Aug 2026· PLoS ONE· Vol 21· 0 citations· 34 references
Medicine
TL;DR
The research offers an in-depth analysis of various DP techniques to construct a secure face recognition system employing a Convolutional Neural Network and face classifiers, and concludes that the DP blur with Logistic regression predictors provides the highest privacy, achieving excellent accuracy rates of 97% and 77% for these datasets.
Abstract
Protecting facial recognition privacy is crucial amid deep fake threats, biometric risks, and third-party database access concerns. Despite many recent face recognition methods achieving high accuracy, most existing works either ignore privacy protection or apply privacy mechanisms without designing CNN structures that effectively learn from heavily perturbed facial data. This research introduces a secure face recognition system based on Differential Privacy (DP), employing a Convolutional Neural Network (CNN) and face classifiers. In this study, we develop a CNN through the incorporation of multiple batch normalization layers. This CNN is capable of recognizing the randomized image of the DP technique. To ensure privacy, the face database undergoes perturbation using DP techniques before releasing to any unauthorized access. The CNN model learns from these perturbed images, extracting features that are subsequently used by a predictor to classify the face. The CNN model learns from these images and then this trained CNN extracts features from an image that needs to be recognized. Ultimately, a predictor classifies this face. We evaluate three DP techniques namely Laplacian, Gaussian, and DP-blur using four predictors to evaluate the privacy-preserving capabilities of the proposed method. Each DP technique is evaluated by varying privacy parameters from 0.5 to 8 with an interval of 0.5. This research employs two datasets, namely LFW and IC. The DP blur with Logistic regression predictors provides the highest privacy, achieving excellent accuracy rates of 97% and 77% for these datasets. This outcome surpasses all baseline methods. The research offers an in-depth analysis of various DP techniques to construct a secure face recognition system. The method will aid in the automatic recognition of faces while ensuring privacy.
Biometric authentication is commonly adopted because biometric traits are unique and difficult to copy. Fingerprint recognition, in particular, is widely used in many practical systems, but privacy remains a serious concern. Many existing fingerprint systems store biometric templates in a form that can be misused if leaked. In these situations, attackers may reconstruct or reverse the data, revealing sensitive personal information. Since biometric characteristics cannot be replaced like passwords, any compromise may have long-term consequences. For this reason, privacy-preserving biometric designs are increasingly necessary. This study presents a cancelable fingerprint recognition system that combines Convolutional Neural Networks (CNNs) and Support Vector Regression (SVR). The CNN part of the system is utilized to learn the distinctive features of the fingerprints from the images directly, without the need to define them through manual engineering. The features obtained have a good degree of robustness to typical changes such as rotation, noise, and variability in the acquisition process. These features are further processed through an SVR model, unlike being stored in the form of fingerprint templates, thus preventing the risk of reconstruction attacks. Evaluation was performed on fingerprint images from the FVC2004 database, using image augmentation to simulate variability in pressure, orientation, and illumination conditions. The proposed framework achieved a recognition accuracy of 99.4%, an Equal Error Rate (EER) of 1.0%, and an Area Under the Curve (AUC) of 0.994, demonstrating strong robustness and reliability for privacy-preserving cancelable fingerprint recognition.
K. Gondi, Madhu Shukla· Engineering, Technology &...· 0 citations
Face recognition becomes one of the most adopted biometric technics due to its applications in intelligent surveillance, access control, border security, digital authentication, criminal investigation and human computer interaction. The development of Deep convolutional neural networks (CNNs) significantly improved accuracy of recognition even in unconstrained environments such as pose variations, illumination changes, facial expressions, occlusions and low-resolution images. Conventional CNNs mainly focus on local spatial features and so it has limited ability to preserve hierarchical association between facial components. Capsule Networks (CapsNets) overcome this by representing visual features as vector capsules with existence and geometric properties of objects. The self supervised learning of CapsNets enables feature learning from unlabelled images. This article presents a Self supervised Capsule Network (SS-CapsNet) integrates convolutional feature extraction, capsule based learning, dynamic routing and contrastive self supervised learning into a combined framework for robust face recognition. This approach simultaneously learns discriminative identity from large scale unlabelled dataset while preserves facial geometry. The SS-CapsNet provides improved robustness against pose variations, illumination changes, facial occlusions and image degradation.
