Face-based Authentication Research Articles

PREVENTION OF RODENT ATTACK ON TERTIARY PACKAGE AT STORAGE LEVEL

This proposes to use some image processing methods as a data normalization method for machine learning. Conventionally, z-score normalization is widely used for pre-processing of data. In the proposed approach, in addition to z-score normalization, a number of histogram-based image processing methods such as histogram equalization are applied to training data and test data as a pre-processing method for machine learning. We evaluate the effectiveness of the proposed approach by using a support vector machine algorithm and a random forest one. In experiments, the proposed scheme is applied to a face-based authentication algorithm with SVM/random forest classifiers to confirm the effectiveness. For SVM classifiers, both z- score normalization and image enhancement work well as a pre-processing method for improving the accuracy. In contrast, for random forest classifiers, a number of image enhancement methods work well, although z- score normalization is unusual for improving the accuracy. The proposed pre-processing method focuses on leveraging histogram analysis to address challenges related to contrast variations, colour distributions, and noise levels in diverse image datasets. The key objectives include the development of an adaptive contrast enhancement algorithm, colour normalization techniques, and strategies for noise reduction.

μPEWFace: Parallel ensemble of weighted deep convolutional neural networks with novel loss functions for face-based authentication

Training Deep Convolutional Neural Networks (DCNN) with large-scale face images takes a significant amount of processing resources and the tuning/optimization time cost for face-based authentication. It must continue to improve its accuracy and speed during the matching phase. In this study, we propose a method, μPEWFace, that inherits not only the benefits of recent DCNNs with adaptive loss functions, such as MagFace, ElasticFace, and AdaFace, for boosting accuracy but also the means to reduce matching time. Consequently, our method expands on the weighted voting mechanism that leverages suboptimal trained models to improve the discriminative capabilities of face-based authentication, as opposed to searching for the best optimal model. In order to boost the efficiency of face-based authentication, we also propose performing the matching phase for each model in parallel. To demonstrate the speed and accuracy of our method, we conduct exhaustive experiments using a variety of well-known benchmarks, including LFW, CFP-FP, AgeDB-30, CALFW, CPLFW, and IJB-B. The experimental findings demonstrate that the proposed method for face-based authentication achieves state-of-the-art results and exhibits remarkable performance.© 2023 Published by Elsevier Ltd.

Face-based Authentication Using Computational Secure Sketch

Biometric features are quite suitable for identity authentication due to its inherent properties – universality, uniqueness and persistence. In fact, biometric authentication has been widely used in our daily life, especially in mobile devices. However, biometric features are quite sensitive, and once a feature is leaked to an evil adversary, it cannot be used in authentication any more. This leads to a push on research of biometric privacy protection. In this paper, we propose a face-based authentication system with the help of a computational secure sketch. The computational secure sketch takes charge of error tolerance on the face samplings. Then the face features of the same user are used to extract an authentication key, which is in turn used to do the identity authentication for the user. The computational security of the computational secure sketch makes sure that the public information obtained by the adversary does not affect the pseudorandomness of the authentication key, hence the privacy of face features is guaranteed. Moreover, the privacy protection technique in our face-based authentication system can be extended to other biometric-based authentication.

Deteksi Spoofing Wajah Menggunakan Faster R-CNN dengan Arsitektur Resnet50 pada Video

Deteksi wajah merupakan proses mendasar dan penting dalam bidang pengenalan wajah yang sudah diteliti secara luas. Tujuan deteksi wajah adalah menentukan keberadaan dan menandai posisi wajah, baik pada gambar maupun video, yang disebut dengan bounding box. Salah satu masalah penting dalam deteksi wajah adalah membedakan wajah spoof dan non-spoof yang disebut sebagai deteksi spoofing wajah. Deteksi spoofing wajah merupakan pekerjaan penting yang digunakan untuk menjamin keamanan otentikasi berbasis wajah dan sistem analisis wajah. Oleh karena itu, dibutuhkan sebuah model yang dapat mendeteksi spoofing wajah. Pada makalah ini dilakukan proses membangun model yang dapat digunakan untuk mendeteksi wajah spoof dan non-spoof pada video menggunakan algoritme Faster R-CNN dengan arsitektur Resnet50. Faster R-CNN merupakan salah satu algoritme yang unggul dalam menyelesaikan berbagai persoalan deteksi objek. Dataset yang digunakan adalah Replay-Attack Database yang disediakan oleh Idiap Dataset Distribution Portal. Pada tahap training digunakan 360 video spoof dan non-spoof. Rata-rata nilai akurasi yang dihasilkan pada tahap training adalah 97,07%, dengan jumlah epoch sebanyak 21. Hasil pengujian menunjukkan bahwa model yang dihasilkan berhasil menentukan bounding box dengan akurat dan mendeteksi spoof dan non-spoof wajah pada video dengan efektif.

Adversarial examples for replay attacks against CNN-based face recognition with anti-spoofing capability

In the race of arms between attackers, trying to build more and more realistic face replay attacks, and defenders, deploying spoof detection modules with ever-increasing capabilities, CNN-based methods have shown outstanding detection performance thus raising the bar for the construction of realistic replay attacks against face-based authentication systems. Rather than trying to rebroadcast even more realistic faces, we show that attackers can successfully fool a face authentication system equipped with a deep learning spoof detection module, by exploiting the vulnerabilities of CNNs to adversarial perturbations. We first show that mounting such an attack is not a trivial task due to the unique features of spoofing detection modules. Then, we propose a method to craft adversarial images that can be successfully exploited to build an effective replay attack. Experiments conducted on the REPLAY-MOBILE database demonstrate that our attacked images achieve good performance against a face recognition system equipped with CNN-based anti-spoofing, in that they are able to pass the face detection, spoof detection and face recognition modules of the authentication chain.

Privacy-Preserving Support Vector Machine Computing Using Random Unitary Transformation

A privacy-preserving support vector machine (SVM) computing scheme is proposed in this paper. Cloud computing has been spreading in many fields. However, the cloud computing has some serious issues for end users, such as the unauthorized use of cloud services, data leaks, and privacy being compromised. Accordingly, we consider privacy-preserving SVM computing. We focus on protecting visual \red{information} of images by using a random unitary transformation. Some properties of the protected images are discussed. The proposed scheme enables us not only to protect images, but also to have the same performance as that of unprotected images even when using typical kernel functions such as the linear kernel, radial basis function(RBF) kernel and polynomial kernel. Moreover, it can be directly carried out by using well-known SVM algorithms, without preparing any algorithms specialized for secure SVM computing. In an experiment, the proposed scheme is applied to a face-based authentication algorithm with SVM classifiers to confirm the effectiveness.

Visual Search in Authentication Systems Based on Memorized Faces: Effects of Memory Load and Retention Interval

Authentication systems based on a graphical login scheme employing face images have been discussed as a potential alternative to passwords. Typically, users are asked to memorize several faces that, during login, need to be recognized among distractor faces. In the present study, we analyzed the impact of memory load (4, 6, 8 to-be-remembered faces) and retention interval (hour, day, week, month) on performance in 72 participants. We found no evidence for strong performance decrements when memory load increased. Longer retention intervals yielded a slight increase of login failures, but post hoc analyses indicated that this was mainly due to worse performance of few individuals in the upper part of our age distribution. Display search times increased with longer retention interval, probably reflecting decay or retrieval problems in long-term memory. Users utilized global scanning strategies within the search arrays. Implications for face-based authentication system design are discussed.