Multibiometric Cryptosystems Based on Feature-Level Fusion

Multibiometric Cryptosystems Based on Feature-Level Fusion

ABSTRACT:

Multi-biometric 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 uni-biometric systems. However, multi-biometric 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: 1) practical implementation of the proposed feature-level fusion framework using two well-known biometric cryptosystems, namely, fuzzy vault and fuzzy commitment, and 2) 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 uni-biometric counterparts.

ARCHITECTURE:

EXISTING SYSTEM:

(i) Non-invertibility—given a secure template, it must be computationally difficult to find a biometric feature set that will match with the given template, and

(ii) Revocability— given two secure templates generated from the same biometric data, it must be computationally hard to identify that they are derived from the same data or obtain the original biometric data.

DISADVANTAGES OF EXISTING SYSTEM:

While multi-biometric systems have improved the accuracy and reliability of biometric systems, sufficient attention has not been paid to security of multi-biometric templates. Though a biometric system can be compromised in a number of ways, leakage of biometric template information to unauthorized individuals constitutes a serious security and privacy threat due to the following two reasons:

1) Intrusion attack: If an attacker can hack into a biometric database, he can easily obtain the stored biometric information of a user. This information can be used to gain unauthorized access to the system by either reverse engineering the template to create a physical spoof or replaying the stolen template.

2) Function creep: An adversary can exploit the biometric template information for unintended purposes (e.g., covertly track a user across different applications by cross-matching the templates from the associated databases) leading to violation of user privacy. Security of multi-biometric templates is especially crucial as they contain information regarding multiple traits of the same user.

PROPOSED SYSTEM:

We propose a feature-level fusion framework to simultaneously secure multiple templates of a user using biometric cryptosystems. To demonstrate the viability of this framework, we propose simple algorithms for the following three tasks:

1) Converting different biometric representations into a common representation space using various embedding algorithms: (a) binary strings to point-sets, (b) point-sets to binary strings, and (c) fixed-length real-valued vectors to binary strings.

2) Fusing different features into a single multibiometric template that can be secured using an appropriate biometric cryptosystem such as fuzzy vault and fuzzy commitment; efficient decoding strategies for these biometric cryptosystems are also proposed.

3) Incorporating a minimum matching constraint for each trait, in order to counter the possibility of an attacker gaining illegitimate access to the secure system by simply guessing/knowing only a subset of the biometric traits

ADVANTAGES OF PROPOSED SYSTEM:

ü Compared to uni-biometric systems that rely on a single biometric trait, multi-biometric systems can provide higher recognition accuracy and larger population coverage.

ü Consequently, multi-biometric systems are being widely adopted in many large-scale identification systems.

MODULES:

Fingerprint feature Module

IRIS feature Module

Feature-Level Fusion Module

Secure data forwarding Module

Performance Evaluation Module