Abstract

The emergence of Digital Justice in conjunction with advanced Data Analysis techniques presents the opportunity to advance the criminal justice system toward an innovative Data-Driven approach. An important issue of public safety is the analysis of legal recidivism. Assessing recidivism is a complex measurement problem that necessitates reconstructing a subject’s criminal history from criminal records, which usually reside in different autonomous databases. In addition, the collection and processing of sensitive legal-related data about individuals imposes consideration of privacy legislation and confidentiality implications. This paper presents the design and development of a Proof of Concept (PoC) for a Privacy-Preserving Data Integration (PPDI) framework to establish a Data Warehouse across criminal and court sources within the Italian Justice Domain and a Data Mart to assess the recidivism phenomena.

References

• Eupid - european patient identity management. https:// eupid.eu. Accessed: Aug. 01, 2024.
• Luca Bolognini and Camilla Bistolfi. Pseudonymization and impacts of big (personal/anonymous) data processing in the transition from the directive 95/46/ec to the new EU general data protection regulation. Comput. Law Secur. Rev., 33(2):171–181, 2017.
• Peter Christen, Thilina Ranbaduge, and Rainer Schnell. Linking Sensitive Data - Methods and Techniques for Practical Privacy-Preserving Information Sharing. Springer, 2020.
• Chris Clifton, Murat Kantarcioglu, AnHai Doan, Gunther Schadow, Jaideep Vaidya, Ahmed K. Elmagarmid, and Dan Suciu. Privacy-preserving data integration and sharing. In DMKD, pages 19–26. ACM, 2004.
• Elizabeth Ashley Durham, Murat Kantarcioglu, Yuan Xue, Csaba T´oth, Mehmet Kuzu, and Bradley A. Malin. Composite bloom filters for secure record linkage. IEEE Trans. Knowl. Data Eng., 26(12):2956–2968, 2014.
• Benjamin C. M. Fung et al. Privacy-preserving data publishing: A survey of recent developments. ACM Comput. Surv., 42(4):14:1–14:53, 2010.
• J M Gouweleeuw, Peter Kooiman, and PP De Wolf. Post randomisation for statistical disclosure control: Theory and implementation. Journal of official Statistics, 14(4):463, 1998.
• Yehuda Lindell and Benny Pinkas. Secure multiparty computation for privacy-preserving data mining. J. Priv. Confidentiality, 1(1), 2009.
• Riccardo Pozzi, Riccardo Rubini, Christian Bernasconi, and Matteo Palmonari. Named entity recognition and linking for entity extraction from italian civil judgements. In Proceedings of AIxIA 2023. Springer, 2023.
• R. Schnell. Privacy-preserving record linkage. In K. Harron, H. Goldstein, and C. Dibben, editors, Methodological Developments in Data Linkage, pages 201–225. John Wiley & Sons, UK, December 2015.
• Rainer Schnell, Tobias Bachteler, and J¨org Reiher. Privacypreserving record linkage using bloom filters. BMC Medical Informatics Decis. Mak., 9:41, 2009.
• Rainer Schnell, Tobias Bachteler, and J¨org Reiher. A novel error-tolerant anonymous linking code, 2011.
• Duncan Smith. Secure pseudonymisation for privacypreserving probabilistic record linkage. J. Inf. Secur. Appl., 34:271–279, 2017.
• Khoi-Nguyen Tran, Dinusha Vatsalan, and Peter Christen. Geco: an online personal data generator and corruptor. In Proc. of CIKM 2013, pages 2473–2476. ACM, 2013.
• Lisa Trigiante, Domenico Beneventano, and Sonia Bergamaschi. Privacy-preserving data integration for digital justice. Technical Report TR-2025-01, Department of Engineering “Enzo Ferrari”, University of Modena and Reggio Emilia, 2025. https://dbgroup.ing.unimore.it/ TecRep/trigiante2025_1.pdf.
• Dinusha Vatsalan, Peter Christen, and Vassilios S. Verykios. A taxonomy of privacy-preserving record linkage techniques. Inf. Syst., 38(6):946–969, 2013.
• Anushka Vidanage, Thilina Ranbaduge, Peter Christen, and Rainer Schnell. Taxonomy of attacks on privacy-preserving record linkage. J. Priv. Confidentiality, 12(1), 2022.