Biometric encryption integrates physiological traits with cryptographic operations to improve authentication security. Retinal vasculature is particularly attractive due to its internal protection, permanence, and high inter-subject variability. we present a revised and rigorously justified multidimensional retinal encryption framework that generates three independent keys—RDDM (Retinal Diagonal Distance Metric), ROTD (Radial Origin-Terminus Distance), and DRID (Diagonal–Radial Intersection Distance)—from a single retinal vessel map. This framework is intended as a biometric-driven key generation and strengthening module to enhance user authentication, rather than a standalone standard encryption algorithm. It operates under a threat model focused on resisting brute-force key guessing in controlled biometric contexts, but not advanced attacks like quantum cryptanalysis or side-channel exploitation. Retinal images undergo preprocessing (CLAHE, vessel segmentation, skeletonization, endpoint detection) to extract stable endpoints. These endpoints produce distance measures that are normalized and combined into polyalphabetic key streams. We provide stepwise derivations of the encryption E(x) and decryption D(y) equations, explicitly justify mod 124 as the symbol table size used in implementation, and include a detailed cryptanalytic evaluation (entropy, NIST SP800-22 randomness tests, Hamming distance, collision analysis, noise sensitivity, and Full-Space Key Guessing (FSKG) calculations). Experimental results on three retinal samples (n_vessels = 27,41,105) show substantially increased FSKG times and near-maximal key entropy relative to single-key baselines. Limitations and sensitivity to image quality are discussed.

The rapid growth of cloud computing has introduced significant benefits in terms of data storage and processing but it has also increased the risks of unauthorized access and data breaches. Therefore, this study presents a biometric-based encryption system which is designed to enhance cloud data security through the integration of facial recognition and homomorphic encryption. The proposed system employs an Autoencoder (AE) for feature extraction, Convolutional Neural Network (CNN) for facial recognition, and the Brakerski-Gentry-Vaikuntanathan (BGV) algorithm for secure data encryption and decryption. The adopted AE is used to efficiently compresses facial features into latent vectors used both for recognition and as encryption keys. Furthermore, the experimental evaluation of the techniques adopted using both primary facial datasets and the LFW dataset demonstrated that the AE achieved a training accuracy of 99.84% and validation accuracy of 98.59%, while the CNN attained a training accuracy of 97.05% and validation accuracy of 95.04%. Additionally, the result of the BGV encryption process recorded an average encryption time of 0.023 seconds and decryption time of 0.019 seconds, indicating minimal computational overhead. Results confirm that the integration of biometric encryption enhances both data confidentiality and authentication reliability in cloud environments. This system provides a robust and efficient framework for securing sensitive data in modern cloud infrastructures, ensuring privacy, integrity, and accessibility for authorized users.

SecureMD5: A new stream cipher for secure file systems and encryption key generation with artificial intelligence

In this paper, we proposed a personalized fingerprint recognition model that could yield a high average accuracy of 95% across many datasets (”FVC2000- FVC2002- FVC2004 datasets”) and surpass all the baseline experiments. The model utilized modern preprocessing techniques, robust feature extraction—orientation, texture, and frequency-based descriptors—and a LightGBM classifier, and a core point identifier, fine-tuned using stratified cross-validation and stratified feature selection. One of the main novel aspects of the work is the generation of secure biometric-based public/private key pairs, coupled with a password specific to the user derived from the extracted fingerprint features. This paradigm adds a dual layer of security by linking biometric authentication directly to cryptographic key material. We conducted exhaustive experiments on the FVC 2000-FVC 2002-FVC 2004 datasets to demonstrate the reliability and versatility of the model across a variety of fingerprint features. The proposed pipeline is an ideal candidate for privacy- preserving biometric-based applications, such as secure access control, identity management, and biometric encryption frame- works.

