1,721,161 research outputs found
Evaluating the Privacy Exposure of Interpretable Global and Local Explainers
No full textDuring the last few years, the abundance of data has significantly boosted the performance of Machine Learning models, integrating them into several aspects of daily life. However, the rise of powerful Artificial Intelligence tools has introduced ethical and legal complexities. This paper proposes a computational framework to analyze the ethical and legal dimensions of Machine Learning models, focusing specifically on privacy concerns and interpretability. In fact, recently, the research community proposed privacy attacks able to reveal whether a record was part of the black-box training set or inferring variable values by accessing and querying a Machine Learning model. These attacks highlight privacy vulnerabilities and prove that GDPR regulation might be violated by making data or Machine Learning models accessible. At the same time, the complexity of these models, often labelled as “black-boxes”, has made the development of explanation methods indispensable to enhance trust and facilitate their acceptance and adoption in high-stake scenarios. Our study highlights the trade-off between interpretability and privacy protection. By introducing REVEAL, this paper proposes a framework to evaluate the privacy exposure of black-box models and their surrogate-based explainers, whether local or global. Our methodology is adaptable and applicable across diverse black-box models and various privacy attack scenarios. Through an in-depth analysis, we show that the interpretability layer introduced by explanation models might jeopardize the privacy of individuals in the training data of the black-box, particularly with powerful privacy attacks requiring minimal knowledge but causing significant privacy breaches
Specifying Mining Algorithms with Iterative User-Defined Aggregates
No full textWe present a way of exploiting domain knowledge in the design and implementation of data mining algorithms, with special attention to frequent patterns discovery, within a deductive framework. In our framework, domain knowledge is represented by way of deductive rules, and data mining algorithms are specified by means of iterative user-defined aggregates and implemented by means of user-defined predicates. This choice allows us to exploit the full expressive power of deductive rules without loosing in performance. Iterative user-defined aggregates have a fixed scheme, in which user-defined predicates are to be added. This feature allows the modularization of data mining algorithms, thus providing a way to integrate the proper domain knowledge exploitation in the right point. As a case study, the paper presents how user-defined aggregates can be exploited to specify and implement a version of the a priori algorithm. Some performance analyzes and comparisons are discussed in order to show the effectiveness of the approach
Evaluating the Privacy Exposure of Interpretable Global Explainers
No full textIn recent years we are witnessing the diffusion of AI systems based on powerful Machine Learning models which find application in many critical contexts such as medicine, financial market and credit scoring. In such a context it is particularly important to design Trustworthy AI systems while guaranteeing transparency, with respect to their decision reasoning and privacy protection. Although many works in the literature addressed the lack of transparency and the risk of privacy exposure of Machine Learning models, the privacy risks of explainers have not been appropriately studied. This paper presents a methodology for evaluating the privacy exposure raised by interpretable global explainers able to imitate the original black-box classifier. Our methodology exploits the well-known Membership Inference Attack. The experimental results highlight that global explainers based on interpretable trees lead to an increase in privacy exposure
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
PRIMULE: Privacy risk mitigation for user profiles
Full text linkThe 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
Origin and destination attachment: study of cultural integration on Twitter
Full text linkThe cultural integration of immigrants conditions their overall socio-economic integration as well as natives’ attitudes towards globalisation in general and immigration in particular. At the same time, excessive integration—or assimilation—can be detrimental in that it implies forfeiting one’s ties to the origin country and eventually translates into a loss of diversity (from the viewpoint of host countries) and of global connections (from the viewpoint of both host and home countries). Cultural integration can be described using two dimensions: the preservation of links to the origin country and culture, which we call origin attachment, and the creation of new links together with the adoption of cultural traits from the new residence country, which we call destination attachment. In this paper we introduce a means to quantify these two aspects based on Twitter data. We build origin and destination attachment indices and analyse their possible determinants (e.g., language proximity, distance between countries), also in relation to Hofstede’s cultural dimension scores. The results stress the importance of language: a common language between origin and destination countries favours origin attachment, as does low proficiency in the host language. Common geographical borders seem to favour both origin and destination attachment. Regarding cultural dimensions, larger differences among origin and destination countries in terms of Individualism, Masculinity and Uncertainty appear to favour destination attachment and lower origin attachment
- …
