Article

Remarks on BioHash and its mathematical foundation

Authors:
To read the full-text of this research, you can request a copy directly from the authors.

Abstract

The mathematical foundation of BioHash, a technique used to combine tokenized random number and biometrics, is described. BioHash is an ensemble of random projections to preserve the intra-class variations while enhancing the inter-class variations, and thus it is able to achieve zero error rate when the legitimate token is used or when the biometric data is stolen. Its performance reverts to the original state when the legitimate token is stolen and used by the imposter to claim as the legitimate user. The technique offers two possible error outcomes known as false accept rate (FAR) and false reject rate (FRR). The technique acts as a novel form of biometrics, which can solve the non-revocable and privacy invasion issue of the conventional biometrics. The system has been widely deployed in various security systems due to its immutable characteristics.

No full-text available

Request Full-text Paper PDF

To read the full-text of this research,
you can request a copy directly from the authors.

... Teoh et al. [6] proposed BioHash as a scheme of static biometric discretization. They transformed the original biometric feature using a projection matrix before discretization. ...
... This section will briefly examine the information leakage issue under this context. A typical uniform quantization scheme, which utilizes a threshold-based approach, such as 2 N discretization scheme [6] is also considered for comparison with our scheme which utilizes modulo operation. ...
... 12-15, the performance under stolen-token scenario is poorer than those shown in Figs. [6][7][8][9] where the helper data are not compromised. ...
Article
In this paper, a dynamic biometric discretization scheme based on Linnartz and Tuyls’s quantization index modulation scheme (LT-QIM) [Linnartz and Tuyls, 2003] is proposed. LT-QIM extracts one bit per feature element and takes care of the intra-class variation of the biometric features. Nevertheless, LT-QIM does not consider statistical distinctiveness between users, and thus lacks the capability of preserving the discriminative power of the original biometric features. We put forward a generalized LT-QIM scheme in such a way that it allocates multiple bits to each feature element according to a statistical distinctiveness measure of the feature. Hence, more bits are assigned to high distinctive features and fewer bits to low distinctive features. With provision for intra-class variation compensation and dynamic bit allocation by means of the statistical distinctiveness measure, the generalized scheme enhances the verification performance compared to the original scheme. Several comparative studies are conducted on two popular face data sets to justify the efficiency and feasibility of our proposed scheme. The security aspect is also considered by including a stolen-token scenario.
... BioHashing proposed by Teoh et al. is an instance of biometric salting in which a Tokenized (pseudo) Random Number (TRN) is combined with biometric features to generate BioCodes [24]. BioHashing has been experimentally reported to achieve nearly zero Equal Error Rates (ERR) for various modalities [13,24,55]. This substantial increase in performance is due to increase in inter-user variations caused by random projection. ...
... Thus, projection on normally distributed (or Gaussian distributed) random vectors having zero mean and unit variance is a distance preserving mapping with less computation costs. The following papers are suggested to be referred for usage, deeper insights, and mathematical proofs [5,22,55,60]. ...
... It is preprocessed to remove noise and extract region of interest (ROI). Preprocessed sample is subjected to signal level distortions by user-specific Random Projections (RP) [5,55,60]. Let X I is preprocessed image of dimension d × N and R is the user-specific projection matrix of dimension k × d, where k < d/2. Column entries of R are independent random variables with the standard normal distribution having zero mean and unit variance. ...
Article
Full-text available
Wide spread use of biometric based authentication requires security of biometric data against identity thefts. Cancelable biometrics is a recent approach to address the concerns regarding privacy of biometric data, public confidence, and acceptance of biometric systems. This work proposes a template protection approach which generates revocable binary features from phase and magnitude patterns of log-Gabor filters. Multi-level transformations are applied at signal and feature level to distort the biometric data using user specific tokenized variables which are observed to provide better performance and security against information leakage under correlation attacks. A thorough analysis is performed to study the performance, non-invertibility, and changeability of the proposed approach under stolen token scenario on multiple biometric modalities. It is revealed that generated templates are non-invertible, easy to revoke, and also deliver good performance.
... PNN is a kind of radial basis network primarily based on the Bayes–Parzen classification. Besides the input layer, it contains a pattern, summation and output layers [17]. The pattern layer consists of one neuron for each input vector in the training set, while the summation layer contains one neuron for each class to be recognized. ...