This paper presents the implementation and evaluation of a Multi-key Multi-modalities Biometric Encryption System designed for business enterprises, leveraging cloud storage for secure and scalable data management.The system integrates multiple biometric modalities fingerprint, iris scan, and face recognition to enhance data security through advanced multi-key encryption techniques, utilizing algorithms such as Advanced Encryption Standard (AES) and Rivest-Shamir-Adleman (RSA).The encrypted biometric data is securely stored in the cloud, providing enterprises with efficient storage solutions.The system's performance was evaluated across several parameters including encryption/decryption time, biometric match accuracy, data transfer speeds, energy consumption, cost, and user satisfaction.The results demonstrate that multi-modal systems offer superior accuracy and security compared to singlemodality systems, reducing error rates and enhancing reliability.However, multi-modal authentication incurs higher costs, energy consumption, and slightly longer processing times.Despite these trade-offs, the system achieved high user satisfaction, particularly in high-security environments where data protection is a priority.The findings indicate that the proposed system is a viable solution for businesses seeking a secure, scalable, and efficient method of protecting sensitive data.

With the rapid development of financial Internet of Things (FIoT) scenarios, protecting the security and privacy of personal biometric data has become particularly important. The study provides a detailed introduction to the proposed algorithm framework, which includes key steps such as the preprocessing of biometric features, feature extraction, feature fusion and encryption. We utilize the powerful capabilities of the convolutional neural network (CNN) in the feature extraction stage to identify and extract key information from biometric features, which are then used to generate encryption keys. Through this method, the research not only improves the accuracy of feature extraction but also enhances the complexity and security of the key. The research also enhanced the algorithm’s ability to resist attacks by integrating multiple cryptographic techniques, such as advanced encryption standards and elliptic curve cryptography (ECC), to defend against potential security threats. The experimental results show that our algorithm significantly improves the security and privacy protection capabilities of the system while maintaining high recognition accuracy. In addition, we also explored future research directions, including exploring more types of biometric features, further optimizing algorithm parameters, and enhancing the algorithm’s resistance to attacks. The biometric encryption algorithm integrating CNN proposed in this paper provides a new security solution for financial IoT scenarios.

Human fingers have fingerprints and mechanoreceptors for biometric information encryption and tactile perception. Ideally, electronic skin (e-skin) integrates identity information and tactile sensing, but this remains challenging. Research on encryption and tactile sensing rarely overlaps. Here, we report using magnetization structures and combinations of magnetic materials to achieve two types of functions: 6n × n invisible secure encryption is achieved through a n × n dipole magnetic array, and multipole magnets are used to achieve decoupling of pressure at various positions and sliding in different directions. The sliding distance ranges from 0 to 2.5 mm, with speeds between 5 and 25 mm/s. This study is based on flexible magnetic films, which have the potential to be used in wearable devices. The magnetic ring and signal detection modules verify the prospects of this fundamental principle in human-computer interaction (HCI) and demonstrate its applications in user identity recognition and tactile interaction.

In the modern digital world, biometric systems are a significant part of personal identification and access control. The use of sensitive biometric data such as iris and facial features raises huge privacy concerns because of the possibilities of data breaches and misuse. Therefore, this project focuses on the enhancement of the security of multimodal biometric systems through encryption mechanisms. The idea is to generate a strong biometric key based on features produced from iris and face biometric systems through advanced machine learning techniques. The features are then employed to produce a strong biometric key capable of encrypting the secret value using the AES algorithm. AES is a widely adopted symmetric encryption algorithm that ensures high efficiency in its software implementation and seamless processing capabilities of image data. This provides not only the reinforcement of authentication but also maintains confidentiality of biometric characteristics and mitigates the risks of privacy attacks and unauthorized access. Thus, this multimodal biometric encryption improves reliability, robustness, and the resistance power of the system against potential attacks, making it a promising step forward in the realm of secure biometric authenticationsystems. Keywords- Biometric encryption,Multimodal biometrics, ,Privacy attacks,Advanced Encryption Standard (AES), Biometric key generation,Iris recognition,Face recognition,Machine learning,Bio-crypto systems, Data security.

