2026-07-22T11:56:48Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:17611 2026-04-20T13:23:09Z ddc:004 open_access

Security of Machine Learning (Dagstuhl Seminar 22281) Biggio, Battista Carlini, Nicholas Laskov, Pavel Rieck, Konrad Cinà, Antonio Emanuele adversarial machine learning machine learning security Machine learning techniques, especially deep neural networks inspired by mathematical models of human intelligence, have reached an unprecedented success on a variety of data analysis tasks. The reliance of critical modern technologies on machine learning, however, raises concerns on their security, especially since powerful attacks against mainstream learning algorithms have been demonstrated since the early 2010s. Despite a substantial body of related research, no comprehensive theory and design methodology is currently known for the security of machine learning. The proposed seminar aims at identifying potential research directions that could lead to building the scientific foundation for the security of machine learning. By bringing together researchers from machine learning and information security communities, the seminar is expected to generate new ideas for security assessment and design in the field of machine learning. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Battista Biggio and Nicholas Carlini and Pavel Laskov and Konrad Rieck and Antonio Emanuele Cinà 2023 Is Part Of Dagstuhl Reports, Volume 12, Issue 7 (2023) Article Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/DagRep.12.7.41 urn:nbn:de:0030-drops-176117 https://drops.dagstuhl.de/entities/document/10.4230/DagRep.12.7.41 eng https://creativecommons.org/licenses/by/4.0/legalcode