Exploring deep convolutional generative adversarial networks (DCGAN) in biometric systems: a survey study

Abstract

Over the past few years, there has been a proliferation of research in the area of generative adversarial networks (GANs). GANs present a novel approach to producing synthetic data in varying fields including medicine, traffic control, text transferring, image generation, and cybersecurity. To improve the quality of synthetic generation, specifically for images, the GAN technique was paired with convolutional neural networks (CNNs) to build deep convolutional generative adversarial networks (DCGAN). The DCGAN framework is a simple yet stable framework shown to generate quality photorealistic images. There are a number of studies reviewing GANs, providing a comparative analysis of performance, stabilization, and training methods. With respects to the DCGAN architecture, there are literature reviews reporting its usage in forensic sketch to face transformation and fuzzy face recognition. Here, we provide a review detailing the use of the DCGAN framework with biometrics samples for advancements in biometric authentication systems and cybersecurity. As GANs have shown to be a primary tool in generating deepfakes, we explore the use of DCGANs to generating synthetic biometrics that can deceive security systems and serve as quality training data for other machine learning models. The goal of this review is to contribute a concise consolidated review of techniques involving the DCGAN framework and biometric samples for the improvement of biometric recognition systems and to be used as a reference point for future work in cybersecurity.