... r is the smoothing parameter of the Gaussian kernel and is also the only parameter dependent on the user's choice. In this paper, the value of r is set to 0.1 [17]. ...
Article
In this paper, we propose an innovative touch-less palm print recognition system. This project is motivated by the public’s demand for non-invasive and hygienic biometric technology. For various reasons, users are concerned about touching the biometric scanners. Therefore, we propose to use a low-resolution web camera to capture the user’s hand at a distance for recognition. The users do not need to touch any device for their palm print to be acquired. A novel hand tracking and palm print region of interest (ROI) extraction technique are used to track and capture the user’s palm in real-time video stream. The discriminative palm print features are extracted based on a new method that applies local binary pattern (LBP) texture descriptor on the palm print directional gradient responses. Experiments show promising result using the proposed method. Performance can be further improved when a modified probabilistic neural network (PNN) is used for feature matching. Verification can be performed in less than one second in the proposed system.
... PNN is a kind of radial basis network primarily based on the Bayes-Parzen classification. Besides the input layer, it contains a pattern, summation and output layers (T. Andrew et al., 2006). The pattern layer consists of one neuron for each input vector in the training set, while the summation layer contains one neuron for each class to be recognized. ...
... σ is the smoothing parameter of the Gaussian kernel and is also the only parameter dependent on the user's choice. In this paper, the value of σ is set to 0.1 (T. Andrew et al., 2006). ...
Conference Paper
Full-text available
In this research, we propose an innovative touch-less palm print recognition system. This project is motivated by the public's demand for non-invasive and hygienic biometric technology. For various reasons, users are concerned about touching the biometric scanners. Therefore, we propose to use a low-resolution web camera to capture the user's hand at a distance for recognition. The users do not need to touch any device for their palm print to be extracted for analysis. A novel hand tracking and palm print region of interest (ROI) extraction technique are used to track and capture the user's palm in real time video streams. The discriminative palm print features are extracted based on a new way that applies local binary pattern (LBP) texture descriptor on the palm print directional gradient responses. Experiments show promising result by using the proposed method. Performance can be further improved when a modified probabilistic neural network (PNN) is used for feature matching.
... Threshold-based biometric hashing methods for faces, fingerprints and palmprints, are proposed in [4], [5], [25]. The idea of BioHashing is further developed in [26], [27], which is mainly for multi-factor authentications. In [6], a non-invertible quantization and ECC based method for creating renewable binary face templates is proposed. ...
Article
Full-text available
Secure storage of biometric templates has become an increasingly important issue in biometric authentication systems. We study how secure sketch, a recently proposed error-tolerant cryptographic primitive, can be applied to protect the templates. We identify several practical issues that are not addressed in the existing theoretical framework, and show the subtleties in evaluating the security of practical systems. We propose a general framework to design and analyze a secure sketch for biometric templates, and give a concrete construction for face biometrics as an example. We show that theoretical bounds have their limitations in practical schemes, and the exact security of the system often needs more careful investigations. We further discuss how to use secure sketch in the design of multifactor authentication systems that allow easy revocation of user credentials.
... Theoretical analysis of the BioHashing technique is presented in [72] using random projection theory. However, random projection theory addresses the distance preserving property in the domain of real numbers, and it is not clear how this is preserved in the quantized domain. ...
... It demonstrates zero or nearzero EER when both the biometric features and the random matrix generation key are legitimate. Theoretical analysis of the BioHashing technique is presented in [22] using the RP theory. However, the RP theory addresses the distance-preserving property in the domain of real numbers, and it is not clear how the distance is preserved in the quantized domain. ...
Article
Full-text available
Changeability and privacy protection are important factors for widespread deployment of biometrics-based verification systems. This paper presents a systematic analysis of a random-projection (RP)-based method for addressing these problems. The employed method transforms biometric data using a random matrix with each entry an independent and identically distributed Gaussian random variable. The similarity- and privacy-preserving properties, as well as the changeability of the biometric information in the transformed domain, are analyzed in detail. Specifically, RP on both high-dimensional image vectors and dimensionality-reduced feature vectors is discussed and compared. A vector translation method is proposed to improve the changeability of the generated templates. The feasibility of the introduced solution is well supported by detailed theoretical analyses. Extensive experimentation on a face-based biometric verification problem shows the effectiveness of the proposed method.
