User-wise Perturbations for User Identity Protection in EEG-Based BCIs
Not on the map. Why?
Abstract (arXiv)
Objective: An electroencephalogram (EEG)-based brain-computer interface (BCI) is a direct communication pathway between the human brain and a computer. Most research so far studied more accurate BCIs, but much less attention has been paid to the ethics of BCIs. Aside from task-specific information, EEG signals also contain rich private information, e.g., user identity, emotion, disorders, etc., which should be protected. Approach: We show for the first time that adding user-wise perturbations can make identity information in EEG unlearnable. We propose four types of user-wise privacy-preserving perturbations, i.e., random noise, synthetic noise, error minimization noise, and error maximization noise. After adding the proposed perturbations to EEG training data, the user identity information in the data becomes unlearnable, while the BCI task information remains unaffected. Main results: Experiments on six EEG datasets using three neural network classifiers and various traditional machine learning models demonstrated the robustness and practicability of the proposed perturbations. Significance: Our research shows the feasibility of hiding user identity information in EEG data without impacting the primary BCI task information.
Key facts. Cited by 5 papers in the map (data through 14 Oct 2026). Builds on 10 of its 70 references that are in the map. First posted on arXiv 4 Nov 2024.
Builds on
10 of 70 references.
References · 10
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,166
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
- 2016EEGNet: A Compact Convolutional Network for EEG-based Brain-Computer Interfacescited by 628
- 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 193
- 2020Transfer Learning for Motor Imagery Based Brain-Computer Interfaces: A Complete Pipelinecited by 31
- 2019On the Vulnerability of CNN Classifiers in EEG-Based BCIscited by 17
- 2020Tiny noise, big mistakes: Adversarial perturbations induce errors in Brain-Computer Interface spellerscited by 15
- 2017Online and Offline Domain Adaptation for Reducing BCI Calibration Effortcited by 10
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 3.
5 papers.
- 2025Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfacescited by 7
- 2024PAT: Privacy-Preserving Adversarial Transfer for Accurate, Robust and Privacy-Preserving EEG Decodingcited by 3
- 2026SAFE: Secure and Accurate Federated Learning for Privacy-Preserving Brain-Computer Interfacescited by 2
- 2026Synthetic Data Generation for Brain-Computer Interfaces: Overview, Benchmarking, and Future Directionscited by 0
- 2026Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiologycited by 0
- 2026Differentially Private EEG Feature Anonymization: A Privacy-Utility Case Study in Clinical Neurophysiology10 Sep 2026
- 2026Synthetic Data Generation for Brain-Computer Interfaces: Overview, Benchmarking, and Future Directions11 Mar 2026
- 2026SAFE: Secure and Accurate Federated Learning for Privacy-Preserving Brain-Computer Interfaces9 Jan 2026
- 2025Revisiting Euclidean Alignment for Transfer Learning in EEG-Based Brain-Computer Interfaces13 Feb 2025
- 2024PAT: Privacy-Preserving Adversarial Transfer for Accurate, Robust and Privacy-Preserving EEG Decoding16 Dec 2024