SAFE: Secure and Accurate Federated Learning for Privacy-Preserving Brain-Computer Interfaces
This work addresses privacy and robustness issues in brain-computer interfaces, which is critical for real-world applications, though it appears incremental as it builds on federated learning with specific enhancements.
The paper tackles the challenges of generalization, adversarial vulnerability, and privacy leakage in EEG-based brain-computer interfaces by proposing SAFE, a federated learning approach that improves decoding accuracy and adversarial robustness while protecting user privacy, outperforming 14 state-of-the-art methods and even centralized training without privacy protection.
Electroencephalogram (EEG)-based brain-computer interfaces (BCIs) are widely adopted due to their efficiency and portability; however, their decoding algorithms still face multiple challenges, including inadequate generalization, adversarial vulnerability, and privacy leakage. This paper proposes Secure and Accurate FEderated learning (SAFE), a federated learning-based approach that protects user privacy by keeping data local during model training. SAFE employs local batch-specific normalization to mitigate cross-subject feature distribution shifts and hence improves model generalization. It further enhances adversarial robustness by introducing perturbations in both the input space and the parameter space through federated adversarial training and adversarial weight perturbation. Experiments on five EEG datasets from motor imagery (MI) and event-related potential (ERP) BCI paradigms demonstrated that SAFE consistently outperformed 14 state-of-the-art approaches in both decoding accuracy and adversarial robustness, while ensuring privacy protection. Notably, it even outperformed centralized training approaches that do not consider privacy protection at all. To our knowledge, SAFE is the first algorithm to simultaneously achieve high decoding accuracy, strong adversarial robustness, and reliable privacy protection without using any calibration data from the target subject, making it highly desirable for real-world BCIs.