BioEncoding: A Reliable Tokenless Cancelable Biometrics Scheme for Protecting IrisCodes

Abstract

SUMMARYDespite their usability advantages over traditional authentication systems, biometrics-based authentication systems suffer from inherent privacy violation and non-revocability issues. In order to address these issues, the concept of cancelable biometrics was introduced as a means of generating multiple, revocable, and noninvertible identities from true biometric templates. Apart from BioHashing, which is a two-factor cancelable biometrics technique based on mixing a set of tokenized userspecific random numbers with biometric features, cancelable biometrics techniques usually cannot preserve the recognition accuracy achieved using the unprotected biometric systems. However, as the employed token can be lost, shared, or stolen, BioHashing suffers from the same issues associated with token-based authentication systems. In this paper, a reliable tokenless cancelable biometrics scheme, referred to as BioEncoding, for protecting IrisCodes is presented. Unlike BioHashing, BioEncoding can be used as a one-factor authentication scheme that relies only on sole IrisCodes. A unique noninvertible compact bit-string, referred to as BioCode, is randomly derived from a true IrisCode. Rather than the true IrisCode, the derived BioCode can be used efficiently to verify the user identity without degrading the recognition accuracy obtained using original IrisCodes. Additionally, BioEncoding satisfies all the requirements of the cancelable biometrics construct. The performance of BioEncoding is compared with the performance of BioHashing in the stolen-token scenario and the experimental results show the superiority of the proposed method over BioHashing-based techniques.

On the Security of BioEncoding Based Cancelable Biometrics

“…The transformation process of BioEncoding, illustrated in Fig. 1, can be summarized in the following steps [8]:…”

“…Regarding the diversity requirement, it is possible to generate a large number of different BioCodes especially for large address words since 2 2 m different random sequences can be generated using address words of length m. For the non-invertibility requirement, the many-to-one nature of the transformation process can guarantee its irreversibility. In [8], it has been shown that BioEncoding is robust against the brute-force search attacks.…”

“…In BE techniques, such as fuzzy commitment [3], fuzzy extractors [4], and fuzzy vaults [5], biometric templates are linked with a user-specific key to produce a biometrically encrypted pseudo-identity for the user so that the key can be released only if the true biometric template is present on verification. On the other hand, CB methods, such as distorting transforms [6], BioHashing [7], and BioEncoding [8], generate revocable protected templates from true biometric templates through applying different non-invertible transforms to true templates in different applications. Matching is done in the transform domain after applying the same transform (applied in enrollment) to a fresh template during authentication.…”

“…Simoens et al [17] demonstrated how protected templates generated by code-offset [3] and bit-permutation sketches [4] can be linked and reversed. BioEncoding [8] is a recently proposed CB scheme for protecting standard iris codes † [18] that offers several advantages over other CB techniques. It has been shown in [8] that protected templates, referred to as BioCodes, generated from true templates can be used efficiently to verify the user identity without deteriorating the recognition accuracy achieved using original (unprotected) recognition systems.…”

“…BioEncoding [8] is a recently proposed CB scheme for protecting standard iris codes † [18] that offers several advantages over other CB techniques. It has been shown in [8] that protected templates, referred to as BioCodes, generated from true templates can be used efficiently to verify the user identity without deteriorating the recognition accuracy achieved using original (unprotected) recognition systems. Besides, unlike other template protection systems, BioEncoding can be used as a one-factor (tokenless) method.…”