Biometric Authentication Research Articles

RegTech innovations streamlining compliance, reducing costs in the financial sector

Regulatory Technology (RegTech) innovations are reshaping the landscape of compliance within the financial sector, presenting opportunities for institutions to enhance efficiency and reduce operational costs. This paper examines the impact of RegTech solutions by focusing on their capacity to streamline compliance processes and mitigate expenses associated with regulatory adherence. Through a qualitative research methodology that includes case studies and expert interviews, the study explores the various dimensions of RegTech applications, ranging from identity verification and risk management to fraud prevention and regulatory reporting. Key findings indicate that RegTech tools leverage advanced technologies such as artificial intelligence, machine learning, and blockchain to automate complex compliance tasks, thereby reducing the need for manual intervention and minimizing human error. These technologies facilitate real-time monitoring and analysis of transactions, which enhances compliance accuracy and operational efficiency. Furthermore, the paper reveals that the adoption of RegTech solutions significantly lowers compliance costs by optimizing resource allocation and reducing the time and labor traditionally required for compliance-related activities. The study concludes that RegTech innovations hold the potential to transform the financial sector's approach to compliance management. By embracing these technologies, financial institutions can not only ensure regulatory compliance more effectively but also achieve considerable cost savings. The paper calls for further research into the long-term impacts of RegTech adoption on the financial industry's regulatory landscape and suggests that regulatory bodies and financial institutions collaborate to foster an environment conducive to RegTech innovation and implementation.

Application to Detect Fake Social Media Profile & Verification Using Block Chain Technology

This paper proposes a novel social media platform that leverages blockchain technology to address the rising concerns of fake profiles and privacy violations. Our system prioritizes robust identity verification through a decentralized approach and immutable user data storage on a blockchain ledger. By eliminating centralized control and single points of failure, the platform enhances trust and security in online interactions. Additionally, we integrate government-issued ID verification (e.g., Aadhaar card) through smart contracts to add an extra layer of trust and strengthen user profiles. This paper details the design, implementation, and functionalities of the proposed system, aiming to showcase its effectiveness in revolutionizing online identity verification within social media applications

Smart Attendance System (Multi-Factor Authentication)

Abstract: The "SMART Attendance System using Facial and OTP Verification" project aims to revolutionize traditional attendance management processes by integrating advanced biometric technologies. In this project, a sophisticated system is developed to automate attendance tracking using facial recognition and OTP verification methods. The system utilizes computer vision algorithms to accurately identify individuals based on their facial features, ensuring reliable attendance recording. Additionally, OTP verification adds an extra layer of security, enhancing the integrity of the system. The project encompasses the design and implementation of the software and hardware components required for seamless operation. Through this innovative solution, organizations can streamline attendance monitoring, improve efficiency, and mitigate identity fraud. The project not only offers a practical application of emerging technologies but also provides valuable insights into biometric authentication systems' development and deployment.

Enhance the Security of ATM Machine Access with Face and Fingerprint Recognition

Abstract: The project introduces an innovative approach to enhance the security and accessibility of Automated Teller Machines (ATMs). In this era where financial transactions are increasingly digital and essential, safeguarding ATM access is of paramount importance. This project leverages the power of biometric authentication, combining fingerprint and face recognition technologies to create a robust and reliable access control system. The proposed system allows ATM users to authenticate their identity with a seamless and secure process. Fingerprint recognition provides a high-precision, individualized identification method, while face recognition adds an additional layer of security, ensuring the users identity matches the stored biometric data. This dual-biometric approach significantly reduces the risk of unauthorized access and fraudulent activities at ATMs. Beyond enhancing security, the project contributes to user convenience by streamlining the authentication process, eliminating the need for traditional ATM cards or PINs. Users can access their accounts swiftly and securely, thereby improving the overall ATM experience. Furthermore, the project’s incorporation of state-of-the-art biometric technologies underscores its potential to set a standard for secure ATM access not only in the financial sector but also in various other domains where access control is critical.