... Hence, one cannot employ strong encryption here, which necessarily leads a compromise made between security and the performance. Moreover salting based solutions are usually specific to a biometric trait [7,6]. Kong et al. do a detailed analysis of the current biohashing based approaches [8], and concludes that the zero EER reported is obtained in carefully set experimental conditions and unrealistic under assumptions from a practical view point. ...
Conference Paper
Full-text available
Biometric authentication over public networks leads to a variety of privacy issues that needs to be addressed before it can become popular. The primary concerns are that the biometrics might reveal more information than the identity itself, as well as provide the ability to track users over an extended period of time. In this paper, we propose an authentication protocol that alleviates these concerns. The protocol takes care of user privacy, template protection and trust issues in biometric authentication systems. The protocol uses asymmetric encryption, and captures the advantages of biometric authentication. The protocol provides non-repudiable identity verification, while not revealing any additional information about the user to the server or vice versa. We show that the protocol is secure under various attacks. Experimental results indicate that the overall method is efficient to be used in practical scenarios.
... This leads to a restriction on the possible functions that can be used and in salting, resulting in a compromise made between security and the performance. Some of the popular salting-based approaches are biohashing [8], [13] and salting for face template protection [14]. Moreover, salting-based solutions are usually specific to a biometric trait, and in general do not offer well-defined security. ...
Article
Full-text available
Concerns on widespread use of biometric authentication systems are primarily centered around template security, revocability, and privacy. The use of cryptographic primitives to bolster the authentication process can alleviate some of these concerns as shown by biometric cryptosystems. In this paper, we propose a provably secure and blind biometric authentication protocol, which addresses the concerns of user's privacy, template protection, and trust issues. The protocol is blind in the sense that it reveals only the identity, and no additional information about the user or the biometric to the authenticating server or vice-versa. As the protocol is based on asymmetric encryption of the biometric data, it captures the advantages of biometric authentication as well as the security of public key cryptography. The authentication protocol can run over public networks and provide nonrepudiable identity verification. The encryption also provides template protection, the ability to revoke enrolled templates, and alleviates the concerns on privacy in widespread use of biometrics. The proposed approach makes no restrictive assumptions on the biometric data and is hence applicable to multiple biometrics. Such a protocol has significant advantages over existing biometric cryptosystems, which use a biometric to secure a secret key, which in turn is used for authentication. We analyze the security of the protocol under various attack scenarios. Experimental results on four biometric datasets (face, iris, hand geometry, and fingerprint) show that carrying out the authentication in the encrypted domain does not affect the accuracy, while the encryption key acts as an additional layer of security.
... Since the ECC algorithms only work in binary system with hamming distance. In order to use ECC algorithms, BioHash [25,23,26,32,31] method can be introduced to convert the biometric feature vectors into binary strings. Therefore, BioHash and ECC theory can be combined to enhance key binding to a biometric system. ...
Article
Full-text available
Biometric encryption is the basis for biometric template pro-tection and information security. While existing methods are based on iris or fingerprint modality, face has so far been considered not reliable enough to meet the requirement for error correcting ability. In this paper, we present a novel biometric key binding method based on near infrared (NIR) face biometric. An enhanced BioHash algorithm is developed by imposing an NXOR mask onto the input to the subsequent error cor-recting code (ECC). This way, when combined with ECC and NIR face features, it enables reliable binding of face biometric features and the biometric key. Its ability for template protection and information cryp-tography is guarantied by the theory of encryption. The security level of NIR face recognition system is thereby improved. Experimental results show that the security benefit is gained with a sacrifice of 1-2% drop in the recognition performance.
... The most popular methods of implementing cancelable biometrics involve non-invertible mappings applied to rectangular tessellations of face or fingerprint images [50], salting of biometric features with a secret key [51], and computing quantized random projections of biometric feature vectors [52]. An example of a cancelable transformation applied to a face image, similar to schemes proposed in [50], is shown in Figure 9. ...
Article
Full-text available
BIOMETRICS are an important and widely used class of methods for identity verification and access control. Biometrics are attractive because they are inherent properties of an individual. They need not be remembered like passwords, and are not easily lost or forged like identifying documents. At the same time, bio- metrics are fundamentally noisy and irreplaceable. There are always slight variations among the measurements of a given biometric, and, unlike passwords or identification numbers, biometrics are derived from physical characteristics that cannot easily be changed. The proliferation of biometric usage raises critical privacy and security concerns that, due to the noisy nature of biometrics, cannot be addressed using standard cryptographic methods. In this article we present an overview of "secure biometrics", also referred to as "biometric template protection", an emerging class of methods that address these concerns.
