See at: CNR ExploRA

2022 Contribution to conference Open Access

IAIL 2022 - Imagining the AI Landscape after the AI Act
Dushi D., Naretto F., Panigutti C., Pratesi F.
We summarize the first Workshop on Imagining the AI Landscape after the AI Act (IAIL 2022), co-located with 1st International Conference on Hybrid Human-Artificial Intelligence (HHAI 2022), held on June 13, 2022 in Amsterdam, Netherlands.Project(s): CoHuBiCoL , TAILOR , HumanE-AI-Net , SoBigData-PlusPlus

See at: ceur-ws.org | ISTI Repository | CNR ExploRA

2023 Contribution to conference Open Access

Imagining the AI landscape after the AI act (Preface)
Dushi D., Naretto F., Pratesi F.
We provide a summary of the second Workshop on Imagining the AI Landscape after the AI Act (IAIL 2023), co-located with the 2nd International Conference on Hybrid Human-Artificial Intelligence (HHAI 2023), held on June 27, 2023 in Munich, Germany.Project(s): CoHuBiCoL , TAILOR , HumanE-AI-Net , SoBigData-PlusPlus

See at: ceur-ws.org | ISTI Repository | CNR ExploRA

See at: CNR ExploRA

Managing travels with PETRA: The Rome use case
Botea A., Braghin S., Lopes N., Guidotti R., Pratesi F.
The aim of the PETRA project is to provide the basis for a city-wide transportation system that supports policies catering for both individual preferences of users and city-wide travel patterns. The PETRA platform will be initially deployed in the partner city of Rome, and later in Venice, and Tel-Aviv.Source: 31st IEEE International Conference on Data Engineering. Data Mining and Smart Cities Applications Workshop, pp. 110–111, Seoul, Korea, 13-17/04/2015
DOI: 10.1109/icdew.2015.7129558
Project(s): PETRA
Metrics:

See at: doi.org | ieeexplore.ieee.org | CNR ExploRA

Mobility Mining for Journey Planning in Rome
Berlingerio M., Bicer V., Botea A., Braghin S., Lopes N., Guidotti R., Pratesi F.
We present recent results on integrating private car GPS routines obtained by a Data Mining module. into the PETRA (PErsonal TRansport Advisor) platform. The routines are used as additional "bus lines", available to provide a ride to travelers. We present the effects of querying the planner with and without the routines, which show how Data Mining may help Smarter Cities applications.Source: European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases. European Conference, pp. 222–226, Porto, Portugal, 07-11/09/2015
DOI: 10.1007/978-3-319-23461-8_18
Project(s): PETRA
Metrics:

See at: doi.org | link.springer.com | CNR ExploRA

2023 Conference article Open Access

Trustworthy AI at KDD Lab
Giannotti F., Guidotti R., Monreale A., Pappalardo L., Pedreschi D., Pellungrini R., Pratesi F., Rinzivillo S., Ruggieri S., Setzu M., Deluca R.
This document summarizes the activities regarding the development of Responsible AI (Responsible Artificial Intelligence) conducted by the Knowledge Discovery and Data mining group (KDD-Lab), a joint research group of the Institute of Information Science and Technologies "Alessandro Faedo" (ISTI) of the National Research Council of Italy (CNR), the Department of Computer Science of the University of Pisa, and the Scuola Normale Superiore of Pisa.Source: Ital-IA 2023, pp. 388–393, Pisa, Italy, 29-30/05/2023
Project(s): SoBigData-PlusPlus

See at: ceur-ws.org | ISTI Repository | CNR ExploRA

Assessing privacy risk in retail data
Pellungrini R., Pratesi F., Pappalardo L.
Retail data are one of the most requested commodities by commercial companies. Unfortunately, from this data it is possible to retrieve highly sensitive information about individuals. Thus, there exists the need for accurate individual privacy risk evaluation. In this paper, we propose a methodology for assessing privacy risk in retail data. We define the data formats for representing retail data, the privacy framework for calculating privacy risk and some possible privacy attacks for this kind of data. We perform experiments in a real-world retail dataset, and show the distribution of privacy risk for the various attacks.Source: Personal Analytics and Privacy. An Individual and Collective Perspective, edited by Riccardo Guidotti, Anna Monreale, Dino Pedreschi, Serge Abiteboul, pp. 17–22, 2017
DOI: 10.1007/978-3-319-71970-2_3
Project(s): SoBigData
Metrics:

