<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Riccardo Guidotti</style></author><author><style face="normal" font="default" size="100%">Anna Monreale</style></author><author><style face="normal" font="default" size="100%">Matwin, Stan</style></author><author><style face="normal" font="default" size="100%">Dino Pedreschi</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Brefeld, Ulf</style></author><author><style face="normal" font="default" size="100%">Fromont, Elisa</style></author><author><style face="normal" font="default" size="100%">Hotho, Andreas</style></author><author><style face="normal" font="default" size="100%">Knobbe, Arno</style></author><author><style face="normal" font="default" size="100%">Maathuis, Marloes</style></author><author><style face="normal" font="default" size="100%">Robardet, Céline</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Black Box Explanation by Learning Image Exemplars in the Latent Feature Space</style></title><secondary-title><style face="normal" font="default" size="100%">Machine Learning and Knowledge Discovery in Databases</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2020</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2020//</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://link.springer.com/chapter/10.1007/978-3-030-46150-8_12</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">Springer International Publishing</style></publisher><pub-location><style face="normal" font="default" size="100%">Cham</style></pub-location><isbn><style face="normal" font="default" size="100%">978-3-030-46150-8</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">We present an approach to explain the decisions of black box models for image classification. While using the black box to label images, our explanation method exploits the latent feature space learned through an adversarial autoencoder. The proposed method first generates exemplar images in the latent feature space and learns a decision tree classifier. Then, it selects and decodes exemplars respecting local decision rules. Finally, it visualizes them in a manner that shows to the user how the exemplars can be modified to either stay within their class, or to become counter-factuals by “morphing” into another class. Since we focus on black box decision systems for image classification, the explanation obtained from the exemplars also provides a saliency map highlighting the areas of the image that contribute to its classification, and areas of the image that push it into another class. We present the results of an experimental evaluation on three datasets and two black box models. Besides providing the most useful and interpretable explanations, we show that the proposed method outperforms existing explainers in terms of fidelity, relevance, coherence, and stability.</style></abstract></record><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Roberto Pellungrini</style></author><author><style face="normal" font="default" size="100%">Anna Monreale</style></author><author><style face="normal" font="default" size="100%">Riccardo Guidotti</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Alzate, Carlos</style></author><author><style face="normal" font="default" size="100%">Anna Monreale</style></author><author><style face="normal" font="default" size="100%">Bioglio, Livio</style></author><author><style face="normal" font="default" size="100%">Bitetta, Valerio</style></author><author><style face="normal" font="default" size="100%">Bordino, Ilaria</style></author><author><style face="normal" font="default" size="100%">Caldarelli, Guido</style></author><author><style face="normal" font="default" size="100%">Ferretti, Andrea</style></author><author><style face="normal" font="default" size="100%">Riccardo Guidotti</style></author><author><style face="normal" font="default" size="100%">Gullo, Francesco</style></author><author><style face="normal" font="default" size="100%">Pascolutti, Stefano</style></author><author><style face="normal" font="default" size="100%">Pensa, Ruggero G.</style></author><author><style face="normal" font="default" size="100%">Robardet, Céline</style></author><author><style face="normal" font="default" size="100%">Squartini, Tiziano</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Privacy Risk for Individual Basket Patterns</style></title><secondary-title><style face="normal" font="default" size="100%">ECML PKDD 2018 Workshops</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2019</style></year><pub-dates><date><style  face="normal" font="default" size="100%">2019//</style></date></pub-dates></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://link.springer.com/chapter/10.1007/978-3-030-13463-1_11</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">Springer International Publishing</style></publisher><pub-location><style face="normal" font="default" size="100%">Cham</style></pub-location><isbn><style face="normal" font="default" size="100%">978-3-030-13463-1</style></isbn><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">Retail data are of fundamental importance for businesses and enterprises that want to understand the purchasing behaviour of their customers. Such data is also useful to develop analytical services and for marketing purposes, often based on individual purchasing patterns. However, retail data and extracted models may also provide very sensitive information to possible malicious third parties. Therefore, in this paper we propose a methodology for empirically assessing privacy risk in the releasing of individual purchasing data. The experiments on real-world retail data show that although individual patterns describe a summary of the customer activity, they may be successful used for the customer re-identifiation.</style></abstract></record></records></xml>