BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Département de mathématiques et applications - ECPv6.2.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Département de mathématiques et applications
X-ORIGINAL-URL:https://www.math.ens.psl.eu
X-WR-CALDESC:évènements pour Département de mathématiques et applications
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:Europe/Paris
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:20230326T010000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:20231029T010000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=Europe/Paris:20231004T123000
DTEND;TZID=Europe/Paris:20231004T133000
DTSTAMP:20260515T172458
CREATED:20231005T083341Z
LAST-MODIFIED:20231005T083404Z
UID:16856-1696422600-1696426200@www.math.ens.psl.eu
SUMMARY:Julia Kempe - Towards Understanding Adversarial Robustness
DESCRIPTION:04 October 2023\, 12h30-13h30 (Paris time)\, room Amphi Jaures (29 Rue d’Ulm).\nJulia Kempe (NYU Centre for Data Science and Courant Institute)\nTitle: Towards Understanding Adversarial Robustness\nAbstract: Adversarial vulnerability of neural nets\, their failure under small\, imperceptible perturbations\, and subsequent techniques to create robust models have attracted significant attention; yet we still lack a full understanding of this phenomenon. In this talk I will introduce the problem and current defenses and then explore how tools and insights coming from statistical physics\, in particular certain infinite-width limits of neural nets\, help shed more light on the origins of the interplay between models and adversarial perturbations\, and how these tools can help us devise strategies to circumvent them.
URL:https://www.math.ens.psl.eu/evenement/julia-kempe-towards-understanding-adversarial-robustness/
LOCATION:Amphi Jaurès (29 Rue d’Ulm)
CATEGORIES:Séminaire Data de l’ENS
END:VEVENT
END:VCALENDAR