Cardiff University | Prifysgol Caerdydd ORCA
Online Research @ Cardiff 
WelshClear Cookie - decide language by browser settings

Semantic attack on anonymised transaction data

Alshuhail, Asma 2021. Semantic attack on anonymised transaction data. PhD Thesis, Cardiff University.
Item availability restricted.

[thumbnail of Asma Alshuhail PhD Thesis]
PDF (Asma Alshuhail PhD Thesis) - Accepted Post-Print Version
Available under License Creative Commons Attribution No Derivatives.

Download (1MB) | Preview
[thumbnail of Cardiff University Electronic Publication Form] PDF (Cardiff University Electronic Publication Form) - Supplemental Material
Restricted to Repository staff only

Download (249kB)


Publishing data about individuals is a double-edged sword; it can provide a significant benefit for a range of organisations to help understand issues concerning individuals, and improve services they offer. However, it can also represent a serious threat to individuals’ privacy. To overcome these threats, researchers have worked on developing anonymisation methods. However, the anonymisation methods do not take into consideration the semantic relationships and meaning of data, which can be exploited by attackers to expose protected data. In our work, we study a specific anonymisation method called disassociation and investigate if it provides adequate protection for transaction data. The disassociation method hides sensitive links between transaction’s items by dividing them into chunks. We propose a de-anonymisation approach to attacking transaction data anonymised by the disassociated data. The approach exploits the semantic relationships between transaction items to reassociate them. Our findings reveal that the disassociation method may not effectively protect transaction data. Our de-anonymisation approach can recombine approximately 60% of the disassociated items and can break the privacy of nearly 70% of the protected itemets in disassociated transactions.

Item Type: Thesis (PhD)
Date Type: Completion
Status: Unpublished
Schools: Computer Science & Informatics
Date of First Compliant Deposit: 15 February 2022
Date of Acceptance: 14 February 2022
Last Modified: 11 Mar 2023 02:52

Actions (repository staff only)

Edit Item Edit Item


Downloads per month over past year

View more statistics