Wireless Ad Hoc Networks (WANETs) have attracted considerable attention due to their decentralized nature and flexibility, but they also face critical security challenges. Traditional mechanisms often struggle to cope with the dynamic, distributed, and resource-constrained characteristics of these networks. This review examines the use of fuzzy logic- based techniques to strengthen WANET security frameworks, focusing on their effectiveness in intrusion detection, attack prevention, and network resilience. The literature highlights diverse applications of fuzzy logic, including trusted routing protocols, encryption and decryption of fuzzy matrices, parallel encryption with digit arithmetic of cover text, congestion control and QoS scheduling, multicast key distribution, data division using fuzzy logic and blockchain, malicious node eviction in vehicular ad hoc networks, biometric encryption for IoT, multi-level authentication with fuzzy logic-based quantum key distribution, and fog-based secure IoT architectures. Additional contributions include fuzzy logic applications in random number generation, performance evaluation of encryption algorithms, energy-efficient schemes, multipath routing, web spam detection, data security enhancement, key management, packet-dropping attack detection, and high-speed public-key cryptography. The findings suggest that fuzzy logic enhances WANET security and performance by enabling decision-making under uncertainty, improving attack detection, and optimizing resource utilization. However, challenges such as frequent rekeying, larger key sizes, communication and storage overheads, and network congestion remain, requiring further research for efficient deployment in resource-constrained environments.

The Framework for Privacy-Focused Digital Identity Verification Supporting Financial Inclusion in Africa proposes an integrated, secure, and ethically aligned model for digital identification systems that enhance access to financial services while safeguarding individual privacy. The framework addresses the dual challenge of expanding digital financial inclusion across Africa’s underserved populations and maintaining trust through data protection and regulatory compliance. It emphasizes privacy-preserving technologies such as federated identity management, zero-knowledge proofs, and biometric encryption to authenticate users without disclosing sensitive personal information. By enabling decentralized and consent-based data sharing, the model ensures individuals retain ownership of their digital identities while allowing financial institutions to verify eligibility and compliance with Know Your Customer (KYC) and Anti-Money Laundering (AML) regulations. The framework also integrates blockchain-based audit trails for transparent verification processes and tamper-proof recordkeeping, enhancing institutional accountability. It adopts interoperable standards to link national ID systems, mobile network operators, and fintech platforms, enabling seamless cross-border transactions and inclusive participation in the digital economy. A multilayer governance structure encompassing regulators, financial service providers, and civil society stakeholders promotes ethical oversight and equitable access. Furthermore, the framework supports context-sensitive deployment, accommodating infrastructural disparities and socio-cultural factors unique to African regions. It aligns with global data protection norms such as the General Data Protection Regulation (GDPR) and the African Union Convention on Cyber Security and Personal Data Protection (Malabo Convention), while encouraging local innovation in identity ecosystems. Ultimately, this privacy-centered digital identity verification framework establishes a resilient foundation for secure inclusion, reducing barriers for the unbanked, mitigating identity fraud, and fostering digital trust. By combining privacy engineering, inclusive design, and interoperable governance, it contributes to the broader agenda of sustainable digital transformation and equitable financial empowerment across Africa.

Abstract Whether we realize it or not, our smartphones/tablets store an extremely rich amount of information about ourselves, our daily activities, secrets, preferences, and plans. To talk about professional or purely private matters, we use communicators. For this data, modern technology gives us a sense of security. We are reassured by encryption based on alphanumeric codes. But remembering passwords that are too complex is inconvenient. That’s why we often use biometric security - fingerprint readers or facial recognition. Not only for the unlocking of the device, but also for the effective use of many applications (e.g. mobile banking). But evidence of a crime could be a file, document, photo or conversation stored only on our device. Our crime. If law enforcement demands that we unlock the device, what should we do? Looking at modern legal solutions in this area, the international standard of not incriminating oneself is clear - we cannot be forced to reveal information stored only in memory (e.g. passcode). However, when it comes to whether we are required to place our thumb on a reader or look into a Face id camera, the law is silent or extremely inconsistent. Paradoxically, the technology that makes our data more secure seems to have the opposite effect of diminishing our fundamental rights as potential suspects. The most troubling threads in this area will be addressed in this paper. Where do we stand? What’s next for our fair trial rights?