Enhancing Digital Cheque Security: A Machine Learning Approach to Signature Fraud Mitigation

Enhancing Digital Cheque Security: A Machine Learning Approach to Signature Fraud Mitigation

익명표현의 자유에 대한 비판적 고찰

With the introduction of the Internet real-name system and the Constitutional Court ruling in the early 2010s, multiple research has been executed on the Constitutional Court’s ruling. And as a result, research on freedom of expression and freedom of anonymous expression was intensively conducted until the mid-2010s. Since then, however, almost no research has been conducted on freedom of anonymous expression. Considering the development and changes in online media and Social Networking Services since 2010, the issue needs to be revisited. The content and scope of freedom of expression in ancient Greece and even in the 17th century were very different from today. Even John Milton, the author of Areopagitica, thought that the freedom of the Catholics did not need to be guaranteed. Even after Areopagitica, freedom of expression was emphasized as a very important element during the French Revolution in the process of America’s separation from Britain. The issue of anonymity in freedom of expression has been a continuous issue since the 14th century. Regarding freedom of anonymous expression, the Constitutional Court ruled that the Internet real-name system was unconstitutional in 2012, and about the real-name Internet bulletin board system during the election campaign, it ruled that it was constitutional in 2010 and 2015, but changed its position and ruled it unconstitutional in 2021. However, the Constitutional Court ruled that the identity verification system on public institution bulletin boards was constitutional in 2022, making it clear that freedom of anonymous expression cannot be guaranteed indefinitely. When considering the fact that public bulletin boards are a channel through which the general public can convey their opinions in the realm of ‘nation vs. individual,’ such a decision does not seem to be desirable. Today's media environment is very different from the past. The biggest change is that, unlike in the past, individuals produce more information than any other information-producers. However, in the process, anonymity serves as one of the main causes of fake news and hate speech. Considering all the circumstances, the anonymity in freedom of expression should be guaranteed to the maximum extent possible in the ‘individual-to-state’ dimension, but it would be desirable to guarantee it to a relatively weak level in the ‘individual-to-individual’ domain.

Vulnerabilities in One Time Passwords and Protection Method Using Secret Key and Biometric Hash Code

In the present era, conducting financial transactions online is both simple and widely embraced for its convenience. However, engaging in internet-based financial transactions exposes individuals to potential threats like password attacks, malware, phishing, and other illicit activities. Recognizing these risks, many banks have enhanced security measures by incorporating One-Time Password (OTP) authentication alongside traditional login credentials. Despite these improvements, security issues persist in online transactions. To mitigate such concerns, OTPs can be delivered via SMS to the account owner's mobile number. Even with heightened security, internet banking remains susceptible to various attacks, including online phishing, Man-in-the-Middle attacks, SQL injection, and brute force attacks. To address these challenges, this proposed model introduces a Biometric mobile OTP-based transaction authentication method.

A framework for security improvement on usage of mobile money application based on iris biometric authentication method

ABSTRACT Offering transactions through mobile devices has many advantages, such as cashless payments, lower transaction costs, and provide employment opportunities. However, it introduces access security challenges that must be dealt with, which may allow unauthorized access, resulting in theft. This work proposes a framework to improve security on the usage of Mobile Money Services (MMS) by using two-factor authentication (2FA) of PIN and iris biometric authentication method (IRBAM). The rapid application development (RAD) approach was used to develop mobile money applications based on the proposed framework. The proposed framework will improve the security of accessing MMS.

Immutable Identity Validation Using Soul bound Token Abhishek Sharma,

The "Immutable Identity Validation System: A Blockchain and Soulbound Token Approach" paper introduces an innovative method for verifying digital identities. By combining blockchain technology and Soulbound Tokens (SBTs), it enhances security and privacy in identity verification processes. SBTs, designed as non-transferable and tamper-proof digital assets, play a crucial role in bolstering the security and reliability of the system. Their unique properties ensure that user privacy is prioritized while also facilitating swift verification through blockchain transparency. This approach addresses the growing demand for robust identity verification solutions, particularly in sectors like education and corporations, where fraud prevention and streamlined processes are critical. The methodology involves various steps, including SBT generation, blockchain integration, user control mechanisms, and stringent security measures. Both frontend and backend development, along with the integration of blockchain using tools like Ganache and decentralized data storage through IPFS, contribute to building a secure and user-friendly system. Thorough testing, documentation, and knowledge transfer are essential to ensuring the system's reliability, security, and compliance with legal standards. Ultimately, the goal is to establish a globally accepted framework for identity verification in today's interconnected digital landscape. Keywords:; privacy; security; Blockchain; Cryptography; Decentralization; Soul Bound Token (SBT), distributed ledger.

