Producing secure multimodal biometric descriptors using artificial neural networks

Abstract

With the rapidly growing use of biometric authentication systems, the security of these systems and the privacy of users have attracted significant attention in recent years. Multi‐modal biometrics have been able to improve the accuracy of the system but require additional bandwidth to exchange the data. Fragile watermarking has been used to allow the transmission of both biometric templates using the amount of data required to transmit one of them, that is, the cover image, while securing these templates against attacks. Despite the high accuracy of these systems, communicating such templates imposes risks towards the privacy of the users. In this study, a new method is proposed to generate fixed‐size descriptors for the face and fingerprint templates, including the timestamp of the transmission and a unique system identifier. The inclusion of the timestamp enables the system to detect and deny replay attacks, while the unique system identifier maintains the privacy of the users. The experiments conducted to evaluate the proposed method have shown that the proposed method has been able to achieve these features while maintaining high recognition rates, 99.41% and 99.32%, similar to the use of the entire biometric templates in the matching stage.

A Comprehensive Review of Unimodal and Multimodal Fingerprint Biometric Authentication Systems: Fusion, Attacks, and Template Protection

“…Atilla et al developed a system with a fixed-size descriptor, transmission timestamp integration, and a unique system identification number for fingerprints and face templates. The system achieved a recognition rate of 99.41% and incorporated privacy protection and anti-replay features (301). Tomar et al proposed a hybrid approach that combines fingerprints and facial images in a multimodal biometric framework.…”

A protocol to establish trust on biometric authentication devices

“…Some authors, like Atilla et al, proposed a timestamp-based technique to prevent replay attacks in a biometric-based authentication system. 18 The authors have presented a new approach for generating descriptors containing information on a candidate's acquired fingerprint and face templates, the timestamp of managing these templates, and a system identifier (SID). The primary advantages of the proposed technique utilizing the descriptor outlined in this research are the ability to authenticate a candidate with a single similarity measurement between the descriptors generated for the templates collected at the sensors and those stored in the database as the ability to detect replay attacks.…”

“…Some authors, like Atilla et al, proposed a timestamp‐based technique to prevent replay attacks in a biometric‐based authentication system 18 . The authors have presented a new approach for generating descriptors containing information on a candidate's acquired fingerprint and face templates, the timestamp of managing these templates, and a system identifier (SID).…”

“…Furthermore, the biometric‐based access control system is vulnerable to replay attacks. Therefore, some authors, like Atilla et al 18 proposed a timestamp‐based technique to prevent replay attacks in a biometric‐based authentication system. However, the proposed mechanism relies on a timestamp‐based mechanism, which further requires time synchronization between devices and may incur overhead.…”