Biometric authentication methods have become increasingly popular for their ability to offer secure and convenient access control. However, concerns about the privacy and security of biometric data have arisen. In this study, we present a novel approach to address these concerns by proposing a cancellable biometric encryption technique for secure and format-preserving iris authentication. Our method leverages the Quotient Filter data structure to transform encrypted iris templates into cancellable templates while preserving their original format. We carefully select an appropriate format-preserving encryption algorithm for iris templates and design a mapping scheme to achieve cancellability. To assess the effectiveness and performance of our approach, extensive experiments are conducted. The quantitative results indicate the efficiency and efficacy of our cancellable biometric encryption technique using the Quotient Filter. Our innovation, the Iris Authentication for Multiple Cancelled Instances Using a Quotient Filter (IAMCIQF), demonstrates competitive performance across several key metrics. IAMCIQF achieves a high level of security strength and strikes a balance between security and efficiency in terms of key size, encryption and decryption speeds and storage efficiency when compared to other existing techniques. The quantitative outcomes underscore IAMCIQF’s potential as a promising solution for attaining secure and format-preserving iris authentication, addressing critical concerns about biometric data security.

ABSTRACT This paper proposed a noble face recognition and biometric encryption technique for the biometric passport by applying encrypted biometric data encoded into the High-Capacity Color Two-Dimensional (HCC2D) Code to secure the biometric data. The proposed biometric encryption method is attained by applying the Secure Force (SF) algorithm and encoding it into the HCC2D code. The face recognition technology is achieved by combining the Viola-Jones (VJ) algorithm and the Local Binary Patterns (LBP) algorithm to extract the facial features and generate the template. This method will ensure the safety and security of a biometric passport from unauthorized access without knowing the passport holder. The proposed method will provide more security for border crossing and illegal immigrants for national security.

Biometrics effect our live. Security applications employ biometrics. Biometric encryption is growing. Encryption requires biometric key creation. Long, random, and unexpected is the key. Information and communication security research emphasizes long, strong encryption keys. The proposed system uses fingerprint biometrics to generate a long, random biometric encryption key for symmetric encryption. Pre-processing removed noise from donor fingerprint images in the dataset. The program then trains an updateable Tuned VGG-16 convolutional neural network model and tests it on fingerprint images to learn fundamental fingerprint properties. The convolutional neural netwoprk CNN model retains the final weights for the second model to extract encryption key features. Transfer learning built a second convolutional neural network model to retrieve features without relearning. Keeping vector mean for processing. The last step generates an encryption key based on each person's vector of unique biometric features can be used for symmetric encryption algorithms to encrypt personal documents on the personal PC or personal cloud. Our CNN based method uses biometrics to recognize people and create safe and trustworthy encryption keys with over 99% accuracy in testing. Our 98%-accurate deep ANN classifier exceeds the support vector machine and random forest classifiers.

Biometric authentication, leveraging unique physiological or behavioral traits for identity verification, has emerged as a cornerstone of contemporary security systems. However, the increasing sophistication of cyber threats and the potential vulnerabilities of biometric data demand continuous innovation to fortify authentication mechanisms. This research paper delves into the intricate integration of Artificial Intelligence (AI) with biometric encryption systems to elevate authentication robustness to unprecedented levels. The pursuit of enhanced security in biometric authentication systems is motivated by the escalating need to safeguard sensitive personal information from unauthorized access and malicious exploitation. Current biometric systems, though effective, face challenges such as spoofing, replay attacks, and the risk of biometric data compromise. [1]The introduction of AI into this paradigm offers a transformative approach, aiming not only to overcome these challenges but also to adapt and evolve in response to emerging threats. The objectives of this research encompass a comprehensive evaluation of existing biometric authentication systems, the exploration of potential advantages stemming from the infusion of AI, the development of a prototype system exemplifying AI-integrated biometric encryption, and a meticulous assessment of its performance through experimentation and analysis. As the paper concludes, it not only summarizes the key discoveries but also underscores the broader implications for the field of biometric authentication. The fusion of biometric encryption and AI not only fortifies security but also sets the stage for future innovations, shaping the landscape of secure and reliable authentication mechanisms in an increasingly digital world.

