Utility-Drivenk-Anonymization of Public Transport User Data

Abstract

In this article, we propose a k-anonymity approach that prioritizes the generalization of attributes based on their utility. We focus on transport data, which we consider a special case in which many or all attributes are quasi-identifiers (e.g., origin, destination, ride start time), as they allow correlation with easily observable auxiliary data. The novelty in our approach lies in introducing normalization techniques as well as distance and utility metrics that allow the consideration of not only numerical attributes but also categorical attributes by representing them in tree or graph form. The prioritization of the attributes in the generalization process is based on the attributes' utility and can further be influenced by either automatically or manually assigned attribute weights. We evaluate and compare different options for all components of our mechanism as well as present an extensive performance evaluation of our approach using real-world data. Lastly, we show in which cases suppression of records can counter-intuitively lead to higher data utility.INDEX TERMS Clustering, k-anonymity, privacy, tap-in tap-out transportation data, utility.

Information Security and Privacy in Railway Transportation: A Systematic Review

“…Furthermore, with the aim of communicating with other sources to improve safety and provide better services, railways are periodically sending information (e.g., location coordinates) to a network shared with other users. Although these networks are still vulnerable to cyberattacks [ 66 ], the implementation of differential privacy [ 67 ] or anonymisation techniques [ 68 , 69 ] can be seen as an interesting solution to protect data privacy. Likewise, the development of architectures aimed at dealing with sensitive data should be developed following security and privacy-by-design principles, namely, accountability, authentication, availability, confidentiality, integrity, non-repudiation, revocation and data privacy [ 41 ].…”

A New Anonymization Model for Privacy Preserving Data Publishing: CANON

“…Finally, it was seen that their model provided more utility than the others. Bhati et al [34] focused on the anonymization of transport user data. A k-anonymity based anonymization model considering both numerical and categorical data was proposed.…”