Enhancing Digital Payment Security with Biometric Authentication and AI: A Big Data Approach

The arrival of digital payment technologies has brought unprecedented convenience to businesses and consumers. However, the rapid adoption of digital payments relies on both parties trusting the technology to handle their transactions securely and accurately. Conventional approaches to security issues rely on complex and frequent updates to the software that underpins digital payment systems, as well as cryptographic solutions that are challenging to implement and may, from time to time, require replacement as older systems are hacked. The introduction of biometric data-driven payment security enhances the current security systems, reducing system overheads, and increasing customer confidence in the technology. Our approach is to leverage advances in Artificial Intelligence (AI) systems, driven by the latest developments in big data technology. This novel combination is capable of improving the dynamic three-tier digital payment security model, ultimately reducing both fraud and overheads and increasing trust from both businesses and consumers.

Signature Recognition and Verification Using Machine Learning

This project focuses on the development and implementation of a robust signature recognition and verification system leveraging machine learning techniques. Handwritten signatures serve as essential personal identifiers in numerous applications, such as financial transactions, legal documents, and access control. Traditional methods of signature verification often lack efficiency and accuracy, prompting the need for automated and intelligent systems. The proposed project aims to address this challenge by employing state-of-the-art machine learning algorithms for signature analysis. The project involves the creation of a comprehensive dataset consisting of diverse signature samples. Through the utilization of image processing and deep learning techniques, the system will extract relevant features such as stroke dynamics, pressure, and spatial characteristics from the signatures. The core of the project lies in training a machine learning model on the dataset, enabling it to learn the distinctive patterns inherent in individual signatures. During the verification phase, the developed system will assess the input signature's similarity against the stored templates, providing a confidence score to indicate the level of authenticity. The outcome of this project will be a reliable and efficient signature recognition and verification system that can be applied in real-world scenarios, enhancing security and reducing the risk of fraudulent activities. The project not only contributes to the advancement of biometric authentication systems but also provides valuable insights into the integration of machine learning in document security applications.

Survey on the convergence of learning techniques for precise pattern identification in fingerprint analysis

Fingerprint analysis has been an essential component of forensic science and biometric authentication systems. The precise recognition of fingerprint patterns is critical for solving crimes, confirming identities and assuring the security of numerous applications. In recent years, the convergence of learning approaches, particularly machine learning and deep learning, has played an essential part in improving the accuracy and efficiency of fingerprint pattern recognition. In this paper, we discuss recent advancements in physiological-based biometric multimodalities, with a particular focus on the field of precise pattern identification in fingerprint analysis. Additionally, we assume the task of summarizing and examining a range of physiological-based biometric modalities, encompassing both traditional and deep learning approaches. A detailed review of several biometric measurements across many modalities is presented, encompassing various phases, including preprocessing, feature extraction and classification, which are thoroughly discussed. We provide a comprehensive analysis of the challenges and future developments associated with conventional and deep learning methodologies. The objective is to enable investigators to recognize these problems. A review is conducted to evaluate the standard and deep learning approaches employed in different physiological-based biometric systems. The comparative analysis of this review suggests that more advancement is necessary for the development of a reliable physiological-based approach to enhance and optimize the functionality of the fingerprint system.

How many FIDO protocols are needed? Analysing the technology, security and compliance

To overcome the security vulnerabilities caused by weak passwords, thus bridge the gap between user friendly interfaces and advanced security features, the Fast IDentity Online (FIDO) alliance defined a number of authentication protocols. The existing literature leverages all versions of the FIDO protocols, without indicating the reasons behind the choice of each individual FIDO protocol (i.e., U2F, UAF, FIDO2). Inevitably, the question “which protocol is more suitable per case” becomes significant. To provide an answer to the previous question, this article performs a thorough comparative analysis on the different protocol specifications and their technological and market support, to identify whether any protocol has become obsolete. To reach to a conclusion, the proposed approach (i) explores the existing literature, (ii) analyses the specifications released by the FIDO Alliance, elaborating on the security characteristics, (iii) inspects the technical adoption by the industry and (iv) investigates the compliance of the FIDO with standards, regulations and other identity verification protocols. Our results indicate that FIDO2 is the most widely adopted solution; however, U2F remains supported by numerous web services as a two-factor authentication (2FA) choice, while UAF continues to be utilised in mobile clients seeking to offer the Transaction Confirmation feature.

Enhancing Resilience in Biometric Research: Generation of 3D Synthetic Face Data Using Advanced 3D Character Creation Techniques from High-Fidelity Video Games and Animation.

