Fingerprint Generation and Presentation Attack Detection using Deep Neural Networks

Kim, Hakil; Cui, Xuenan; Kim, Man-Gyu; Nguyen, Thi Thuy Nga

doi:10.1109/mipr.2019.00074

Cited by 19 publications

(14 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, Sudiro et al [34] used Artificial Neural Network to address Fingerprint extraction issues while achieving 41% False Acceptance Rate. Kim et al [35] also used a deep neural network to address issues arising from fingerprint collections. Cao and Jain [36] present fingerprint synthesis technique to reduce processing time error of fetching fingerprint images from the database.…”

Section: 1results Of Fingerprint Biometric Authenticationmentioning

confidence: 99%

A survey of biometric approaches of authentication

Yusuf¹,

Marafa²,

Shehu³

et al. 2020

IJACR

View full text Add to dashboard Cite

Information security refers to a means of preventing unauthorized users from access to information. Risk management usually adopts in information security to provide solutions to security challenges by minimizing risks.Risk can be minimized by administrative control and defense mechanisms. Access control can also enforce the user right access and thereby minimizing risks. Authentication is one of the techniques used in access control systems to protect unauthorized access. Many approaches for authentication have been proposed to address security challenges. These approaches have a conflict with the system usability and therefore required the modification of tradition password techniques for better solutions. Information Authentication is the common method used by security experts to verify the users' identities before getting access right into the system. Access controls are enforced for all users, irrespective of categories they belong. Traditional authentication methods [1] were enough to protect the unauthorized access right as many security breaches were reported. Therefore, advanced security methods that are based on human features required.

show abstract

Section: 1results Of Fingerprint Biometric Authenticationmentioning

confidence: 99%

A survey of biometric approaches of authentication

Yusuf¹,

Marafa²,

Shehu³

et al. 2020

IJACR

View full text Add to dashboard Cite

show abstract

“…In their work, two methods are designed based on GAN, with the first one applying evolutionary optimization in the space of latent variables and the second one using gradient-based search. In the work of Kim et al [59], the fingerprints, namely the master minutia set, were generated from a two-stage GAN. The two-stage GAN is composed of two GANs: the first GAN is for generally describing fingerprints, and the second GAN uses the outputs from the first GAN to create fingerprint images.…”

Section: Bioinformatic-based Recognitionmentioning

confidence: 99%

Generative Adversarial Networks

et al. 2021

View full text Add to dashboard Cite

Generative Adversarial Networks (GANs) have promoted a variety of applications in computer vision and natural language processing, among others, due to its generative model’s compelling ability to generate realistic examples plausibly drawn from an existing distribution of samples. GAN not only provides impressive performance on data generation-based tasks but also stimulates fertilization for privacy and security oriented research because of its game theoretic optimization strategy. Unfortunately, there are no comprehensive surveys on GAN in privacy and security, which motivates this survey to summarize systematically. The existing works are classified into proper categories based on privacy and security functions, and this survey conducts a comprehensive analysis of their advantages and drawbacks. Considering that GAN in privacy and security is still at a very initial stage and has imposed unique challenges that are yet to be well addressed, this article also sheds light on some potential privacy and security applications with GAN and elaborates on some future research directions.

show abstract

“…Kim et al [14] proposed a system to generate artificial fingerprints and detect fake fingerprints using deep neural networks. They used different architecture of a generative adversarial network (GAN) to generate the fingerprints.…”

Section: Introductionmentioning

confidence: 99%

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

Sandouka

Bazi

Alajlan

2021

Sensors

View full text Add to dashboard Cite

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.

show abstract

Fingerprint Generation and Presentation Attack Detection using Deep Neural Networks

Cited by 19 publications

References 5 publications

A survey of biometric approaches of authentication

A survey of biometric approaches of authentication

Generative Adversarial Networks

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

Contact Info

Product

Resources

About