Modality For Authentication Research Articles

Privacy-preserving continuous authentication using behavioral biometrics

Continuous authentication modalities collect and utilize users’ sensitive data to authenticate them continuously. Such data contain information about user activities, behaviors, and other demographic information, which causes privacy concerns. In this paper, we propose two privacy-preserving protocols that enable continuous authentication while preventing the disclosure of user-sensitive information to an authentication server. We utilize homomorphic cryptographic primitives that protect the privacy of biometric features with an oblivious transfer protocol that enables privacy-preserving information retrieval. We performed the biometric evaluation of the proposed protocols on two datasets, a swipe gesture dataset and a keystroke dynamics dataset. The biometric evaluation shows that the protocols have very good performance. The execution time of the protocols is measured by considering continuous authentication using: only swipe gestures, keystroke dynamics, and hybrid modalities. The execution time proves the protocols are very efficient, even on high-security levels.

Using ECG Authentication for Biometrics in Smart Cities

All the biometric systems are based on some important features of these modalities which are mainly known for their uniqueness in one way or the other. However, the automatic attendance system using heart biometrics is focused as it is internally unique and focused on internal flexibility of the heart. Heart biometrics include different authentication modalities such as ECG, SCG, PCG and so on. It is primarily focused on authentication using ECG signals which uses algorithms or techniques such as SVM (support vector machine) for authentication purposes and dynamic time warping for signal matching. Algorithms used have shown high accuracy results and the challenges faced were considerable and effectively managed to improve for further advancements.

EyeDrive: A Deep Learning Model for Continuous Driver Authentication

Eye movement (EM) is considerably a new behavioral modality for biometric authentication. In this work, we use this modality in the context of continuous driver authentication. Existing models rely on different modalities that limit their usage or are inconvenient to drivers. We propose an end-to-end learning model that takes the remote eye movement profiles solely and produces embeddings for driver authentication scenarios. The model is based on Long short-term memory (LSTM) and dense networks to learn temporal characteristics from the EM profiles. We focus on low-rate devices because of their affordability. Yet, they present a challenge because of their limited ability to capture quality measurements. To evaluate our model, two low frame-rate devices are used to build our datasets, which are Autocruis and GazePoint. The authentication performance outperforms state-of-the-art with as low as 30 seconds frame length with both devices. The best authentication performances for the identification/verification modes are 92.38/0.76% and 91.05/0.11% for the first and the second datasets, respectively.

Generalized Replay Spoofing Countermeasure Based on Combining Local Subclassification Models

Automatic speaker verification (ASV) systems play a prominent role in the security field due to the usability of voice biometrics compared to alternative biometric authentication modalities. Nevertheless, ASV systems are susceptible to malicious voice spoofing attacks. In response to such threats, countermeasures have been devised to prevent breaches and ensure the safety of user data by categorizing utterances as either genuine or spoofed. In this paper, we propose a new voice spoofing countermeasure that seeks to improve the generalization of supervised learning models. This is accomplished by alleviating the problem of intraclass variance. Specifically, the proposed approach addresses the generalization challenge by splitting the classification problem into a set of local subproblems in order to lessen the supervised learning task. The system outperformed existing state-of-the-art approaches with an EER of 0.097% on the ASVspoof challenge corpora related to replaying spoofing attacks.

A Comprehensive Survey on ECG Signals as New Biometric Modality for Human Authentication: Recent Advances and Future Challenges

Electrocardiogram (ECG) has extremely discriminative characteristics in the biometric field and has recently received significant interest as a promising biometric trait. However, ECG signals are susceptible to several types of noises, such as baseline wander, powerline interference, and high/low-frequency noises, making it challenging to realize biometric identification systems precisely and robustly. Therefore, ECG signal denoising is a major preprocessing step and plays a crucial role in ECG-based biometric human identification. ECG signal analysis for biometric recognition can combine several steps, such as preprocessing, feature extraction, feature selection, feature transformation, and classification which is a very challenging task. Moreover, the employed success measures and appropriate constitution of the ECG signal database also play significant roles in biometric system analysis, considering that publicly available databases are essential by the research community to evaluate the performance of their proposed algorithms. In this survey, we review most of the techniques employed for the ECG as biometrics for human authentication. Firstly, we present an overview and discussion on ECG signal preprocessing, feature extraction, feature selection, and feature transformation for ECG-based biometric systems. Secondly, we present a survey of the available ECG databases to evaluate and compare the acquisition protocol, acquisition hardware, and acquisition resolution (bits) for ECG-based biometric systems. Thirdly, we also present a survey on different techniques, including deep learning methods: deep supervised learning, deep semi-supervised learning, and deep unsupervised learning, for ECG signal classification. Lastly, we present the state-of-art approaches of information fusion in multimodal biometric systems.