... Différentes améliorations ont été proposées, comme une approche multimodale [18, 19] , l'amélioration de l'extraction des paramètres pour les empreintes digi- tales [22] et quelques variantes [29, 31]. Il a aussi été proposé de combiner cette technique avec des engagements flous basés sur les codes correcteurs [28, 5]. Des études sur la sécurité de la biométrie révocable ont été développées, avec un nouveau formalisme, les métriques correspondantes et de nouveaux critères de sécurité [21, 2]. ...
... The performance is as good as that before transformation by elimination of false accept rates (FAR) without suffering from increased occurrence of false reject rates (FRR). BioHashing technique was presented in [5] using the random projection (RP) theory. The Johnson-Lindenstrauss (JL) [6] result stated that Euclidean distances are retained well in RP. ...
Conference Paper
Full-text available
Biometric template protection is a crucial issue to be addressed for widespread deployment of biometrics-based recognition systems in real life application. Although a number of biometric template protection methods have been reported, it is still a challenging task to devise a scheme to satisfy both security and performance. In this paper, a two-step hybrid approach is proposed to generate a cancelable voiceprint template utilizing the advantages of both Template Transformation and Biometric Cryptosystem. The original voiceprint is transformed with random matrix based on the similarity-preserving of random projection. Chaff points are added to the codebook and matching is also performed in the transformed domain. Random projection improves the cancelability while chaff points conceal the genuine codeword to enhance the security. Binary indexes help identify the genuine codeword accurately. The effectiveness of the proposed method is well supported by detailed analysis. The experimental results demonstrate that the recognition performance is well-kept as the original template does.
... Différentes améliorations ont été proposées, comme une approche multimodale [18,19], l'amélioration de l'extraction des paramètres pour les empreintes digitales [22] et quelques variantes [29,31]. Il a aussi été proposé de combiner cette technique avec des engagements flous basés sur les codes correcteurs [28,5]. ...
Article
Full-text available
Le développement des systèmes biométriques entraîne des nouvelles menaces et vulnérabilités sur la vie privée des personnes. Cet article pré-sente les techniques de biométrie révocable utilisées pour la protection des données et les limites de tels systèmes.
... Binarization, a many to one mapping, helps in achieving irreversibility. Instead of the original biometric, the generated BioCode is stored in the database, and the user specific random data is provided to the enrollee as a token [99,101]. For positive authentication a genuine user needs to provide his/her original biometric data and the token. ...
Article
Full-text available
Wide spread use of biometric based authentication implies the need to secure biometric reference data. Various template protection schemes have been introduced to prevent biometric forgery and identity thefts. Cancelable biometrics and visual cryptography are two recent technologies introduced to address the concerns regarding privacy of biometric data, and to improve public confidence and acceptance of biometric systems. Cancelable biometrics is an important technique that allows generation of revocable biometric templates. As the number of biometric instances are limited and once compromised they are lost forever. Cancelable biometrics allows templates to be cancelled and revoked like passwords innumerable times. Recently, various approaches that utilize visual cryptography to secure the stored template and impart privacy to the central databases have been introduced. This work attempts to summarize the existing approaches in literature making use of these two technologies to protect biometric templates.
... However, Kong, Cheung and Zhang pointed out that the good performance of BioHashing and its variants, including PalmHashing, is based on the assumption that users' tokens have never been stolen [3,4,12], an incident called the worst or stolen-token scenario. Unfortunately, this assumption is not always hold in practice [27]. ...
Article
Full-text available
2DPalmHash Code (2DPHC) was proposed as a cancelable code for secure palmprint verification. In order to relieve the vertical and horizontal dislocation problems, palmprint codes, including 2DPHC, need to be shifted both in horizontal and vertical directions and matched repeatedly, which leads to high computational complexity. However, according to our analysis, horizontal-shift matching can be ignored. Therefore, the multiple-shift matching of 2DPHC can be greatly simplified. Simplified 2DPHC (S2DPHC) has three-fold advantages: (1) reduces matching complexity; (2) enhances changeability performance; (3) improves verification performance. Furthermore, the superiorities of S2DPHC over 2DPHC in terms of changeability and verification performances are validated via rigorously analysis and extensive experimentation.
