Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
126 tokens/sec
GPT-4o
47 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

SEMBA:SEcure multi-biometric authentication (1803.10758v1)

Published 28 Mar 2018 in cs.CR

Abstract: Biometrics security is a dynamic research area spurred by the need to protect personal traits from threats like theft, non-authorised distribution, reuse and so on. A widely investigated solution to such threats consists in processing the biometric signals under encryption, to avoid any leakage of information towards non-authorised parties. In this paper, we propose to leverage on the superior performance of multimodal biometric recognition to improve the efficiency of a biometric-based authentication protocol operating on encrypted data under the malicious security model. In the proposed protocol, authentication relies on both facial and iris biometrics, whose representation accuracy is specifically tailored to trade-off between recognition accuracy and efficiency. From a cryptographic point of view, the protocol relies on SPDZ a new multy-party computation tool designed by Damgaard et al. Experimental results show that the multimodal protocol is faster than corresponding unimodal protocols achieving the same accuracy.

Citations (27)

Summary

  • The paper proposes SEMBA, a secure multi-biometric authentication protocol that uses Secure Multiparty Computation (SMPC) on encrypted face and iris data processed with score-level fusion.
  • SEMBA achieves recognition accuracy comparable to complex unimodal systems while reducing computational complexity, data transmissions, and processing speed, especially in configurations using fewer features.
  • The protocol has practical implications for enhancing secure authentication in resource-constrained environments like mobile devices and theoretical significance for integrating cryptography with biometric systems.

An Overview of "SEMBA: Secure Multi-Biometric Authentication"

In this scholarly examination of SEMBA, a protocol designed for secure multi-biometric authentication, the authors Giulia Droandi, Tommaso Pignata, and Riccardo Lazzeretti advance the field of biometric security through innovative application of multimodal biometric recognition processed on encrypted data using Secure Multiparty Computation (SMPC). Their work targets the need to authenticate individuals with a high degree of security against malicious adversaries, a challenge pertinent in today's digital landscape riddled with cyber threats such as identity theft and unauthorized data access.

SEMBA leverages the SPDZ protocol, a framework allowing the evaluation of arithmetic circuits over encrypted biometrics, to secure such data against active adversaries. A critical aspect of SEMBA is its integration of facial and iris biometric data, each chosen for its unique strengths in authentication processes. These modalities are streamlined to achieve a desirable balance between recognition precision and computational efficiency.

Contributions and Findings

The authors propose a system that harmonizes recognition performance with lowered computational complexity, subverting the complexity barrier that generally arises in processing biometric data in the encrypted domain. This proposal not only matches the accuracy of unimodal systems but does so in a more resource-conserving manner. A notable computational methodology adopted is the use of score-level fusion integrating matching scores derived from facial and iris data. Among the tested configurations, the approach shows a reduction in computational need, achieving better or equal efficiency to standalone iris recognition systems, often considered a benchmark for biometric accuracy.

The experimental results signifiy that SEMBA, through score-level fusion, requires fewer data transmissions and less computational effort without sacrificing security. These efficiencies are highlighted in configurations such as the use of only 1600 iris features coupled with a simple eigenface representation. SEMBA achieves the same error rate in multimodal configurations compared to complex unimodal systems while improving processing speed and authenticity verification rates.

Implications and Future Prospects

The practical implications of SEMBA highlight its potential to enhance secure authentication systems in real-world applications, especially in contexts demanding high security with constrained computational resources, such as mobile devices. Additionally, the research propels the investigation into further refinements of SMPC frameworks capable of handling more biometric modalities or integrating behavioral biometric data.

On a theoretical level, this research financially aligns with the push towards advanced cryptographic tools within biometric systems. By ensuring security even in the face of adversaries actively attempting to subvert the system, SEMBA sets a precedent for protocols seeking universality in their application across diverse and potentially adversarial environments.

The continuation of this research could plausibly incorporate other cryptographic methods more efficient than present protocols or explore fusion at different analytical stages. Such pursuits may result in not only optimized processing overheads but potentially revolutionary enhancements in biometric authentication reliability and security fidelity.

Conclusion

SEMBA demonstrates a significant stride in secure biometric authentication through its adept application of SMPC and multi-modal fusion techniques. Its alignment with the emergent demands for robust, efficient, and secure systems denotes a crucial step forward in both theoretical exploration and practical implementation of advanced biometric security solutions. Future work that builds on these findings might refine scalability and adaptability, supporting the increasingly ubiquitous and diverse applications of biometric authentication technologies.