Authors: Emna Kalai Zaghouani; Adel Benzina; Rabah Attia
Addresses: SERCom Laboratory, Tunisia Polytechnic School, University of Carthage, Tunis, Tunisia ' LISI Lab INSAT, and Higher School of Documentation ISD, Manouba University, Tunis, Tunisia ' SERCom Laboratory, Tunisia Polytechnic School, University of Carthage, Tunis, Tunisia
Abstract: An electrocardiogram (ECG) biometric system can be wearable and offers continuous authentication. It is suitable for medical applications and has proved its benefits over traditional biometric systems. In this paper, we propose a solution to protect the ECG reference template from eavesdroppers spying the wireless link (between the wearable device and the target application) to preserve the privacy of the ECG reference template. The scheme fulfils the ISO/IEC 24745 biometric template protection requirements. The proposed solution is based on linear prediction coding of the ECG extracted features. We add a specific secret key to enhance unlinkability and renewability of the protected template. We evaluate the authentication performance of the unprotected and the protected system with a large database. Theoretical and empirical evaluations show that the proposed system outstands the fuzzy commitment scheme in terms of algorithmic complexity and energy consumption while preserving the same authentication performances proving its effectiveness, and efficiency.
Keywords: e-health; authentication; electrocardiogram; ECG security and privacy; ISO/IEC 24745; time complexity; energy consumption.
International Journal of Bio-Inspired Computation, 2019 Vol.14 No.3, pp.139 - 150
Received: 01 Feb 2018
Accepted: 21 Nov 2018
Published online: 13 Nov 2019 *