Privacy Preserving Computation in the Cloud using Homomorphic

Pulicherla, Sarath (2025) Privacy Preserving Computation in the Cloud using Homomorphic. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (480kB) | Preview

Abstract

The use of privacy-preserving data analytics has grown to be a necessity because of the fast-paced advancement of both digital healthcare and financial systems. Conventional encryption secures data when it is not accessed and during its transfer, however, it still requires decryption to carry out computation which results in the risk of the sensitive information being exposed to breaches. Homomorphic Encryption (HE) gets rid of this drawback since it allows performing mathematical operations on encrypted data directly. The present work sees the CKKS approximate homomorphic encryption scheme, which is realized through the Microsoft SEAL 4.1 library, as a means to carry out secure statistical analysis.

The Iris dataset, the Pima Indians Diabetes dataset, and a large Credit Card Fraud dataset with 284,807 transactions were the three real-world datasets that were analyzed in the study. An entire Ubuntu-based experimental pipeline was created which comprised encoding, encryption, encrypted computation, decryption, and decoding. To handle datasets larger than CKKS slot capacity, a chunking strategy was employed. The results indicated very precise encrypted mean calculations, with errors less than 5×10⁻⁷, and practical efficiency, where the whole credit card dataset was processed in about one second. The results confirm that the CKKS-based HE can allow secure analytics in real healthcare and financial environments while being tolerable in terms of accuracy and scalability.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Salahuddin, Jawad UNSPECIFIED
Uncontrolled Keywords:	Homomorphic Encryption; Microsoft SEAL; CKKS; Privacy-Preserving Analytics; Encrypted Computation; Iris Dataset; Diabetes Dataset; Credit Card Fraud Dataset
Subjects:	T Technology > T Technology (General) > Information Technology > Cloud computing 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:	04 Sep 2026 09:16
Last Modified:	04 Sep 2026 09:16
URI:	https://norma.ncirl.ie/id/eprint/9819

Actions (login required)

View Item