See at: Lecture Notes in Computer Science | link.springer.com | CNR ExploRA

2022 Report Open Access

Mobility data mining: from technical to ethical (Dagstuhl Seminar 22022)
Berendt B., Matwin S., Renso C., Meissner F., Pratesi F., Raffaeta A., Rockwell G.
This report documents the program and the outcomes of Dagstuhl Seminar 22022 "Mobility Data Analysis: from Technical to Ethical" that took place fully remote and hosted by Schloss Dagstuhl from 10-12 January 2022. An interdisciplinary team of 23 researchers from Europe, the Americas and Asia in the fields of computer science, ethics and mobility analysis discussed interactions between their topics and fields to bridge the gap between the more technical aspects to the ethics with the objective of laying the foundations of a new Mobility Data Ethics research field.Source: ISTI Research report, pp.35–66, 2022
DOI: 10.4230/dagrep.12.1.35
Project(s): MASTER
Metrics:

See at: ISTI Repository | doi.org | CNR ExploRA

2019 Journal article Open Access

PRIMULE: Privacy risk mitigation for user profiles
Pratesi F., Gabrielli L., Cintia P., Monreale A., Giannotti F.
The availability of mobile phone data has encouraged the development of different data-driven tools, supporting social science studies and providing new data sources to the standard official statistics. However, this particular kind of data are subject to privacy concerns because they can enable the inference of personal and private information. In this paper, we address the privacy issues related to the sharing of user profiles, derived from mobile phone data, by proposing PRIMULE, a privacy risk mitigation strategy. Such a method relies on PRUDEnce (Pratesi et al., 2018), a privacy risk assessment framework that provides a methodology for systematically identifying risky-users in a set of data. An extensive experimentation on real-world data shows the effectiveness of PRIMULE strategy in terms of both quality of mobile user profiles and utility of these profiles for analytical services such as the Sociometer (Furletti et al., 2013), a data mining tool for city users classification.Source: Data & knowledge engineering 125 (2019). doi:10.1016/j.datak.2019.101786
DOI: 10.1016/j.datak.2019.101786
Project(s): SoBigData
Metrics:

See at: ISTI Repository | Archivio istituzionale della Ricerca - Scuola Normale Superiore | Data & Knowledge Engineering | www.sciencedirect.com | CNR ExploRA

Privacy-aware distributed mobility data analytics
Pratesi F., Monreale A., Wang H., Rinzivillo S., Pedreschi D., Andrienko G., Andrienko N.
We propose an approach to preserve privacy in an analytical process- ing within a distributed setting, and tackle the problem of obtaining aggregated information about vehicle traffic in a city from movement data collected by in- dividual vehicles and shipped to a central server. Movement data are sensitive because they may describe typical movement behaviors and therefore be used for re-identification of individuals in a database. We provide a privacy-preserving framework for movement data aggregation based on trajectory generalization in a distributed environment. The proposed solution, based on the differential pri- vacy model and on sketching techniques for efficient data compression, provides a formal data protection safeguard. Using real-life data, we demonstrate the ef- fectiveness of our approach also in terms of data utility preserved by the data transformation.Source: SEBD 2013 - 21st Italian Symposium on Advanced Database Systems, Roccella Jonica, Reggio Calabria, Italy, 30 June - 3 July 2013
Project(s): LIFT

See at: CNR ExploRA

2014 Journal article Open Access

Privacy-by-design in big data analytics and social mining
Monreale A., Rinzivillo S., Pratesi F., Giannotti F., Pedreschi D.
Privacy is ever-growing concern in our society and is becoming a fundamental aspect to take into account when one wants to use, publish and analyze data involving human personal sensitive information. Unfortunately, it is increasingly hard to transform the data in a way that it protects sensitive information: we live in the era of big data characterized by unprecedented opportunities to sense, store and analyze social data describing human activities in great detail and resolution. As a result, privacy preservation simply cannot be accomplished by de-identification alone. In this paper, we propose the privacy-by-design paradigm to develop technological frameworks for countering the threats of undesirable, unlawful effects of privacy violation, without obstructing the knowledge discovery opportunities of social mining and big data analytical technologies. Our main idea is to inscribe privacy protection into the knowledge discovery technology by design, so that the analysis incorporates the relevant privacy requirements from the start.Source: EPJ 3 (2014). doi:10.1140/epjds/s13688-014-0010-4
DOI: 10.1140/epjds/s13688-014-0010-4
Project(s): DATA SIM , PETRA
Metrics:

See at: EPJ Data Science | EPJ Data Science | www.epjdatascience.com | CNR ExploRA

