Deepfake Resistant Framework: Real Time Biometrics Identity Verification in Remote Banking

Chandrasagaran, Shanthini (2025) Deepfake Resistant Framework: Real Time Biometrics Identity Verification in Remote Banking. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (663kB) | Preview

Abstract

The progressive sophistication of deep-fake technologies, powered by breakthroughs in Generative Adversarial Networks (GANs) and deep learning, presents an opportunity to elevate the resilience of biometric identity verification systems across the banking and FinTech landscape. These advanced, synthetic assets—including facial, audio, and behavioral signatures—demand a higher standard of security than conventional methods currently offer.

My research is dedicated to designing and successfully implementing a leading-edge, multi-modal verification framework. This system is specifically designed for real-time, robust biometric identification within critical financial Know Your Customer (KYC) processes. The proposed defense leverages the power of four integrated layers—facial recognition, voice authentication, behavioral biometrics, and active liveness detection—to achieve optimal resilience and adaptability.

To validate its strength, I will generate sophisticated synthetic challenges using advanced deepfake tools. Detection will be handled by fine-tuned Convolutional Neural Networks (CNNs). A key contribution is the development of a vulnerability scoring dashboard, providing financial institutions with the crucial ability to quantitatively measure and proactively visualize their exposure status. Implemented in Python on Google Colab for real-time performance, this study delivers a powerful and essential defense system that secures the digital identity lifecycle against evolving AI-driven methodologies.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Spelman, Ross UNSPECIFIED
Subjects:	H Social Sciences > HG Finance > Banking T Technology > TK Electrical engineering. Electronics. Nuclear engineering > Biometric Identification Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	03 Sep 2026 10:32
Last Modified:	03 Sep 2026 10:32
URI:	https://norma.ncirl.ie/id/eprint/9792

Actions (login required)

View Item