ContAuth

User authentication is key in user authorization on smart and personal devices. Over the years, several authentication mechanisms have been proposed: these also include behavioral-based biometrics. However, behavioral-based biometrics suffer from two issues: they are prone to degradation in performance (accuracy) over time (e.g., due to data distribution changes arising from user behavior) and the need to learn the machine learning model from scratch, when adding new users. In this paper, we propose ContAuth, a system that can enhance the robustness of behavioral-based authentication. ContAuth continuously adapts to new incoming data (data incremental learning) and is able to add new users without retraining (class incremental learning). Specifically, ContAuth combines deep learning models with online learning models to achieve learning on the fly, thereby preventing a severe drop in the accuracy between sessions (over time). To add new users, ContAuth employs class incremental learning methods. We evaluate ContAuth on multiple behavior-based user authentication modalities: breathing, gait. and EMG. Our results show that our framework can help True Positive Rate (TPR) to remain high (>85 %) compared to other methods for all the modalities except EMG (>70%) across the sessions while keeping False Positive Rates (FPR) at a minimum (0-10%). It can achieve up to 35% improvement in TPR over a traditional deep learning model. Additionally, iCaRL (an incremental learning method) enables ContAuth to allow the addition of new users by alleviating catastrophic forgetting, to a large extent. Finally, we also show that ContAuth can be deployed efficiently and effectively on device, further providing data privacy.

Raman and IR spectroscopic modality for authentication of turmeric powder

Deliberate chemical contamination of food powders has become a major food safety concern worldwide. This study used Raman imaging and FT-IR spectroscopy to detect Sudan Red and white turmeric adulteration in turmeric powder. While Sudan Red Raman spectral peaks were identifiable in turmeric-Sudan Red samples, Sudan Red false positive detection was observed in binary Raman images, limiting effective quantitative detection. In addition, white turmeric Raman spectral peaks were unidentifiable in turmeric-white turmeric mixtures. However, IR spectra of turmeric-Sudan Red and turmeric-white turmeric samples provided discrete identifier peaks for both the adulterants. Partial least squares regression models were developed using IR spectra for each mixture type. The models estimated Sudan Red and white turmeric concentrations with correlation coefficients of 0.97 and 0.95, respectively. Priority should be given to developing an IR imaging system and incorporating it with Raman system to simultaneously measure of food samples for detection of adulterants.

A Robust Multimodel Biometric Crypto System

Biometric based authentication has several advantages over traditional password or PIN based authentication process because biometric is consists of physical or behavioural characteristics i.e fingerprint, face, Finger Knuckle Print (FKP), iris, voice etc. Unimodal biometric system h as some drawbacks i.e non universality, inter-class variation, intra-class variation; system can be circumvented by the skilled imposter etc. These drawbacks can overcome by multimodal biometric system as it combines more than one modality for authentication. When multimodal system combined with cryptography it makes system more robust and secure. In this paper, a robust multimodal biometric crypto system has been proposed, in which two modalities (FKP and face) are used for authentication of a person and one modality (fingerprint) is used for key generation. AES algorithm with fingerprint based key is used for securing the biometric templates. At authentication time, decision level fusion with AND rule is used for making the final decision. The proposed multimodal biometric crypto system is more robust and secure as compare with other multimodal biometric systems. Experimental results are shown with the help of MATLAB3. 2017b.

Frequency analyses of human voice using fast Fourier transform

Quantitative analysis of human voice has been subject of interest and the subject gained momentum when human voice was identified as a modality for human authentication and identification. The main organ responsible for production of sound is larynx and the structure of larynx along with its physical properties and modes of vibration determine the nature and quality of sound produced. There has been lot of work from the point of view of fundamental frequency of sound and its characteristics. With the introduction of additional applications of human voice interest grew in other characteristics of sound and possibility of extracting useful features from human voice. We conducted a study using Fast Fourier Transform (FFT) technique to analyze human voice to identify different frequencies present in the voice with their relative proportion while pronouncing selected words like numbers. Details of findings are presented

Application of biometric models of authentication in mobile equipment

Today’s mobile devices are the most common investment in the technology industry as it is almost impossible to find a person who does not own a personal phone. Being the weakest point of nearly every user, as the data stored in it is essential, increased phone access security has been achieved by using biometric authentication modalities on these mobile devices. Here, the biometric modules that are most commonly used for authentication and how they are shared, the process of access and the weaknesses of each of these biometric modalities will be elaborated. Also indicate what are the potential attacks and problems that can be encountered in each of the biometric authentication methods on mobile devices.

