Multibiometric Cryptosystems Based on Feature-Level Fusion

Abstract

Abstract-Multibiometric systems are being increasingly deployed in many large scale biometric applications (e.g., FBI-IAFIS, UIDAI system in India) because they have several advantages such as lower error rates and larger population coverage compared to unibiometric systems. However, multibiometric systems require storage of multiple biometric templates (e.g., fingerprint, iris, and face) for each user, which results in increased risk to user privacy and system security. One method to protect individual templates is to store only the secure sketch generated from the corresponding template using a biometric cryptosystem. This requires storage of multiple sketches. In this paper, we propose a feature level fusion framework to simultaneously protect multiple templates of a user as a single secure sketch. Our main contributions include: (i) practical implementation of the proposed feature level fusion framework using two wellknown biometric cryptosystems, namely, fuzzy vault and fuzzy commitment, and (ii) detailed analysis of the trade-off between matching accuracy and security in the proposed multibiometric cryptosystems based on two different databases (one real and one virtual multimodal database), each containing the three most popular biometric modalities, namely, fingerprint, iris, and face. Experimental results show that both the multibiometric cryptosystems proposed here have higher security and matching performance compared to their unibiometric counterparts.

Dual Fingerprints Fusion for Cryptographic Key Generation

“…Feature-level fusion framework for the design of multibiometric cryptosystems proposed by Abhishek nagar et al [11] that simultaneously protects the multiple templates of a user using a single secure sketch. Fingerprint, face, Iris are taken into account and the functionalities of the modules are Embedding algorithm, fusion module and biometric cryptosystem.…”

Refining Multibiometrics System by Exhausting Multiple feature Extraction

“…Embedding algorithms [1] convert feature representation into common representation. Fuzzy vault encoding and decoding algorithms are used for securing point set based biometric features [1] [7]. Fuzzy commitment encoding and decoding algorithms are used to secure the biometric features in binary vector format [ …”

“…Now days the use of multibiometric system in many large scale applications like in FBI, User ID cards in India is going to be increased. Because they are providing some advantages over unibiometric system like lower error rate, large population coverage, it also given that a certain degree of elasticity for some unusable biometric traits and also face spoofing attack [1].…”

Feature Level Fusion of Multimodal Biometrics and Two Tier Security in ATM System

“…Therefore, researchers, for a long time period, have been investigating ways to use biometric features of the user rather than memorable password or passphrase, in an attempt to produce tough and repeatable cryptographic keys [7]. In the existing approaches the passwords has been replaced by biometrics and it is no longer need to be remembered as it remains as a part of the body.…”