K. Minney Prisilla, N. Jayashri· International journal of com...· 0 citations
Face recognition becomes an important biometric implementation in any surveillance, access control, forensic and intelligent security system applications. Despite of technical advances in deep learning models, recognition accuracy normally affected by facial pose, illumination, occlusion, expression, aging factors and limited availability of labelled dataset. These challenges reduce the robustness of face recognition models in real world environments [1][2][3]. Recent researches demonstrated that the super-resolution techniques based on Generative Adversarial Networks (GANs) reconstruct high-quality facial images very effectively from low-resolution input images. It supports to improve feature representation and face recognition [4][5]. Therefore, this research motivated from this advancement and proposes an Adaptive Super-Resolution Generative Adversarial Network (Adaptive SRGAN) for face recognition. It integrates adaptive learning with image super resolution to reconstruct identity preserving high resolution facial images by employing adaptive learning rate optimization, dynamic loss weighting, attention guided feature enhancement and identity preserving loss functions. However, it enhances reconstruction quality by preserving discriminative facial characteristics [6]. The proposed model is expected to achieve higher Peak Signal to Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), recognition accuracy, precision, recall, and F1-score while reducing false acceptance and false rejection rates. Simultaneously, Adaptive SRGAN delivers a robust and scalable solution for improving face recognition systems.
M. Kirubakaran, A. S. Aneeshkumar· International journal of com...· 0 citations
A comparative analysis of existing studies is presented to highlight the evolution of deep learning techniques and their effectiveness in improving recognition accuracy and computational efficiency and emerging research directions are outlined to provide insights for future research.
Patel Bhautika Ronak· International journal of res...· 0 citations
User authentication plays an essential role in security assurance in the present-day digital world. Traditional password-based authentication approaches are increasingly becoming vulnerable to attacks, while single modal biometric systems suffer from challenges such as noise susceptibility, deception, and intra-class variations. This paper proposes a secure and reliable multimodal biometric system using fingerprints, facial characteristics, and irises using Convolutional Neural Network (CNN) to address these weaknesses. In this system, self-learning CNN based representations are utilized for every biometric characteristic, allowing for automatic extraction of distinct deep representations without hand-crafted features. The obtained confidence or attributes across different biometrics are merged to create a combined representation for authentication. Confidence-based classification approach is utilized for authenticating the genuine and impersonator user. Efficiency of the proposed system has been tested using unique assessment criteria including accuracy, recall, true negative rate, false positive rate, precision, and false negative rates. Experimental outcomes demonstrate that the presented CNN-based multimodal biometric system achieves superior accuracy and robustness compared to the conventional single-modal systems and thus it can be used for practical security applications where reliability is required.
Samatha J· Journal of Intelligent Decis...· 0 citations
Finger vein recognition technology has become one of the primary solutions for high-security identification systems. However, traditional finger vein recognition methods face several limitations, such as the risk of permanent identity loss due to biometric data leakage. Through designing cancelable biometrics, users' privacy and security can be further protected, and the risk of biometric data misuse can be reduced. In this paper, we propose Deep Bio-Hashing Network (DBHN) for privacy-preserving finger vein recognition, achieving end-to-end cancelable recognition. Specifically, we design a class center alignment module to improve feature alignment, which aligns the variations of all potential finger views with the finger center view via a learnable transformation. Furthermore, to tackle the security problem caused by stolen tokenized random numbers, a Deep Bio-Hashing layer is proposed, which utilizes a system-level token instead of assigning unique tokens to each user. To supervise the learning process of DBHN, we design a hybrid loss function including classification loss, consistency-based localization loss, and class center triplet loss. Finally, we conduct experiments and analysis on three publicly available datasets. Experimental results show that our method has favorable recognition performance and achieves competitive results compared to state-of-the-art hash-based methods. The analysis verifies the cancelable biometrics attributes and justifies the resilience of the method against existing security and privacy attacks.
Jie Gui, Yifan Wang, Minjing Dong et al.· IEEE Transactions on Image P...· 0 citations