biometric-fingerprint-gen.pdf

Node Root

Ogban-Asuquo Ugot

University of Lagos

Chika Yinka-Banjo

Sanjay Misra

Covenant University

root

Manuscript

The availability of biometric data for cybersecurity studies is very important and the Generative Adversarial Network (GAN) provides a means of generating realistic fake biometric data that may mitigate some of the privacy concerns with using real biometric data. This paper trains a Deep Convolutional Generative Adversarial Network (DCGAN) to generate fake biometric fingerprint images. The quality of the generated images is measured using the NFIQ2 algorithm and although the qualitative analysis of the fake fingerprints indicate that the images are of good quality, the NFIQ2 scores obtained for the fake fingerprints are of low utility value. We also explore fingerprint matching by first extracting the minutiae feature points from both the fake generated fingerprint samples and the real fingerprint images using the MINDTCT technique. The minutiae feature points from the fake fingerprint images are then matched (one-to-many) against feature points extracted from real fingerprint images using the BOZORTH3 algorithm. This is done in order to appraise the GANs ability to generate data points with features that generalize beyond the precise domain of the training datasets features. The results from the fingerprint matching show that the fake generated fingerprint samples contain unique fingerprint images.

M Akinyemi

C Yinka-Banjo

Ugot O A Nwachuku

Estimating the Time-Lapse Between Medical Insurance Reimbursement with Non-parametric Regression Models

D H Ackley

G E Hinton

T J Sejnowski

A learning algorithm for Boltzmann machines

B K Beaulieu-Jones

Z S Wu

C Williams

R Lee

S P Bhavnani

J B Byrd

C S Greene

Privacy-preserving generative deep neural networks support clinical data sharing

B Biggio

F Roli

Wild patterns: Ten years after the rise of adversarial machine learning

G K Dziugaite

Roy D M Ghahramani

Training generative neural networks via maximum mean discrepancy optimization

G F Elsayed

S Shankar

B Cheung

N Papernot

A Kurakin

I Goodfellow

J Sohl-Dickstein

Adversarial examples that fool both human and computer vision

NIPS 2016 tutorial: Generative adversarial networks

Y Bengio

A Courville

Deep learning

K Grosse

P Manoharan

M Backes

P Mcdaniel

Adversarial examples for malware detection

J Hayes

L Melis

G Danezis

De Cristofaro

LOGAN: Membership inference attacks against generative models

H I Fawaz

G Forestier

J Weber

L Idoumghar

P A Muller

Deep learning for time series classification: a review

B Hitaj

P Gasti

G Ateniese

F Perez-Cruz

Passgan: A deep learning approach for password guessing

C Huang

P Kairouz

X Chen

L Sankar

R Rajagopal

Generative Adversarial Privacy

W Hu

Y Tan

Generating adversarial malware examples for black-box attacks based on GAN

A Hyvärinen

P Pajunen

Nonlinear independent component analysis: Existence and uniqueness results

S Ioffe

C Szegedy

Batch normalization: Accelerating deep network training by reducing internal covariate shift

H J Kelley

Gradient theory of optimal flight paths

Kim J Y Bu

S J Cho

Zero-day malware detection using transferred generative adversarial networks based on deep autoencoders

D P Kingma

J Ba

Adam: A method for stochastic optimization

T Salimans

M Welling

Improving variational inference with inverse autoregressive flow

J Kros

I Fischer

D Song

Adversarial examples for generative models

C Ledig

L Theis

F Huszar

J Caballero

A P Aitken

A Tejani

J Totz

Z Wang

W Shi

Photo-realistic single image super-resolution using a generative adversarial network

X Lu

Y Zhong

Z Zheng

Y Liu

J Zhao

A Ma

J Yang

Multi-scale and multi-task deep learning framework for automatic road extraction

V Mnih

A P Badia

M Mirza

A Graves

T Lillicrap

T Harley

D Silver

K Kavukcuoglu

Asynchronous methods for deep reinforcement learning

H Mohsen

E S El-Dahshan

E S M El-Horbaty

A B Salem

Classification using deep learning neural networks for brain tumors

D E Rumelhart

Williams R J

Learning representations by back-propagating errors

R J Schalkoff

Artificial neural networks

J Schrittwieser

K Simonyan

I Antonoglou

A Huang

A Guez

T Hubert

L Baker

M Lai

A Bolton

Y Chen

Mastering the game of go without human knowledge

W Zaremba

I Sutskever

J Bruna

D Erhan

R Fergus

Intriguing properties of neural networks

W Tang

S Tan

B Li

J Huang

Automatic steganographic distortion learning using a generative adversarial network

A Triastcyn

B Faltings

Generating Higher-Fidelity Synthetic Datasets with Privacy Guarantees

A Vahdat

J Kautz

Nvae: A deep hierarchical variational autoencoder

H Van Hasselt

Deep Reinforcement Learning with Double Q-Learning

C Voyant

G Notton

S Kalogirou

M L Nivet

C Paoli

F Motte

Machine learning methods for solar radiation forecasting: A review

C Xu

J Ren

D Zhang

Y Zhang

Z Qin

K Ren

GANobfuscator: Mitigating information leakage under GAN via differential privacy

M D Zeiler

Fergus R

Visualizing and understanding convolutional networks

J.-Y Zhu

P Kr¨ahenb¨uhl

E Shechtman

A Efros

Generative visual manipulation on the natural image manifold

D Zügner

A Akbarnejad

S Günnemann

Adversarial attacks on neural networks for graph data

T Karras

S Laine

T Aila

A style-based generator architecture for generative adversarial networks

F Zhang

S Xin

J Feng

Combining global and minutia deep features for partial high-resolution fingerprint matching

Biometric Fingerprint Generation using Generative Adversarial Networks

Biometric Fingerprint Generation using Generative Adversarial Networks

Abstract