Generalizing a Secure Framework for Domain Transfer Network for Face Anti-spoofing

Abstract

An essential field in cyber-security is the technology behind the authentication of users. In the contemporary era, alphanumeric passwords have been the primary tool used. A password is easy to understand but theoretically complex to brute force and is very easy to store in large databases since, in essence, they are an array of characters. In practical use, however, passwords tend to be very ineffective as the attributes that make for “strong†passwords are generally really abstract and random. However, human memories tend to remember constructed language, which can be intelligently guessed with sufficient information regarding the person. A widely accepted remedy to this problem is to replace passwords with face recognition software which involves minimal effort for the user and, though not completely immune, is quite challenging to misuse. Misuse is often done by spoofing faces. Spoofing faces means presenting a 2D or even a 3D copy of a face to the camera, pretending it is the real face. Many discovered spoofing methods are taken into consideration and protected against in most software. Even though various methods have been suggested for anti-spoofing, there are challenges that these methods go through, e.g., washed-out images, lack of colour, poor illumination. Our proposal involves the use of OpenCV and deep learning to accurately colourize the image pre-processing and put it through the GAN framework (Wang et al., From RGB to Depth: Domain Transfer Network for Face Anti-Spoofing (2021). https://ieeexplore.ieee.org/document/9507460. Accessed 07 Feb 2022). Furthermore, to secure the image to prevent ill use, the final generated image pair will be encrypted so that only the user can access it. The aim is to combine the power of re-colourization with the GAN framework’s strong anti-spoofing capabilities and make the whole framework secure for the user. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.