AMB-FHE: Adaptive Multi-biometric Fusion with Fully Homomorphic Encryption

2025-03-31

AI Summary

Addressing the challenge of simultaneously achieving security, usability, and privacy preservation in multi-biometric systems, this paper proposes AMB-FHE: the first multi-modal biometric authentication framework supporting runtime adaptive modality selection under fully homomorphic encryption (FHE). AMB-FHE performs encrypted-domain fusion of iris and fingerprint features—enabling dynamic activation or deactivation of either modality without decryption—thus reconciling strong security guarantees with high usability. We innovatively design an encrypted-domain adaptive fusion mechanism that integrates deep feature extraction with joint template encryption. Evaluated on the CASIA+MCYT multimodal dataset, the framework demonstrates end-to-end privacy protection while achieving synergistic optimization of authentication accuracy and cryptographic security.

Technology Category

• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems

Abstract

Biometric systems strive to balance security and usability. The use of multi-biometric systems combining multiple biometric modalities is usually recommended for high-security applications. However, the presentation of multiple biometric modalities can impair the user-friendliness of the overall system and might not be necessary in all cases. In this work, we present a simple but flexible approach to increase the privacy protection of homomorphically encrypted multi-biometric reference templates while enabling adaptation to security requirements at run-time: An adaptive multi-biometric fusion with fully homomorphic encryption (AMB-FHE). AMB-FHE is benchmarked against a bimodal biometric database consisting of the CASIA iris and MCYT fingerprint datasets using deep neural networks for feature extraction. Our contribution is easy to implement and increases the flexibility of biometric authentication while offering increased privacy protection through joint encryption of templates from multiple modalities.

Problem

• Balancing security and usability in biometric systems
• Enhancing privacy in multi-biometric template encryption
• Adapting biometric fusion to dynamic security needs

Innovation

• Adaptive multi-biometric fusion technique
• Fully homomorphic encryption for privacy
• Deep neural networks feature extraction