PRISQUIT: a system for assessing privacy risk versus quality in data sharing
Pratesi F., Monreale A., Trasarti R., Giannotti F., Pedreschi D., Yanagihara T.
Data describing human activities are an important source of knowledge useful for understanding individual and collective behavior and for developing a wide range of user services. Unfortunately, this kind of data is sensitive, because people's whereabouts may allow re-identification of individuals in a de-identified database. Therefore, Data Providers, before sharing those data, must apply any sort of anonymization to lower the privacy risks, but they must be aware and capable of controlling also the data quality, since these two factors are often a trade-off. In this paper we propose PRISQUIT (Privacy RISk versus QUalITy), a system enabling a privacy-aware ecosystem for sharing personal data. It is based on a methodology for assessing both the empirical (not theoretical) privacy risk associated to users represented in the data, and the data quality guaranteed only with users not at risk. Our proposal is able to support the Data Provider in the exploration of a repertoire of possible data transformations with the aim of selecting one specific transformation that yields an adequate trade-off between data quality and privacy risk. We study the practical effectiveness of our proposal over three data formats underlying many services, defined on real mobility data, i.e., presence data, trajectory data and road segment data.Source: ISTI Technical reports, 2016
Project(s): SoBigData

See at: CNR ExploRA

2018 Contribution to book Open Access

See at: arpi.unipi.it | ISTI Repository | doi.org | link.springer.com | CNR ExploRA

2017 Journal article Open Access

A data mining approach to assess privacy risk in human mobility data
Pellungrini R., Pappalardo L., Pratesi F., Monreale A.
Human mobility data are an important proxy to understand human mobility dynamics, develop analytical services, and design mathematical models for simulation and what-if analysis. Unfortunately mobility data are very sensitive since they may enable the re-identification of individuals in a database. Existing frameworks for privacy risk assessment provide data providers with tools to control and mitigate privacy risks, but they suffer two main shortcomings: (i) they have a high computational complexity; (ii) the privacy risk must be recomputed every time new data records become available and for every selection of individuals, geographic areas, or time windows. In this article, we propose a fast and flexible approach to estimate privacy risk in human mobility data. The idea is to train classifiers to capture the relation between individual mobility patterns and the level of privacy risk of individuals. We show the effectiveness of our approach by an extensive experiment on real-world GPS data in two urban areas and investigate the relations between human mobility patterns and the privacy risk of individuals.Source: ACM transactions on intelligent systems and technology (Print) 9 (2017): 31:1–31:27. doi:10.1145/3106774
DOI: 10.1145/3106774
Project(s): SoBigData
Metrics:

See at: ACM Transactions on Intelligent Systems and Technology | doi.acm.org | Archivio della Ricerca - Università di Pisa | ISTI Repository | ACM Transactions on Intelligent Systems and Technology | CNR ExploRA

Fast estimation of privacy risk in human mobility data
Pellungrini R., Pappalardo L., Pratesi F., Monreale A.
Mobility data are an important proxy to understand the patterns of human movements, develop analytical services and design models for simulation and prediction of human dynamics. Unfortunately mobility data are also very sensitive, since they may contain personal information about the individuals involved. Existing frameworks for privacy risk assessment enable the data providers to quantify and mitigate privacy risks, but they suffer two main limitations: (i) they have a high computational complexity; (ii) the privacy risk must be re-computed for each new set of individuals, geographic areas or time windows. In this paper we explore a fast and flexible solution to estimate privacy risk in human mobility data, using predictive models to capture the relation between an individual's mobility patterns and her privacy risk. We show the effectiveness of our approach by experimentation on a real-world GPS dataset and provide a comparison with traditional methods.Source: SAFECOMP 2017 - International Conference on Computer Safety, Reliability, and Security, pp. 415–426, Trento, Italy, 12 September 2017
DOI: 10.1007/978-3-319-66284-8_35
Project(s): SoBigData
Metrics:

See at: Lecture Notes in Computer Science | link.springer.com | CNR ExploRA

2018 Conference article Open Access

Privacy Preserving Multidimensional Profiling
Pratesi F., Monreale A., Giannotti F., Pedreschi D.
Recently, big data had become central in the analysis of human behavior and the development of innovative services. In particular, a new class of services is emerging, taking advantage of different sources of data, in order to consider the multiple aspects of human beings. Unfortunately, these data can lead to re-identification problems and other privacy leaks, as diffusely reported in both scientific literature and media. The risk is even more pressing if multiple sources of data are linked together since a potential adversary could know information related to each dataset. For this reason, it is necessary to evaluate accurately and mitigate the individual privacy risk before releasing personal data. In this paper, we propose a methodology for the first task, i.e., assessing privacy risk, in a multidimensional scenario, defining some possible privacy attacks and simulating them using real-world datasets.Source: 3rd International Conference on Smart Objects and Technologies for Social Good, GOODTECHS 2017, pp. 142–152, Pisa, Italy, 29-30/11/2017
DOI: 10.1007/978-3-319-76111-4_15
Project(s): SoBigData
Metrics:

