scholarly journals Transformers and Generative Adversarial Networks for Liveness Detection in Multitarget Fingerprint Sensors

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 699
Author(s):  
Soha B. Sandouka ◽  
Yakoub Bazi ◽  
Naif Alajlan
Keyword(s):  
Attack Detection ◽  
Generative Adversarial Networks ◽  
The Public ◽  
Mobile Payments ◽  
Liveness Detection ◽  
Adversarial Networks ◽  
Biometric Systems ◽  
Financial Transactions ◽  
International Border ◽  
Material Setting

Fingerprint-based biometric systems have grown rapidly as they are used for various applications including mobile payments, international border security, and financial transactions. The widespread nature of these systems renders them vulnerable to presentation attacks. Hence, improving the generalization ability of fingerprint presentation attack detection (PAD) in cross-sensor and cross-material setting is of primary importance. In this work, we propose a solution based on a transformers and generative adversarial networks (GANs). Our aim is to reduce the distribution shift between fingerprint representations coming from multiple target sensors. In the experiments, we validate the proposed methodology on the public LivDet2015 dataset provided by the liveness detection competition. The experimental results show that the proposed architecture yields an increase in average classification accuracy from 68.52% up to 83.12% after adaptation.

scholarly journals Unified Generative Adversarial Networks for Multidomain Fingerprint Presentation Attack Detection

Entropy ◽  
2021 ◽  
Vol 23 (8) ◽  
pp. 1089
Author(s):  
Soha B. Sandouka ◽  
Yakoub Bazi ◽  
Haikel Alhichri ◽  
Naif Alajlan
Keyword(s):  
Attack Detection ◽  
Generative Adversarial Networks ◽  
Generative Adversarial Network ◽  
Source Domain ◽  
The Public ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Biometric Systems ◽  
Security And Reliability ◽  
Presentation Attack Detection

With the rapid growth of fingerprint-based biometric systems, it is essential to ensure the security and reliability of the deployed algorithms. Indeed, the security vulnerability of these systems has been widely recognized. Thus, it is critical to enhance the generalization ability of fingerprint presentation attack detection (PAD) cross-sensor and cross-material settings. In this work, we propose a novel solution for addressing the case of a single source domain (sensor) with large labeled real/fake fingerprint images and multiple target domains (sensors) with only few real images obtained from different sensors. Our aim is to build a model that leverages the limited sample issues in all target domains by transferring knowledge from the source domain. To this end, we train a unified generative adversarial network (UGAN) for multidomain conversion to learn several mappings between all domains. This allows us to generate additional synthetic images for the target domains from the source domain to reduce the distribution shift between fingerprint representations. Then, we train a scale compound network (EfficientNetV2) coupled with multiple head classifiers (one classifier for each domain) using the source domain and the translated images. The outputs of these classifiers are then aggregated using an additional fusion layer with learnable weights. In the experiments, we validate the proposed methodology on the public LivDet2015 dataset. The experimental results show that the proposed method improves the average classification accuracy over twelve classification scenarios from 67.80 to 80.44% after adaptation.

scholarly journals Palmprint False Acceptance Attack with a Generative Adversarial Network (GAN)

2020 ◽  
Vol 10 (23) ◽  
pp. 8547
Author(s):  
Fei Wang ◽  
Lu Leng ◽  
Andrew Beng Jin Teoh ◽  
Jun Chu
Keyword(s):  
Multimedia Systems ◽  
Generative Adversarial Networks ◽  
Clustering Method ◽  
Generative Adversarial Network ◽  
Adversarial Network ◽  
Adversarial Networks ◽  
Biometric Systems ◽  
Biometric Based Authentication ◽  
False Acceptance

Biometric-based authentication is widely deployed on multimedia systems currently; however, biometric systems are vulnerable to image-level attacks for impersonation. Reconstruction attack (RA) and presentation attack (PA) are two typical instances for image-level attacks. In RA, the reconstructed images often have insufficient naturalness due to the presence of remarkable counterfeit appearance, thus their forgeries can be easily detected by machine or human. The PA requires genuine users’ original images, which are difficult to acquire in practice and to counterfeit fake biometric images on spoofing carriers. In this paper, we develop false acceptance attack (FAA) for a palmprint biometric, which overcomes the aforementioned problems of RA and PA. FAA does not require genuine users’ images, and it can be launched simply with the synthetic images with high naturalness, which are generated by the generative adversarial networks. As a case study, we demonstrate the feasibility of FAA against coding-based palmprint biometric systems. To further improve the efficiency of FAA, we employ a clustering method to select diverse fake images in order to enhance the diversity of the fake images used, so the number of attack times is reduced. Our experimental results show the success rate and effectiveness of the FAA.