Electromagnetic radiation based continuous authentication in edge computing enabled internet of things

Abstract With the rapid proliferation of Internet of Things, the centralized cloud faces the performance problems caused by remote network access and real-time services. To ensure good performance, edge computing paradigm emerges, and requires a secure authentication between edge host and cloud server to safeguard resources against any illegitimate access. Securing edge host authentication is an effective method and cornerstone to protect the information security in edge computing. Existing methods most recognize an entity's identity by password only once at the time of initial stage, which may lead to security problem. Continuous authentication as a novel authentication modality has the ability to alleviate this issue. Unlike the authentication operating merely at point-of-entry, a continuous edge host authentication method is proposed on the basis of electromagnetic radiation which reflects the behavioral characteristics of edge host with heterogeneous hardware. We demonstrate the feasibility of the proposed method through analysis of success rate from ten thousand waterfall spectrograms, and experimental results show that the average success rate of 95% has been achieved by support vector machine combining multiple features.

Active authentication using file system decoys and user behavior modeling: results of a large scale study

Data theft is a growing threat to consumers and organizations which existing security safeguards do not sufficiently address. In particular, existing authentication mechanisms are frequently bypassed or circumvented although in situations where attacks are launched by malicious insiders who already possess valid credentials. We propose methods to enhance existing authentication paradigms with continuous active authentication. Our system adds additional levels of security without burdening the user with more credentials to manage. We utilize two complementary authentication modalities to validate user-identity: (1) behavior profiling for user-system interaction, and (2) baiting adversaries using automatically distributed file-decoy tripwires. We present the results from a 160-subject user study used to validate our system. Our results show that the presence of decoy documents on a system does not interfere with normal user activities, and that, with 95% accuracy, our system will detect an intrusion within 15 minutes with at most one false-positive for 40 hours of user activity.

Biometrics: Accessibility challenge or opportunity?

Biometric recognition is currently implemented in several authentication contexts, most recently in mobile devices where it is expected to complement or even replace traditional authentication modalities such as PIN (Personal Identification Number) or passwords. The assumed convenience characteristics of biometrics are transparency, reliability and ease-of-use, however, the question of whether biometric recognition is as intuitive and straightforward to use is open to debate. Can biometric systems make some tasks easier for people with accessibility concerns? To investigate this question, an accessibility evaluation of a mobile app was conducted where test subjects withdraw money from a fictitious ATM (Automated Teller Machine) scenario. The biometric authentication mechanisms used include face, voice, and fingerprint. Furthermore, we employed traditional modalities of PIN and pattern in order to check if biometric recognition is indeed a real improvement. The trial test subjects within this work were people with real-life accessibility concerns. A group of people without accessibility concerns also participated, providing a baseline performance. Experimental results are presented concerning performance, HCI (Human-Computer Interaction) and accessibility, grouped according to category of accessibility concern. Our results reveal links between individual modalities and user category establishing guidelines for future accessible biometric products.

Expression robust 3D face landmarking using thresholded surface normals

3D face recognition is an increasing popular modality for biometric authentication, for example in the iPhoneX. Landmarking plays a significant role in region based face recognition algorithms. The accuracy and consistency of the landmarking will directly determine the effectiveness of feature extraction and hence the overall recognition performance. While surface normals have been shown to provide high performing features for face recognition, their use in landmarking has not been widely explored. To this end, a new 3D facial landmarking algorithm based on thresholded surface normal maps is proposed, which is applicable to widely used 3D face databases. The benefits of employing surface normals are demonstrated for both facial roll and yaw rotation calibration and nasal landmarks localization. Results on the Bosphorus, FRGC and BU-3DFE databases show that the detected landmarks possess high within-class consistency and accuracy under different expressions. For several key landmarks the performance achieved surpasses that of state-of-the-art techniques and is also training free and computationally efficient. The use of surface normals therefore provides a useful representation of the 3D surface and the proposed landmarking algorithm provides an effective approach to localising the key nasal landmarks.

Data selection for i-vector based automatic speaker verification anti-spoofing

State-of-the-art i-vector based automatic speaker verification (ASV) systems lead to considerably high performance and thus voice becomes one of the most important biometric modality for person authentication. However, similar to other biometrics, ASV systems are highly vulnerable to spoofing attacks. Therefore, developing countermeasures for detecting spoofing attacks plays an important role against the concerns regarding the reliability of ASV systems. Recent studies have shown that simple Gaussian mixture model (GMM) classifier outperforms i-vector countermeasures. In this study, we focus on improving the spoofing detection performance of i-vector system using cosine and probabilistic linear discriminant analysis (PLDA) scoring. Experimental results conducted on ASVspoof 2015 database reveals that the data used to train the two key elements of i-vector system, universal background model (UBM) and the i-vector extractor (T-matrix), play an important role on spoofing detection performance. In this paper, we study the effect of using different type of data (genuine/human or spoofed) to train these two elements and their performance on spoofing detection. In particular, extracting i-vectors using UBM trained with genuine (human) speech utterances and T-matrix trained from both genuine and spoofed utterances leads to 50% performance improvement on spoofing detection. With the proposed scheme, unlike the previous results, i-vector countermeasure outperforms GMM classifier. Finally, experimental results shows that recently proposed constant Q cepstral coefficients (CQCC) shows superior performance in comparison to standard Mel-frequency cepstral coefficients (MFCC).