Conference Paper
Compared with traditional techniques used to establish the identity of a person, biometric systems offer a greater confidence level that the authenticated individual is not impersonated by someone else. However, it is necessary to consider different privacy and security aspects in order to prevent possible thefts and misuses of biometric data. The effective protection of the privacy must encompass different aspects, such as the perceived and real risks pertaining to the users, the specificity of the application, the adoption of correct policies, and data protection methods as well. This chapter focuses on the most important privacy issues related to the use of biometrics, it presents actual guidelines for the implementation of privacy-protective biometric systems, and proposes a discussion of the methods for the protection of biometric data.
Conference Paper
In this work we evaluate the performance of generic local structures as template points for secure fingerprint matching. We present a generic template structure called an n-gon that derives from a set of n neighboring minutiae points. We secure templates consisting of sets of n-gons using the fuzzy vault construct to obfuscate the data. We report the matching performance of our system in terms of the ZeroFAR for comparison with other systems. We also briefly describe a keyed version of our system for comparison with secure systems that utilize a secret user key.
Article
Full-text available
Aiming at the problems of the storage and transmission security of biometric templates, a cancelable template design method based on both random transformation and dynamic projection is proposed by taking into account the vector quantization (VQ)-based speaker recognition algorithm. In the enrollment stage, the LBG (Linde-Buzo-Gray) algorithm is adopted to train the voiceprint characteristics after random transformation, thus obtaining the codebook. Moreover, the codewords in the codebook are dynamically mapped to different random spaces. In the authentication stage, the voiceprint is mapped to the random space of the codewords by means of the same random transformation as that in the enrollment stage, and the verification is then carried out. Theoretical analyses indicate that the random transformation can improve the cancelability of the voiceprint template, and the dynamic projection can increase the uncertainty of the transformation. Simulated results show that the authentication performance of the system remains unchanged before and after the transformation, and that the system EER (Equal Error Ratio) is low when different random matrixes are used to respectively map the codewords and the voiceprint. The cancelability of the proposed method is thus verified.
Article
Biometric bits extraction has emerged as an essential technique for the study of biometric template protection as well as biometric cryptosystems. In this paper, we present a non-invertible but revocable bits extraction technique by means of quantizing the facial data from two feature extractors in the phase domain, which we coin as aligned feature-level fusion phase quantization (AFPQ). In this technique, we utilize helper data to achieve the revocability requirement of bits extraction. The feature averaging and remainder normalization technique are integrated with the helper data to reduce feature variance within the same individual and increase the distinctiveness of bit strings of different individuals to achieve good recognition performance. A scenario in which the system is compromised by an adversary is also considered. As a generic technique, AFPQ can be easily extended to multiple different biometric modalities. KeywordsCancelable biometrics–Feature fusion–Helper data–Phase quantization
Article
The template storage and transmission security are crucial for biometrics-based authentication. Bases on the low storage demand and training cost of VQ-based (Vector-Quantization) voiceprint authentication, a MRP-based (Multispace-Random-Projection) cancelable voiceprint template was proposed in this paper. The performance consistency was investigated by the invariableness of the quantization error. The security of the proposal was clarified by the characteristics of the random matrix and the underdetermined system. The experimental results demonstrated the validity of the proposal.
Article
Biometric authentication systems are primarily centered on template security, revocability, and privacy. The use of cryptographic primitives to enhance the authentication process addressed some of these concerns shown by biometric cryptosystems. The most common computer authentication method is to use alphanumerical usernames and passwords. This method has significant drawbacks. For example, users tend to pick passwords that can be easily guessed. On the other hand, if a password is hard to guess, then it is often hard to remember. In this paper work, we propose a provably secure and blind biometric authentication protocol, which addresses the concerns of user's privacy, template protection, and trust issues.
Conference Paper
Although many biometric characteristics are not secrets, biometric reference data (also known as biometric templates) need to be stored securely and to be protected against unauthorized use. For this purpose, biometric template protection techniques have been developed that do not only prevent privacy leakage and provide confidentiality of the stored biometric templates, but address also problems like identity theft and cross-matching of biometric templates stored in different systems. This paper describes the security and privacy risks associated with storing biometric data and highlights the necessity of using biometric template protection as a potential remedy to these risks. Privacy considerations are discussed with respect to using fingerprint verification for access control to a public outdoor swimming pool.
