BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Penn Engineering Events - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:Penn Engineering Events
X-ORIGINAL-URL:https://seasevents.nmsdev7.com
X-WR-CALDESC:Events for Penn Engineering Events
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20230312T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20231105T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20240310T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20241103T060000
END:STANDARD
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20250309T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20251102T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20240604T130000
DTEND;TZID=America/New_York:20240604T150000
DTSTAMP:20260603T135707
CREATED:20240528T151953Z
LAST-MODIFIED:20240528T151953Z
UID:11524-1717506000-1717513200@seasevents.nmsdev7.com
SUMMARY:ESE PhD Thesis Defense: "Algorithms for Adversarially Robust Deep Learning"
DESCRIPTION:Given the widespread use of deep learning models in safety-critical applications\, ensuring that the decisions of such models are robust against adversarial exploitation is of fundamental importance.  In this thesis\, we discuss recent progress toward designing algorithms that exhibit desirable robustness properties.  First\, we discuss the problem of adversarial examples in computer vision\, for which we introduce new technical results\, training paradigms\, and certification algorithms.  Next\, we consider the problem of domain generalization\, wherein the task is to train neural networks to generalize from a family of training distributions to unseen test distributions.  We present new algorithms that achieve state-of-the-art generalization in medical imaging\, molecular identification\, and image classification.  Finally\, we study the setting of jailbreaking large language models (LLMs)\, wherein an adversarial user attempts to design prompts that elicit objectionable content from an LLM.  We propose new attacks and defenses\, which represent the frontier of progress toward designing robust language-based agents.
URL:https://seasevents.nmsdev7.com/event/ese-phd-thesis-defense-algorithms-for-adversarially-robust-deep-learning/
LOCATION:Wu and Chen Auditorium (Room 101)\, Levine Hall\, 3330 Walnut Street\, Philadelphia\, PA\, 19104\, United States
CATEGORIES:Dissertation or Thesis Defense
ORGANIZER;CN="Electrical and Systems Engineering":MAILTO:eseevents@seas.upenn.edu
END:VEVENT
END:VCALENDAR