When milliards of smart devices are connected to the Internet using the Internet of Things (IoT), robust security methods are required to deliver current information to the objects. Using IoT, the user can be accessed via smart device applications at any time and any place, which challenges IoT security and privacy. From security point of view, users and smart devices should have secure communication channel and digital ID. Authentication is the first step towards any security action. Biometric-based authentication can ensure higher security for developing secure access. In this paper, fingerprint is used as the biometric factor. After scanning the fingerprint using the cellphone’s camera, the image is transmitted to the authentication system. Since the comparison time increases after increasing the database volume, instead of storing the scanned fingerprint image, some key features of the scanned fingerprint are extracted and transmitted to the learning system of the convolutional neural network for detection and authentication and stored in the database. In the user authentication phase, the authentication keys are identified and the passcodes for the user of interest are extracted, and zero code is sent to the forged people; finally, the passcode is examined to check if the user is legal or illegal. In this step, the legal codes for fuzzy encoding of the image and text information are activated, and encryption is carried out in multiple steps depending on the number of members. The final code is compressed using Huffman coding and used for transmission to the network or storage. The proposed method is tested in MATLAB, and the results show that an excellent security is achieved using this cascade encryption method. Conclusively, the proposed hybrid coding technique reduces the information volume by 15.9%.

Biometric encryption, especially based on fingerprint, plays an important role in privacy protection and identity authentication. In this paper, we construct a privacy-preserving linkable ring signature scheme. In our scheme, we utilize a fuzzy symmetric encryption scheme called symmetric keyring encryption (SKE) to hide the secret key and use non-interactive zero-knowledge (NIZK) protocol to ensure that we do not leak any information about the message. Unlike the blind signature, we use NIZK protocol to cancel the interaction between the signer (the prover) and the verifier. The security proof shows that our scheme is secure under the random oracle model. Finally, we implement it on a personal computer and analyze the performance of the constructed scheme in practical terms. Based on the constructed scheme and demo, we give an anonymous cryptocurrency transaction model as well as mobile demonstration.

Abstract India has recently been flooded with smartphones having features of biometric encryption that allows users to encrypt the data on their devices using their biometric features, such as finger impressions or iris patterns. This technology assures users of precluding impermissible intrusions into their private data. However, this idea behind biometric encryption has witnessed critical considerations in the recent past, when Courts of various jurisdictions in the USA were faced with the issue of whether an investigating agency has the power to unlock such smartphones by compelling an accused to depress his fingerprints on the touch ID of the same. The courts have tried to strike a balance between the competing interests of the State and of the accused. While on the one side is the consideration that such power to the investigating agencies are essential for combating crime, on the other, there are the individualistic fundamental rights of the accused. The courts have weighed the prospective impact of giving the investigating agency the said power against an accused’s fundamental rights against self-incrimination, and privacy. This article, after analysing these judgments, endeavours to provide answers to the questions that Indian Courts might face in future concerning search and seizure of smartphones and its implications on the fundamental rights of an accused. This discussion becomes important especially due to the absence of any judicial pronouncements on the issue in India and more so, because even existing pronouncements by the courts in the USA have been quite contradictory.

Privacy preserving biometric authentication using Chaos on remote untrusted server

In symmetric cryptosystems, the protection of secret keys is based on the traditional user authentication and likewise the security of the cryptosystem depends on the secrecy of the secret keys. In the event of lost, theft or infection of these secrete keys; the security of the cryptosystems would be compromised hence exposing critical information. Biometrics has been commercially used to verify user’s identity. Voice biometrics has been proven to be even more effective because it cannot be stolen in some cases like face, fingerprint or even iris biometrics. The research proves that a well-designed system will prompt an authentication question and on verification user must provide both the desired answer as well as desired matching threshold or the system ignores the user features. This research proposes a software-based architecture solution for Biometric Encryption of data using Voice Recognition that employed the Dynamic Time Warping (DTW) technique to solve the problem of speech biometric duration varying with non-linear expansion and contraction. The approach then used database to store the monolithically bind cryptographic key with the equivalent biometric hardened template of the user in such manner that identity of the key will stay hidden unless there is a successful biometric authentication by intended party. The research used the MIT mobile device speaker verification corpus (MDB) and A data set in quiet environment (QDB) for training and verifying session. Finally using the Equal Error Rate (EER) the research evaluated performance or rate at which False Acceptance Rate (FAR) and a False Rejection Rate (FRR) are equal. Therefore, according to the result it offers a better substitute method of user authentication than traditional pre-shared keys for benefit of protecting secret keys.