{"id":2528,"date":"2020-01-14T14:40:59","date_gmt":"2020-01-14T13:40:59","guid":{"rendered":"https:\/\/datascience.unifi.it\/?post_type=tribe_events&#038;p=2528"},"modified":"2020-01-14T14:41:43","modified_gmt":"2020-01-14T13:41:43","slug":"adversarial-machine-learning","status":"publish","type":"tribe_events","link":"https:\/\/datascience.unifi.it\/index.php\/event\/adversarial-machine-learning\/","title":{"rendered":"Adversarial Machine Learning"},"content":{"rendered":"<blockquote>\n<div>\n<div>\n<p>Speaker: Prof. Fabio Roli, Universit\u00e0 di Cagliari<\/p>\n<p>Machine learning algorithms are widely used for cybersecurity<br \/>\napplications, including spam, malware detection, biometric recognition.<br \/>\nIn these applications, the learning algorithm has to face intelligent<br \/>\nand adaptive attackers who can carefully manipulate data to purposely<br \/>\nsubvert the learning process. As machine learning algorithms have not<br \/>\nbeen originally designed under such premises, they have been shown to be<br \/>\nvulnerable to well-crafted attacks, including test-time evasion and<br \/>\ntraining-time poisoning attacks (also known as adversarial examples).<br \/>\nThis talk aims to introduce the fundamentals of adversarial machine<br \/>\nlearning and some techniques to assess the vulnerability of machine<br \/>\nlearning algorithms to adversarial attacks. We report application<br \/>\nexamples including object recognition in images, biometric identity<br \/>\nrecognition, spam and malware detection.<\/p>\n<\/div>\n<\/div>\n<div>\n<blockquote>\n<div>\n<div>Fabio Roli is a Full Professor of Computer Engineering at the University<br \/>\nof Cagliari, Italy, and Director of the Pattern Recognition and<br \/>\nApplications laboratory (<a href=\"http:\/\/pralab.diee.unica.it\/\" target=\"_blank\" rel=\"noopener noreferrer\" data-saferedirecturl=\"https:\/\/www.google.com\/url?q=http:\/\/pralab.diee.unica.it\/&amp;source=gmail&amp;ust=1579095451301000&amp;usg=AFQjCNHmkEsmwG85QkZMzMG0JIJbgcst1A\">http:\/\/pralab.diee.unica.it\/<\/a>)<wbr \/>. He is partner<br \/>\nand R&amp;D manager of the company Pluribus One that he co-founded<br \/>\n(<a href=\"https:\/\/www.pluribus-one.it\/\" target=\"_blank\" rel=\"noopener noreferrer\" data-saferedirecturl=\"https:\/\/www.google.com\/url?q=https:\/\/www.pluribus-one.it&amp;source=gmail&amp;ust=1579095451301000&amp;usg=AFQjCNGXkmJheHdvevKPuQcO-2u6C_W9Nw\">https:\/\/www.pluribus-one.it<\/a>\u00a0). He has been doing research on the design<br \/>\nof pattern recognition and machine learning systems for thirty years.<br \/>\nHis current h-index is 66 according to Google Scholar (December 2019).<br \/>\nHe has been appointed Fellow of the IEEE and Fellow of the International<br \/>\nAssociation for Pattern Recognition. He was a member of NATO advisory<br \/>\npanel for Information and Communications Security, NATO Science for<br \/>\nPeace and Security (2008 \u2013 2011).<\/div>\n<\/div>\n<\/blockquote>\n<\/div>\n<\/blockquote>\n","protected":false},"excerpt":{"rendered":"<p>Speaker: Prof. Fabio Roli, Universit\u00e0 di Cagliari Machine learning algorithms are widely used for cybersecurity applications, including spam, malware detection, biometric recognition. In these applications, the learning algorithm has to &#8230;<\/p>\n","protected":false},"author":1,"featured_media":0,"template":"","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"_tribe_events_status":"","_tribe_events_status_reason":"","footnotes":""},"tags":[],"tribe_events_cat":[],"class_list":["post-2528","tribe_events","type-tribe_events","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events\/2528","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events"}],"about":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/types\/tribe_events"}],"author":[{"embeddable":true,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/users\/1"}],"version-history":[{"count":2,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events\/2528\/revisions"}],"predecessor-version":[{"id":2531,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events\/2528\/revisions\/2531"}],"wp:attachment":[{"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/media?parent=2528"}],"wp:term":[{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tags?post=2528"},{"taxonomy":"tribe_events_cat","embeddable":true,"href":"https:\/\/datascience.unifi.it\/index.php\/wp-json\/wp\/v2\/tribe_events_cat?post=2528"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}