Biometric authentication plays a vital role in various everyday applications with increasing demands for reliability and security. However, the use of real biometric data for research raises privacy concerns and data scarcity issues. A promising approach using synthetic biometric data to address the resulting unbalanced representation and bias, as well as the limited availability of diverse datasets for the development and evaluation of biometric systems, has emerged. Methods for a parameterized generation of highly realistic synthetic data are emerging and the necessary quality metrics to prove that synthetic data can compare to real data are open research tasks. The generation of 3D synthetic face data using game engines' capabilities of generating varied realistic virtual characters is explored as a possible alternative for generating synthetic face data while maintaining reproducibility and ground truth, as opposed to other creation methods. While synthetic data offer several benefits, including improved resilience against data privacy concerns, the limitations and challenges associated with their usage are addressed. Our work shows concurrent behavior in comparing semi-synthetic data as a digital representation of a real identity with their real datasets. Despite slight asymmetrical performance in comparison with a larger database of real samples, a promising performance in face data authentication is shown, which lays the foundation for further investigations with digital avatars and the creation and analysis of fully synthetic data. Future directions for improving synthetic biometric data generation and their impact on advancing biometrics research are discussed.

Analysis of EEG Signals Between Motor Imaginary Tasks and Rest Condition for Biometric Application

Biometric technology has gained immense popularity as an effective solution for enhancing cybersecurity, specifically in countering financial fraud and security threats. EEG-based authentication is unique among biometric authentication methods due to its unparalleled confidentiality and non-replicability. This study explores the feasibility of using motor imagery tasks and rest conditions for human authentication. Ten physically fit subjects, aged between 20 and 28 years, participated voluntarily in the study. The subjects perform imaginary tasks involving their left and right-hand movement. Each task lasted for two minutes, separated by a one-minute break, and EEG data were collected using the EPOC+ device, which features 14-channel electrodes. The sampling frequency was set at 128 Hz. To extract relevant frequency information, Butterworth bandpass filters were employed to extract the alpha (8-13Hz), beta (14-30Hz), and gamma (30-42Hz) frequency bands. Linear features, such as power spectral density (PSD), were obtained using the Welch Method and the Burg Method, while spectral entropy was used to extract non-linear features. Statistical features mean, median, standard deviation, minimum, and maximum were derived from the PSD, and spectral entropy was used as input for the classifiers. Multiple classifiers, including k-nearest neighbor (KNN), support vector machine (SVM), decision tree and Naive Bayes, were employed for the classification task. The Welch method combined with the support vector machine classifier achieved a higher classification accuracy of 96.83% for the beta waves from channels C3, C4, O1, and O2, corresponding to the frontal and occipital lobes. Interestingly, the rest conditions exhibited a higher classification accuracy of 96.83% compared to the motor-imagery tasks, which achieved 96.04%. The utilization of motor imagery tasks and rest conditions, along with the application of advanced classification techniques, holds promise for the development of robust and reliable biometric systems in cybersecurity.

AI-powered malware detection with Differential Privacy for zero trust security in Internet of Things networks

The widespread usage of Android-powered devices in the Internet of Things (IoT) makes them susceptible to evolving cybersecurity threats. Most healthcare devices in IoT networks, such as smart watches, smart thermometers, biosensors, and more, are powered by the Android operating system, where preserving the privacy of user-sensitive data is of utmost importance. Detecting Android malware is thus vital for protecting sensitive information and ensuring the reliability of IoT networks. This article focuses on AI-enabled Android malware detection for improving zero trust security in IoT networks, which requires Android applications to be verified and authenticated before providing access to network resources. The zero trust security model requires strict identity verification for every entity trying to access resources on a private network, regardless of whether they are inside or outside the network perimeter. Our proposed solution, DP-RFECV-FNN, an innovative approach to Android malware detection that employs Differential Privacy (DP) within a Feedforward Neural Network (FNN) designed for IoT networks under the zero trust model. By integrating DP, we ensure the confidentiality of data during the detection process, setting a new standard for privacy in cybersecurity solutions. By combining the strengths of DP and zero trust security with the powerful learning capacity of the FNN, DP-RFECV-FNN demonstrates the ability to identify both known and novel malware types and achieves higher accuracy while maintaining strict privacy controls compared with recent papers. DP-RFECV-FNN achieves an accuracy ranging from 97.78% to 99.21% while utilizing static features and 93.49% to 94.36% for dynamic features of Android applications to detect whether it is malware or benign. These results are achieved under varying privacy budgets, ranging from ϵ=0.1 to ϵ=1.0. Furthermore, our proposed feature selection pipeline enables us to outperform the state-of-the-art by significantly reducing the number of selected features and training time while improving accuracy. To the best of our knowledge, this is the first work to categorize Android malware based on both static and dynamic features through a privacy-preserving neural network model.

