BEGIN:VCALENDAR VERSION:2.0 PRODID:researchseminars.org CALSCALE:GREGORIAN X-WR-CALNAME:researchseminars.org BEGIN:VEVENT SUMMARY:Sven Cattell (Elastic) DTSTART:20210602T190000Z DTEND:20210602T200000Z DTSTAMP:20260423T024455Z UID:GOSS2021/2 DESCRIPTION:Title: The Math of ML Security\nby Sven Cattell (Elastic) as part of Graduat e Online Seminar Series (GOSS)\n\nLecture held in TBA.\n\nAbstract\nSecuri ty is a cat and mouse game. Attackers innovate to bypass defenders\, and d efenders innovate to catch the new attacks. One of the promises of AI is i ts ability to adapt for us. However\, the machine learning models we deplo y are trained on a chronological snapshot of the ever-changing data. They memorize and generalize well on that snapshot but are unreliable when the landscape shifts\, or have various adversarial examples and other holes th at let attackers to bypass the ML models. This talk will focus on how this plays out mathematically on the large datasets we use to create these mod els. We will also talk about how I transitioned into this industrial space \, from a PhD in equivariant algebraic topology and advice that might make things easier for future grad students looking towards ML.\n\nBio: \nSven Cattell is a Senior Security Data Scientist at Elastic. He received his m athematics PhD from Johns Hopkins University where his thesis focused on e quivariant algebraic topology. During his post doctoral his focused shifte d to the geometry of machine learning. While working on his postdoc he co- founded the AI Village at DEFCON which will be at DEFCON for the fourth ti me this year. He also built a math exhibit for the National Science Fair i n DC and a game to teach kids about disinformation and spam. He now works at Elastic Security on their malware models trying to improve the model an d secure it against adversarial attacks.\n LOCATION:https://researchseminars.org/talk/GOSS2021/2/ END:VEVENT END:VCALENDAR