Open Access

ARTICLE

Privacy-Preserving Federated Learning for EEG-Based Biometric Recognition in AI-Enabled Epilepsy Detection

Qiuhao Xu^1,2, Chen Wang^1,3,*, Xi Wen¹, Lurong Jiang¹, Wenying Zheng^4,*, Zhengkui Chen¹

1 School of Information Science and Engineering (School of Cyber Science and Technology), The Zhejiang Provincial Key Laboratory of Digital Fashion and Data Governance, and The Zhejiang Provincial International Cooperation Base for Science and Technology on Cloud Computing Security and Data Aggregation, Zhejiang Sci-Tech University, Hangzhou, China
2 Faculty of Data Science, City University of Macau, Macau, China
3 Zhejiang Provincial Innovation Center of Advanced Textile Technology, Shaoxing, China
4 School of Computer Science and Technology (School of Artificial Intelligence), Zhejiang Sci-Tech University, Hangzhou, China

* Corresponding Authors: Chen Wang. Email: ; Wenying Zheng. Email:

(This article belongs to the Special Issue: GenAI/AI in Biometric Recognition: Theoretical Foundations, Applications, and Emerging Challenges)

Computers, Materials & Continua 2026, 88(3), 36 https://doi.org/10.32604/cmc.2026.082310

Received 13 March 2026; Accepted 15 May 2026; Issue published 23 July 2026

Abstract

The convergence of Generative Artificial Intelligence and biometric recognition is reshaping modern healthcare. It enables more adaptive and intelligent human–machine interactions. Epilepsy, a common neurological disorder affecting millions worldwide, relies heavily on electroencephalography (EEG) signals for diagnosis and monitoring. Wearable consumer devices with EEG sensors support continuous physiological data collection. However, transmitting sensitive biometric data to centralized servers introduces serious privacy and security risks. Federated learning (FL) provides a distributed training framework that keeps raw data on local devices. Despite this advantage, existing FL methods remain vulnerable to gradient leakage attacks, where adversaries may infer private biometric information from shared model updates. To address this issue, we propose PFED, a privacy-preserving federated learning protocol that combines randomized group interaction with volunteer-assisted secure aggregation. The proposed method effectively obfuscates gradient information while maintaining model utility. Experiments on the public CHB-MIT EEG dataset show that PFED achieves reliable epilepsy detection performance and strong privacy protection. These results demonstrate its potential for secure AI-enabled biometric healthcare applications in consumer device environments.

---

Keywords

---