A Blockchain Empowered Smart Home Access Scheme Based on Zero-trust Architecture

The rapid popularity of smart home devices worldwide has brought a lot of convenience to people’s lives and spawned numerous new applications. However, it has also elevated data and privacy security risks in household scenarios to an unprecedented level. In this paper, we propose a device access solution based on a zero-trust network architecture to address the cybersecurity risks in smart home scenarios. The proposed solution utilizes a zero-knowledge identity verification algorithm based on quadratic residues to achieve mutual authentication and authorization between devices and central control without exposing device privacy. To enhance the efficiency of verification and authorization, we introduce an incentive model based on information asymmetric algorithms, distributing a portion of the verification tasks to devices with redundant computing power. By comparing with traditional methods, this solution demonstrates higher security, improved verification efficiency, and optimized allocation of computing resources, all while protecting device privacy.

Biometric ATM Authentication System

As technology progresses, traditional authentication methods like Personal Identification Numbers (PINs) and passwords are becoming more prone to security breaches. To address this issue, biometric-based authentication systems are being seen as a reliable solution to boost security in different areas, such as Automated Teller Machines (ATMs). This study delves into the deployment, advantages, obstacles, and future potential of a biometric-based ATM system. By examining current research, real-life examples, and technological innovations, the aim of this paper is to shed light on the efficiency and viability of biometric authentication in ATM systems. Key Words: Enhanced Security, Authentication, Efficiency, Reliability

Intrinsically Stretchable Organic Photodiodes for Faint Near‐Infrared Light Detection and Extendable Cryptographic Imaging

AbstractSkin‐like optoelectronic devices have progressed in leaps and bounds, permitting considerable applications such as remote medical diagnosis, optical communication, biometric authentication, and 3D vision imaging. However, achieving extendable imaging in such frontier detectors poses a formidable challenge for stretchable electronic materials and remains largely unexplored. Herein, an ultrasensitive intrinsically stretchable organic photodiode is configured by the spatially modularizable‐assembled elastic photoactive film for faint near‐infrared light detection and extendable imaging. The performance metrics of the stretchable organic photodiodes rival that of commercial photodetectors, including high specific detectivity (D*noise) over 1012 Jones at 850 nm, ultralow noise current of 4.1 × 10−15 A Hz−1/2 and high stretchability up to 100%. Furthermore, it is the first time to simultaneously achieve the extendable near‐infrared cryptographic imaging and stable photoplethysmography signal detection based on stretchable photodiodes. These results signify a significant advancement toward enabling practical scenarios for stretchable organic optoelectronics.

Improving user security during a call

The recent development of mobile networks has led to the emergence of new threats and methods of implementing existing ones. Phishing attacks, including robocalls, are causing record losses to both individual users and large corporations. At the same time, existing countermeasures cannot provide protection against such attacks because most existing solutions focus on device authentication, whereas user authentication does not occur during a call. Another problem with mobile networks is that there is no point-to-point encryption, i.e., the speech is encrypted only on the segment from the subscriber to the base station. The subject of study in this article is the process of ensuring user security during a call. The purpose of this study is to develop a model of mutual user authentication and end-to-end data encryption in a mobile network during a call. The main objectives are the protection of users from spoofing and vishing and the proposal of a protection method by implementing mutual authentication of users during a call without storing confidential information on the side of a "trusted third party". Method of secure key exchange and end-to-end encryption during a call in the mobile network was proposed. It prevents the interception of calls by the operator for circuit-switched and packet networks. The methods used are mathematical modelling, ontological approach, and multi-criteria optimization models. Because of this research, an algorithm for mutual authentication of users is proposed by introducing biometric authentication methods and modifying the sequence of messages during a call. The proposed approach can be implemented for CS-call and VoLTE/VoWiFi calls. A call cannot be received without user biometric authentication; such as ear pattern or bone conduction methods. Modified SETUP and CONNECT ACK messages are used to inform the other party about the user verification result. This prevents user spoofing, call masquerading, and robocalls. A combination of the proposed asymmetric encryption, a short authentication string, and hashes of previous calls provides a higher level of confidentiality, integrity, and additional resistance to man-in-the-middle attacks. Conclusions. The scientific novelty of the obtained results is the integration of the above methods into the sequence of call flow messages for providing mutual authentication, end-to-end encryption, and counteraction to the number of network attacks. The proposed methods allow one level to increase the provision of services of privacy and observation groups and can be implemented in the software part of user equipment.