Advancing Brainwave-Based Biometrics: A Large-Scale, Multi-Session Evaluation

2025-01-14

arXiv.org

AI Summary

Existing EEG-based biometric authentication studies suffer from limited scalability due to small sample sizes, single-session recordings, and few subjects (<55), raising concerns about generalizability. Method: Leveraging a large-scale, publicly available, five-year multi-session dataset comprising 345 subjects and over 6,000 recordings, we systematically evaluate model robustness, temporal degradation, and lightweight deployment feasibility. We propose a post-login dynamic re-enrollment strategy to counteract performance decay and adopt supervised contrastive learning with deep feature extraction and cosine similarity matching. Contribution/Results: We observe significant temporal degradation—equal error rate (EER) increases by 11.99 percentage points annually—first reported in EEG biometrics. Our method reduces EER by 16.4% over conventional approaches, achieves industrial-grade accuracy (EER <1%) on thousand-subject verification, supports low-channel deployment (≤8 electrodes), and outperforms binary classifiers with unimodal cosine metrics. Code is fully open-sourced.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Computer Vision: Biometrics, Face, Gesture & Pose
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

The field of brainwave-based biometrics has gained attention for its potential to revolutionize user authentication through hands-free interaction, resistance to shoulder surfing, continuous authentication, and revocability. However, current research often relies on single-session or limited-session datasets with fewer than 55 subjects, raising concerns about generalizability and robustness. To address this gap, we conducted a large-scale study using a public brainwave dataset of 345 subjects and over 6,000 sessions (averaging 17 per subject) recorded over five years with three headsets. Our results reveal that deep learning approaches outperform classic feature extraction methods by 16.4% in Equal Error Rates (EER) and comparing features using a simple cosine distance metric outperforms binary classifiers, which require extra negative samples for training. We also observe EER degrades over time (e.g., 7.7% after 1 day to 19.69% after a year). Therefore, it is necessary to reinforce the enrollment set after successful login attempts. Moreover, we demonstrate that fewer brainwave measurement sensors can be used, with an acceptable increase in EER, which is necessary for transitioning from medical-grade to affordable consumer-grade devices. Finally, we compared our findings with prior work on brainwave authentication and industrial biometric standards. While our performance is comparable or superior to prior work through the use of Supervised Contrastive Learning, standards remain unmet. However, we project that achieving industrial standards will be possible by training the feature extractor with at least 1,500 subjects. Moreover, we open-sourced our analysis code to promote further research.

Problem

• Evaluates brainwave biometrics' scalability with large multi-session data
• Addresses performance decline over time in brainwave authentication
• Explores sensor reduction feasibility for consumer-grade devices

Innovation

• Large-scale multi-session brainwave dataset evaluation
• Deep learning outperforms hand-crafted feature methods
• Fewer sensors enable affordable consumer-grade devices