accuracy of EEG-Based BCIs

TL;DR

This paper introduces Alignment-Based Adversarial Training (ABAT), a novel method that enhances both the robustness and accuracy of EEG-based brain-computer interfaces by combining data alignment with adversarial training.

Contribution

The paper proposes a new approach, ABAT, that integrates EEG data alignment with adversarial training to improve BCI classifier performance and security.

Findings

ABAT improves classification accuracy on multiple EEG datasets.

ABAT enhances robustness against adversarial attacks.

The method is effective across different BCI paradigms and classifiers.

Abstract

Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI studies focused on improving the decoding accuracy, with only a few considering the adversarial security. Although many adversarial defense approaches have been proposed in other application domains such as computer vision, previous research showed that their direct extensions to BCIs degrade the classification accuracy on benign samples. This phenomenon greatly affects the applicability of adversarial defense approaches to EEG-based BCIs. To mitigate this problem, we propose alignment-based adversarial training (ABAT), which performs EEG data alignment before adversarial training. Data alignment aligns EEG trials from different domains to reduce their distribution discrepancies, and adversarial training further robustifies the classification boundary. The integration of data alignment and adversarial training can make the trained EEG classifiers simultaneously more accurate and more robust. Experiments on five EEG datasets from two different BCI paradigms (motor imagery classification, and event related potential recognition), three convolutional neural network classifiers (EEGNet, ShallowCNN and DeepCNN) and three different experimental settings (offline within-subject cross-block/-session classification, online cross-session classification, and pre-trained classifiers) demonstrated its effectiveness. It is very intriguing that adversarial attacks, which are usually used to damage BCI systems, can be used in ABAT to simultaneously improve the model accuracy and robustness.