A Dissimilarity-Based Approach for Biometric Fuzzy Vaults–Application to Handwritten Signature Images

Abstract

Abstract. Bio-Cryptographic systems enforce authenticity of cryptographic applications like data encryption and digital signatures. Instead of simple user passwords, biometrics, such as, fingerprint and handwritten signatures, are employed to access the cryptographic secret keys. The Fuzzy Vault scheme (FV) is massively employed to produce biocryptogra-phic systems, as it absorbs variability in biometric signals. However, the FV design problem is not well formulated in the literature, and different approaches are applied for the different biometric traits. In this paper, a generic FV design approach, that could be applied to different biometrics, is introduced. The FV decoding functionality is formulated as a simple classifier that operates in a dissimilarity representation space. A boosting feature selection (BFS) method is employed for optimizing this classifier. Application of the proposed approach to offline signature biometrics confirms its viability. Experimental results on the Brazilian signature database (that includes various forgeries) have shown FV recognition accuracy of 90% and system entropy of about 69-bits.

Review of key‐binding‐based biometric data protection schemes

“…These alterations were not done with respect to a particular trait, but were performed to improve any specific aspect of the vault. The authors in [85, 86] introduced a generic FV design approach based on the theory of classifiers. Not only the authors extended their work in [85] by employing a BFS method for optimising their model, but also tested it in offline handwritten signatures with promising results.…”

“…The authors in [85, 86] introduced a generic FV design approach based on the theory of classifiers. Not only the authors extended their work in [85] by employing a BFS method for optimising their model, but also tested it in offline handwritten signatures with promising results. This work was further extended in [87] by proposing a scheme which dynamically modifies the user key size.…”

Offline signature-based fuzzy vault: A review and new results

“…By this method, it is less likely that an unlocking element equates a chaff element. For or instance, the same entropy (68-bits) could be achieved with a minimal impact on system robustness (AER = 10.52%) [11].…”

Improving Signature-Based Biometric Cryptosystems Using Cascaded Signature Verification-Fuzzy Vault (SV-FV) Approach

“…Moreover, impact of chaff points δ is minimized through generation of chaff points adaptively according to feature expected variability, so it is less likely that a genuine unlocking point matches with a chaff point [15].…”

“…Instead of training classifiers in the FR space, some proximity measure produces an alternative classification space, called a DR space (for a review on application of DR approach to SV, see [14]). Recently, the authors have proposed a dissimilarity-based approach to design FV systems [15]. Error correction capacity of a FV is considered as a threshold in a dissimilarity space by which a FV classifies genuine and impostor samples.…”