@article {564, title = {Anonymity preserving sequential pattern mining}, journal = {Artif. Intell. Law}, volume = {22}, number = {2}, year = {2014}, pages = {141{\textendash}173}, abstract = {The increasing availability of personal data of a sequential nature, such as time-stamped transaction or location data, enables increasingly sophisticated sequential pattern mining techniques. However, privacy is at risk if it is possible to reconstruct the identity of individuals from sequential data. Therefore, it is important to develop privacy-preserving techniques that support publishing of really anonymous data, without altering the analysis results significantly. In this paper we propose to apply the Privacy-by-design paradigm for designing a technological framework to counter the threats of undesirable, unlawful effects of privacy violation on sequence data, without obstructing the knowledge discovery opportunities of data mining technologies. First, we introduce a k-anonymity framework for sequence data, by defining the sequence linking attack model and its associated countermeasure, a k-anonymity notion for sequence datasets, which provides a formal protection against the attack. Second, we instantiate this framework and provide a specific method for constructing the k-anonymous version of a sequence dataset, which preserves the results of sequential pattern mining, together with several basic statistics and other analytical properties of the original data, including the clustering structure. A comprehensive experimental study on realistic datasets of process-logs, web-logs and GPS tracks is carried out, which empirically shows how, in our proposed method, the protection of privacy meets analytical utility.}, doi = {10.1007/s10506-014-9154-6}, url = {http://dx.doi.org/10.1007/s10506-014-9154-6}, author = {Anna Monreale and Dino Pedreschi and Ruggero G. Pensa and Fabio Pinelli} } @proceedings {242, title = {Anonymous Sequences from Trajectory Data}, year = {2009}, edition = {17}, address = {Camogli, Italy}, author = {Ruggero G. Pensa and Anna Monreale and Fabio Pinelli and Dino Pedreschi} } @conference {CosciaGP09, title = {Social Network Analysis as Knowledge Discovery Process: A Case Study on Digital Bibliography}, booktitle = {ASONAM}, year = {2009}, pages = {279-283}, author = {Michele Coscia and Fosca Giannotti and Ruggero G. Pensa} } @conference {asonam09, title = {Social Network Analysis as Knowledge Discovery Process: A Case Study on Digital Bibliography}, booktitle = {ASONAM}, year = {2009}, pages = {279-283}, author = {Michele Coscia and Fosca Giannotti and Ruggero G. Pensa} } @conference {DBLP:conf/esoric, title = {Pattern-Preserving k-Anonymization of Sequences and its Application to Mobility Data Mining}, booktitle = {PiLBA}, year = {2008}, abstract = {Sequential pattern mining is a major research field in knowledge discovery and data mining. Thanks to the increasing availability of transaction data, it is now possible to provide new and improved services based on users{\textquoteright} and customers{\textquoteright} behavior. However, this puts the citizen{\textquoteright}s privacy at risk. Thus, it is important to develop new privacy-preserving data mining techniques that do not alter the analysis results significantly. In this paper we propose a new approach for anonymizing sequential data by hiding infrequent, and thus potentially sensible, subsequences. Our approach guarantees that the disclosed data are k-anonymous and preserve the quality of extracted patterns. An application to a real-world moving object database is presented, which shows the effectiveness of our approach also in complex contexts.}, url = {https://air.unimi.it/retrieve/handle/2434/52786/106397/ProceedingsPiLBA08.pdf$\#$page=44}, author = {Ruggero G. Pensa and Anna Monreale and Fabio Pinelli and Dino Pedreschi} }