BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//University of Liverpool Computer Science Seminar System//v2//EN
BEGIN:VEVENT
DTSTAMP:20261017T180022Z
UID:Seminar-dept-1519@lxserverM.csc.liv.ac.uk
ORGANIZER:CN=Lutz Oettershagen:MAILTO:Lutz.Oettershagen@liverpool.ac.uk
DTSTART:20261103T130000
DTEND:20261103T140000
SUMMARY:School Seminar Series
DESCRIPTION:Ihsen Alouani: Uncovering Integrity and Confidentiality Flaws in Modern Language Models\n\nLarge Language Models are introducing new classes of security and privacy vulnerabilities that emerge from their internal mechanisms of attention, memory, and optimization. This talk explores how these mechanisms can be exploited to infer sensitive training data, bypass safety alignment, and amplify memorization and extraction attacks. Through recent research on attention-based membership inference, attention-driven jailbreaks, and poisoning-assisted data extraction, the talk will highlight how the very components that make LLMs powerful also create novel attack surfaces. \n\nhttps://www.csc.liv.ac.uk/research/seminars/abstract.php?id=1519
LOCATION:Ashton Lecture Theatre
END:VEVENT
END:VCALENDAR