See at: link.springer.com | ISTI Repository | Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering | Archivio istituzionale della Ricerca - Scuola Normale Superiore | CNR ExploRA

2018 Journal article Open Access

PRUDEnce: A system for assessing privacy risk vs utility in data sharing ecosystems
Pratesi F., Monreale A., Trasarti R., Giannotti F., Pedreschi D., Yanagihara T.
Data describing human activities are an important source of knowledge useful for understanding individual and collective behavior and for developing a wide range of user services. Unfortunately, this kind of data is sensitive, because people's whereabouts may allow re-identification of individuals in a de-identified database. Therefore, Data Providers, before sharing those data, must apply any sort of anonymization to lower the privacy risks, but they must be aware and capable of controlling also the data quality, since these two factors are often a trade-off. In this paper we propose PRUDEnce (Privacy Risk versus Utility in Data sharing Ecosystems), a system enabling a privacy-aware ecosystem for sharing personal data. It is based on a methodology for assessing both the empirical (not theoretical) privacy risk associated to users represented in the data, and the data quality guaranteed only with users not at risk. Our proposal is able to support the Data Provider in the exploration of a repertoire of possible data transformations with the aim of selecting one specific transformation that yields an adequate trade-off between data quality and privacy risk. We study the practical effectiveness of our proposal over three data formats underlying many services, defined on real mobility data, i.e., presence data, trajectory data and road segment data.Source: Transactions on data privacy 11 (2018): 139–167.
Project(s): SoBigData

See at: ISTI Repository | www.tdp.cat | CNR ExploRA

2020 Journal article Open Access

An ethico-legal framework for social data science
Forgó N., Hänold S., Van Den Hoven J., Krügel T., Lishchuk I., Mahieu R., Monreale A., Pedreschi D., Pratesi F., Van Putten D.
This paper presents a framework for research infrastructures enabling ethically sensitive and legally compliant data science in Europe. Our goal is to describe how to design and implement an open platform for big data social science, including, in particular, personal data. To this end, we discuss a number of infrastructural, organizational and methodological principles to be developed for a concrete implementation. These include not only systematically tools and methodologies that effectively enable both the empirical evaluation of the privacy risk and data transformations by using privacy-preserving approaches, but also the development of training materials (a massive open online course) and organizational instruments based on legal and ethical principles. This paper provides, by way of example, the implementation that was adopted within the context of the SoBigData Research Infrastructure.Source: International Journal of Data Science and Analytics (Print) 11 (2020): 377–390. doi:10.1007/s41060-020-00211-7
DOI: 10.1007/s41060-020-00211-7
Project(s): SoBigData , SoBigData-PlusPlus
Metrics:

See at: Vrije Universiteit Brussel Research Portal | ISTI Repository | NARCIS | CNR ExploRA

The TAILOR Handbook of Trustworthy AI
Albertoni R., Allard T., Alves G., Bringas Colmenarejo A., Buijsman S., Casares P. A M, Colantonio S., Couceiro M., Escobar S., Gonzalez-Castañé G., Guidotti R., Heintz F., Hernandez Orallo J., Kuilman S., Makhlouf K., Martinez Plumed F., Monreale A., Pellungrini R., Pratesi F., Ramachandran Pillai R., Rossi A., Rousset M. C., Ruggieri S., Siebert L. C., Skrzypczyski P., Stefanowski J., Straccia U., Òsullivan B., Visentin A., Zgonnikov A., Zhioua S.
The main goal of the Handbook of Trustworthy AI is to provide to non experts, especially researchers and students, an overview of the problem related to the developing of ethical and trustworty AI systems. In particular, we want to provide an overview of the main dimensions of trustworthiness, starting with a understandable explaination of the dimension itsleves, and then presenting the characterization of the problems (staring with a brief summary and the explaination of the importance of the dimension, presenting a taxonomy and some guidelines, if they are available and consolidated), summarizing what are the major challenges and solutions in the field, as well as what are the lastest research developments.Project(s): TAILOR

See at: CNR ExploRA | tailor.isti.cnr.it