Conference Paper
Biometric encryption is the basis for biometric template protection and information security. While existing methods are based on iris or fingerprint modality, face has so far been considered not reliable enough to meet the requirement for error correcting ability. In this paper, we present a novel biometric key binding method based on near infrared (NIR) face biometric. An enhanced BioHash algorithm is developed by imposing an NXOR mask onto the input to the subsequent error correcting code (ECC). This way, when combined with ECC and NIR face features, it enables reliable binding of face biometric features and the biometric key. Its ability for template protection and information cryptography is guarantied by the theory of encryption. The security level of NIR face recognition system is thereby improved. Experimental results show that the security benefit is gained with a sacrifice of 1-2% drop in the recognition performance.
Conference Paper
Biohashing algorithms map biometric features randomly onto binary strings with user-specific tokenized random numbers. In order to protect biometric data, these binary strings, the Biohashes, are not allowed to reveal much information about the original biometric features. In the paper we analyse two Biohashing algorithms using scalar randomization and random projection respectively. With scalar randomization, multiple bits can be extracted from a single element in a feature vector. The average information rate of Biohashes is about 0.72. However, Biohashes expose the statistic information about biometric feature, which can be used to estimate the original feature. Using random projection method, a feature vector in n dimensional space can be converted into binary strings with length of m (m
Article
Fingerprint-based authentication systems in general are prone to several security vulnerabilities. Authentication systems such as Biometric crypto systems, Cancellable templates and Bio-hashing provide a solution for addressing these vulnerabilities. But these systems are vulnerable to the unauthorized access resulting from the spoofed fingerprint templates by the fraudulent users. Hence, it is essential to enhance the features of the existing Biometric fingerprint-based authentication systems. An extensive research has been carried out by various researchers on the existing fingerprint authentication system techniques and it is found that none of them are fully capable of eliminating the security vulnerabilities. Fingerprint authentication system technique based on one time fingerprint template provides a solution for this by generating one time template from the fingerprint features. Although this method addresses vulnerability issues to a certain extent, improvements are highly essential particularly in terms of their security and performance. There are several systems based on finger code, where fingerprint features will be converted into finger code using a circular tessellation technique. Although authentication based on this technique improves security, the possibility of compromising the finger code is a huge threat, which needs to be addressed. In this paper, an innovative model is proposed which generates a secure one time finger code during every user authentication. It is generated using finger code obtained from minutiae vectors using a circular tessellation approach, pseudo-random number generators and timestamp, which are generated during every user transaction session. This unique encoding approach makes it extremely difficult for an unauthorized user to decode the generated finger code that is used for a particular authentication session. Thus, the possibility of compromise of original fingerprint can be avoided and thus security of biometric system can be enhanced. The proposed system also provides better performance in terms of its accuracy, processing speed and complexity.
Article
Full-text available
Given the recent explosion of interest in human authentication, verification based on tokenized pseudo-random numbers and the user-specific biometric feature has received much attention. These methods have significant functional advantages over solely biometrics, i.e. zero equal error rate. The main drawback of the methods proposed in the literature relies in exhibiting low performance when an “impostor” B steals the pseudo-random numbers of A and he tries to authenticate as A. In this paper, we show that a multimodal fusion, where only one biometric characteristic is combined with the pseudo-random numbers, permits to obtain a zero equal error rate when nobody steals the pseudo-random numbers, and good performance when an “impostor” B steals the pseudo-random numbers of A and he tries to authenticate as A. In this paper, we study the fusion among the score obtained by a Face Recognizer (where the face features are combined with pseudo-random numbers) and the scores of the systems submitted to FVC2004.
Article
Full-text available
Because biometrics-based authentication offers several advantages over other authentication methods, there has been a significant surge in the use of biometrics for user authentication in recent years. It is important that such biometrics-based authentication systems be designed to withstand attacks when employed in security-critical applications, especially in unattended remote applications such as e-commerce. In this paper we outline the inherent strengths of biometrics-based authentication, identify the weak links in systems employing biometrics-based authentication, and present new solutions for eliminating some of these weak links. Although, for illustration purposes, fingerprint authentication is used throughout, our analysis extends to other biometrics-based methods.