scholarly journals Fingerprint Presentation Attack Detection using Referential Quality Metrics and Minutiae Count

2021 ◽  
Author(s):  
Akhilesh Verma ◽  
Anshadha Gupta ◽  
Mohammad Akbar ◽  
Arun Kumar Yadav ◽  
Divakar Yadav
Keyword(s):  
Neural Network ◽  
Error Rate ◽  
State Of The Art ◽  
User Authentication ◽  
Attack Detection ◽  
Classification Error ◽  
The Public ◽  
The Past ◽  
Biometric Systems ◽  
Presentation Attack Detection

Abstract The fingerprint presentation attack is still a major challenge in biometric systems due to its increased applications worldwide. In the past, researchers used Fingerprint Presentation Attack Detection (FPAD) for user authentication, but it suffers from reliable authentication due to less focus on reducing the ‘error rate’. In this paper, we proposed an algorithm, based on referential image quality (RIQ)-metrics and minutiae count using neural network, k-NN and SVM for FPAD. We evaluate and validate the error rate reduction with different machine learning models on the public domain, such as LivDet crossmatch dataset2015 and achieved an accuracy of 88% with a neural network, 88.6% with k-NN and 88.8% using SVM. In addition, the average classification error (ACE) score is 0.1197 for ANN, 0.1138 for k-NN and 0.1117 for SVM. Thus, the results obtained show that it was achieved a reasonable accuracy with a low ACE score with respect to other state-of-the-art methods.

scholarly journals On the Effectiveness of Impedance-Based Fingerprint Presentation Attack Detection

Sensors ◽  
2021 ◽  
Vol 21 (17) ◽  
pp. 5686
Author(s):  
Jascha Kolberg ◽  
Daniel Gläsner ◽  
Ralph Breithaupt ◽  
Marta Gomez-Barrero ◽  
Jörg Reinhold ◽  
...  
Keyword(s):  
Thin Film ◽  
Human Skin ◽  
Thin Film Transistor ◽  
Attack Detection ◽  
Biometric Recognition ◽  
The Public ◽  
Biometric Systems ◽  
Bona Fide ◽  
User Friendly ◽  
Presentation Attack Detection

Within the last few decades, the need for subject authentication has grown steadily, and biometric recognition technology has been established as a reliable alternative to passwords and tokens, offering automatic decisions. However, as unsupervised processes, biometric systems are vulnerable to presentation attacks targeting the capture devices, where presentation attack instruments (PAI) instead of bona fide characteristics are presented. Due to the capture devices being exposed to the public, any person could potentially execute such attacks. In this work, a fingerprint capture device based on thin film transistor (TFT) technology has been modified to additionally acquire the impedances of the presented fingers. Since the conductance of human skin differs from artificial PAIs, those impedance values were used to train a presentation attack detection (PAD) algorithm. Based on a dataset comprising 42 different PAI species, the results showed remarkable performance in detecting most attack presentations with an APCER = 2.89% in a user-friendly scenario specified by a BPCER = 0.2%. However, additional experiments utilising unknown attacks revealed a weakness towards particular PAI species.

scholarly journals Colorization of Logo Sketch Based on Conditional Generative Adversarial Networks

Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 497
Author(s):  
Nannan Tian ◽  
Yuan Liu ◽  
Bo Wu ◽  
Xiaofeng Li
Keyword(s):  
Loss Function ◽  
Design Method ◽  
The Self ◽  
Generative Adversarial Networks ◽  
Model Optimization ◽  
Visual Effects ◽  
The Public ◽  
Logo Design ◽  
Adversarial Networks ◽  
Complex Process

Logo design is a complex process for designers and color plays a very important role in logo design. The automatic colorization of logo sketch is of great value and full of challenges. In this paper, we propose a new logo design method based on Conditional Generative Adversarial Networks, which can output multiple colorful logos only by providing one logo sketch. We improve the traditional U-Net structure, adding channel attention and spatial attention in the process of skip-connection. In addition, the generator consists of parallel attention-based U-Net blocks, which can output multiple logo images. During the model optimization process, a style loss function is proposed to improve the color diversity of the logos. We evaluate our method on the self-built edges2logos dataset and the public edges2shoes dataset. Experimental results show that our method can generate more colorful and realistic logo images based on simple sketches. Compared to the classic networks, the logos generated by our network are also superior in visual effects.

Sign in / Sign up

Export Citation Format

Share Document