Homomorphic Encryption In Open Banking

Srirangam, Priyanka (2023) Homomorphic Encryption In Open Banking. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (623kB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Open banking is the practice of enabling secure sharing of financial information of a customer between a data owning financial entity and an innovative financial service provider through a set of well-defined APIs and third-party aggregators. The third-party aggregators use customer data for training AI models to offer competent digital solutions for fraud detection, lending analysis etc. Prior to this, aggregators are required to minimize customer data to eliminate re-identification or data leakage concerns. But the inadequate and possibly confusing regulations around the minimization techniques leave financial institutions to adopt an individualised risk-based approach to evaluate the minimization procedures in place. Thus, usage of homomorphic encryption is proposed in this research work, to encrypt customer data before arriving at the 3rd party aggregators. This will help enhance data security and assuage privacy concerns surrounding data minimization techniques. Homomorphic encryption is a form of encryption which allows for computations to be performed on encrypted data. The result of such computation is same as that of normal operation on plain data. The complexity of computations that can be performed are continuously improving, with latest applications in machine learning. Key focus of the paper is to show a high-level design of an open banking ecosystem embedded with homomorphic encryption. A simple implementation is included to prove that it is feasible to encrypt and decrypt API payloads using available homomorphic encryption libraries. Furthermore, the research includes evaluation of security and performance of the proposed approach, as well as utility of the homomorphically encrypted data for predictive AI models. The paper then concludes with a view of current challenges with the implementation and future areas worthy of research.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Spelman, Ross UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence H Social Sciences > HG Finance > Banking Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Ciara O'Brien
Date Deposited:	25 Apr 2025 09:41
Last Modified:	25 Apr 2025 09:41
URI:	https://norma.ncirl.ie/id/eprint/7469

Actions (login required)

View Item