Designing ECG-based physical unclonable function for security of wearable devices.

As a plethora of wearable devices are being introduced, significant concerns exist on the privacy and security of personal data stored on these devices. Expanding on recent works of using electrocardiogram (ECG) as a modality for biometric authentication, in this work, we investigate the possibility of using personal ECG signals as the individually unique source for physical unclonable function (PUF), which eventually can be used as the key for encryption and decryption engines. We present new signal processing and machine learning algorithms that learn and extract maximally different ECG features for different individuals and minimally different ECG features for the same individual over time. Experimental results with a large 741-subject in-house ECG database show that the distributions of the intra-subject (same person) Hamming distance of extracted ECG features and the inter-subject Hamming distance have minimal overlap. 256-b random numbers generated from the ECG features of 648 (out of 741) subjects pass the NIST randomness tests.

A fuzzy decision support system for multifactor authentication

Multifactor authentication (MFA) is a growing trend for the accurate identification of the legitimate users through different modalities such as biometrics, nonbiometric, and cognitive behavior metric. In this paper, we have developed an adaptive MFA that considers the effects of different user devices, media, environments, and the frequency of authentication to detect the legitimate user. For this purpose, initially, we have evaluated the trustworthiness values of all the authentication modalities in different user devices and media using a nonlinear programming problem with probabilistic constraints. Finally, an evolutionary strategy, using fuzzy “IF–THEN” rule and genetic algorithm has been developed for the adaptive selection of authentication modalities. We have done a numerical simulation to prove the effectiveness and efficiency of the proposed method. Moreover, we have developed a prototype client–server-based application and have done a detailed user study to justify its better usability than the existing counterparts.

Pervasive, Dynamic Authentication of Physical Items

Authentication of physical items is an age-old problem. Common approaches include the use of bar codes, QR codes, holograms, and RFID (radio-frequency identification) tags. Traditional RFID tags and bar codes use a public identifier as a means of authenticating. A public identifier, however, is static: it is the same each time when queried and can be easily copied by an adversary. Holograms can also be viewed as public identifiers: a knowledgeable verifier knows all the attributes to inspect visually. It is difficult to make hologram-based authentication pervasive; a casual verifier does not know all the attributes to look for. Further, to achieve pervasive authentication, it is useful for the authentication modality to be easy to integrate with modern electronic devices (e.g., mobile smartphones) and to be easy for non-experts to use.

Toward the design of adaptive selection strategies for multi-factor authentication

Authentication is the fundamental safeguard against any illegitimate access to a computing device and other sensitive online applications. Because of recent security threats, authentication through a single factor is not reliable to provide adequate protection of these devices and applications. Hence, to facilitate continuous protection of computing devices and other critical online services from unauthorized access, multi-factor authentication can provide a viable option. Many authentication mechanisms with varying degrees of accuracy and portability are available for different types of computing devices. As a consequence, several existing and well-known multi-factor authentication strategies have already been utilized to enhance the security of various applications. Keeping this in mind, we developed a framework for authenticating a user efficiently through a subset of available authentication modalities along with their several features (authentication factors) in a time-varying operating environment (devices, media, and surrounding conditions, like light, noise, motion, etc.) on a regular basis. The present work is divided into two parts, namely, a formulation for calculating trustworthy values of different authentication factors and then the development of a novel adaptive strategy for selecting different available authentication factors based on their calculated trustworthy values, performance, selection of devices, media, and surroundings. Here, adaptive strategy ensures the incorporation of the existing environmental conditions on the selection of authentication factors and provides significant diversity in the selection process. Simulation results show the proposed selection approach performs better than other existing and widely used selection strategies, mainly, random and optimal cost selections in different settings of operating environments. The detailed implementation of the proposed multi-factor authentication strategy, along with performance evaluation and user study, has been accomplished to establish its superiority over the existing frameworks.

Screen Fingerprints: A Novel Modality for Active Authentication

The authors propose a new biometric modality, called a screen fingerprint, for active authentication. A screen fingerprint is acquired by taking a screen recording of the computer being used and extracting discriminative visual features from the recording. The authors demonstrate that the screen fingerprint of an operator captures enough unique human qualities to be usable as a biometric for authentication. The also discuss the advantages over other traditional active authentication modalities. This article is part of a special issue on security.