[Ima.docs.toulouse] [Docs.toulouse] [Docs] [Doctorants] [Séminaire Sécurité/ Systèmes - Jeudi 25/01 à 10h30] Battista Biggio, "AI Security Testing: Lessons Learned and Open Challenges"

Bonjour tout le monde, Dans le cadre des séminaires de l'équipe Sécurité /Systèmes, nous écouterons sur Teams Battista Biggio, professeur associé à l'université de Cagliari (Italie) et co-fondateur de Pluribus One, jeudi 25/01/2024 à 10h30. Battista Biggio nous parlera de ses travaux sur "AI Security Testing: Lessons Learned and Open Challenges". Résumé: AI security testing has become crucial due to the widespread use of AI-based solutions in safety-critical and security-sensitive systems, and to comply with the emerging regulations. This talk aims to shed light on how to develop practical approaches to evaluate AI security properties in a pragmatic manner. I will discuss the emerging challenges and opportunities in AI security testing, along with the state-of-the-art techniques developed to date. The presentation will describe several security testing methods and explain the related challenges they pose. It will also quickly touch upon novel approaches derived from adversarial machine learning that can help overcome the existing AI security limitations. Bio : Battista Biggio (MSc 2006, PhD 2010) is Associate Professor at the University of Cagliari, Italy, and co-founder of the cybersecurity company Pluribus One. He has provided pioneering contributions in machine-learning security, playing a leading role in this field. His seminal paper on “Poisoning Attacks against Support Vector Machines” won the 2022 ICML Test of Time Award. His work on “Wild Patterns” won the 2021 Best Paper Award and Pattern Recognition Medal from Elsevier Pattern Recognition. He has managed several research projects, and regularly serves as a PC member for ICML, NeurIPS, and USENIX Security. He chaired IAPR TC1 (2016-2020), co-organized S+SSPR, AISec and DLS, and served as Associate Editor for IEEE TNNLS, IEEE CIM, and Pattern Recognition. He is a senior member of IEEE and ACM, and a member of IAPR and ELLIS. Cordialement, Ghada Gharbi ________________________________________________________________________________ Réunion Microsoft Teams Participez à partir de votre ordinateur, de votre application mobile ou de l’appareil de la salle Cliquez ici pour rejoindre la réunion<https://teams.microsoft.com/l/meetup-join/19%3ameeting_ZGI5YzFhZ… ID de la réunion : 355 366 181 466 Code secret : jSvE2T Télécharger Teams<https://www.microsoft.com/en-us/microsoft-teams/download-app> | Rejoindre sur le web<https://www.microsoft.com/microsoft-teams/join-a-meeting> Pour en savoir plus<https://aka.ms/JoinTeamsMeeting> | Options de réunion<https://teams.microsoft.com/meetingOptions/?organizerId=7c5194f6… ________________________________________________________________________________ ______________________ Doctorants mailing list -- doctorants(a)ml.lre.epita.fr https://lists.lrde.epita.fr/postorius/lists/doctorants.ml.lre.epita.fr// ______________________ Docs mailing list -- docs(a)ml.lre.epita.fr https://lists.lrde.epita.fr/postorius/lists/docs.ml.lre.epita.fr// ______________________ Docs.toulouse mailing list -- docs.toulouse(a)ml.lre.epita.fr https://lists.lrde.epita.fr/postorius/lists/docs.toulouse.ml.lre.epita.fr//