Pietro Armenante
A greedy generalization algorithm for anonymizing Origin-Destination matrices.
Rel. Luca Vassio, Nikhil Jha, Marco Mellia. Politecnico di Torino, Corso di laurea magistrale in Cybersecurity, 2025
|
Preview |
PDF (Tesi_di_laurea)
- Tesi
Licenza: Creative Commons Attribution Non-commercial No Derivatives. Download (5MB) | Preview |
Abstract
Mobility data, describing the locations and movements of individuals within a geographic area, are a key resource for analysing and managing transportation systems. These data are frequently summarised in the form of origin–destination (OD) matrices, where each entry represents the number of trips between a specific origin and a specific destination. While OD-matrices are a valuable tool for modelling travel demand and managing transport networks, they also raise important privacy concerns, as they may allow the identification of individuals or sensitive travel patterns when published at high spatial resolution. In this work, a k-anonymisation algorithm specifically designed for OD-matrices is presented: the ODkAnon algorithm.
Unlike traditional approaches that apply uniform spatial generalisation to both origin and destination cells, this method dynamically determines, for each flow that does not meet the k-anonymity threshold, whether to generalise the origin or the destination
Relatori
Anno Accademico
Tipo di pubblicazione
Numero di pagine
Corso di laurea
Classe di laurea
URI
![]() |
Modifica (riservato agli operatori) |