Article
Full-text available
Improvements in protein sequence annotation and an increase in the number of annotated protein databases has fueled development of an increasing number of software tools to predict secreted proteins. Six software programs capable of high throughput and employing a wide range of prediction methods, SignalP 3.0, SignalP 2.0, TargetP 1.01, PrediSi, Phobius, and ProtComp 6.0, are evaluated. Prediction accuracies were evaluated using 372 unbiased, eukaryotic, SwissProt protein sequences. TargetP, SignalP 3.0 maximum S-score and SignalP 3.0 D-score were the most accurate single scores (90-91% accurate). The combination of a positive TargetP prediction, SignalP 2.0 maximum Y-score, and SignalP 3.0 maximum S-score increased accuracy by six percent. Single predictive scores could be highly accurate, but almost all accuracies were slightly less than those reported by program authors. Predictive accuracy could be substantially improved by combining scores from multiple methods into a single composite prediction.
Conference Paper
Full-text available
When the data vectors are high-dimensional it is computationally infeasible to use data analysis or pattern recognition algorithms which repeatedly compute similarities or distances in the original data space. It is therefore necessary to reduce the dimensionality before, for example, clustering the data. If the dimensionality is very high, like in the WEBSOM method which organizes textual document collections on a self-organizing map, then even the commonly used dimensionality reduction methods like the principal component analysis may be too costly. It is demonstrated that the document classification accuracy obtained after the dimensionality has been reduced using a random mapping method will be almost as good as the original accuracy if the final dimensionality is sufficiently large (about 100 out of 6000). In fact, it can be shown that the inner product (similarity) between the mapped vectors follows closely the inner product of the original vectors
Article
We have developed a near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals. The computational approach taken in this system is motivated by both physiology and information theory, as well as by the practical requirements of near-real-time performance and accuracy. Our approach treats the face recognition problem as an intrinsically two-dimensional (2-D) recognition problem rather than requiring recovery of three-dimensional geometry, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as "eigenfaces," because they are the eigenvectors (principal components) of the set of faces; they do not necessarily correspond to features such as eyes, ears, and noses. The projection operation characterizes an individual face by a weighted sum of the eigenface features, and so to recognize a particular face it is necessary only to compare these weights to those of known individuals. Some particular advantages of our approach are that it provides for the ability to learn and later recognize new faces in an unsupervised manner, and that it is easy to implement using a neural network architecture.
Article
The statistical variability that is the basis of iris recognition is analysed in this paper using new large databases. The principle underlying the recognition algorithm is the failure of a test of statistical independence on iris phase structure encoded by multi-scale quadrature wavelets. Combinatorial complexity of this phase information across different persons spans about 249 degrees-of-freedom and generates a discrimination entropy of about over the iris, enabling real-time identification decisions with great enough accuracy to support exhaustive searches through very large databases. This paper presents the results of 9.1 million comparisons among several thousand eye images acquired in trials in Britain, the USA, Japan and Korea.
Conference Paper
Biometric authentication has attracted substantial attention over the past few years. It has been reported recently that a new technique called FaceHashing, which is proposed for personal authentication using face images, has achieved perfect accuracy and zero equal error rates (EER). In this paper, we are going to reveal that the secret of FaceHashing in achieving zero EER is based on a false assumption. This is done through simulating the claimants’ experiments. Thus, we would like to alert the use of “safe” token.
Article
We propose a novel cancelable biometric approach, known as PalmHashing, to solve the non-revocable biometric issue. The proposed method hashes palmprint templates with a set of pseudo-random keys to obtain a unique code called palmhash. The palmhash code can be stored in portable devices such tokens and smartcards for verification. Multiple sets of palmhash codes can be maintained in multiple applications. Thus the privacy and security of the applications can be greatly enhanced. When compromised, revocation can also be achieved via direct replacement of a new set of palmhash code. In addition, PalmHashing offers several advantages over contemporary biometric approaches such as clear separation of the genuine-imposter populations and zero EER occurrences. In this paper, we outline the implementation details of this method and also highlight its potentials in security-critical applications.
Revealing the secret of FaceHashing
  • K.-H Cheung
  • A Kong
  • D Zhang
  • M Kamel
  • J You
K.-H. Cheung, A. Kong, D. Zhang, M. Kamel, J. You, Revealing the secret of FaceHashing, in: ICB 2006, in: Lecture Notes in Comput. Sci, vol. 3832, Springer, Berlin, 2006, pp. 106-112.