BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//College of Arts & Sciences - ECPv6.16.2//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-WR-CALNAME:College of Arts & Sciences
X-ORIGINAL-URL:https://cas.uncg.edu
X-WR-CALDESC:Events for College of Arts & Sciences
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: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
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:20260308T070000
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:20261101T060000
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=America/New_York:20251001T160000
DTEND;TZID=America/New_York:20251001T173000
DTSTAMP:20260519T164026
CREATED:20250910T183345Z
LAST-MODIFIED:20250924T114219Z
UID:10000647-1759334400-1759339800@cas.uncg.edu
SUMMARY:Auditing Large Language Model Ecosystems: From Model Outputs to Agentic System Deployment
DESCRIPTION:The College of Arts & Sciences’ Ashby Dialogues presents this lecture by Dr. Tianlong Chen\, a computer science professor from UNC Chapel-Hill. \n\n\n\nThe 2025-26 Ashby Dialogues explores the theme\, “Rethinking the Algorithm: AI and the Human Experience.” \n\n\n\nAbout this presentation: Large Language Models (LLMs) are rapidly evolving from monolithic entities into complex\, interactive ecosystems. While previous research has focused on input-level vulnerabilities\, such as adversarial prompts and jailbreaking\, a new frontier of pragmatic\, system-level risks has emerged.  \n\n\n\nThis presentation shifts the focus from input manipulation to auditing the security and governance of the entire operational stack of LLM agent development. We dissect novel threat aspects that target the ecosystem itself\, including knowledge base poisoning\, covert prompt injection in agent societies\, economic resource exhaustion\, and hardware faults. We then survey a new generation of defenses designed to address these unique challenges\, ranging from proactive output protection to decentralized monitoring.  \n\n\n\nTogether\, these topics provide a blueprint for pragmatic safety\, covering both the immediate securing of LLM agentic systems and the principles for their long-term management. Attendees will leave with a comprehensive framework for this next generation of trustworthy AI. \n\n\n\nFree and open to the public.
URL:https://cas.uncg.edu/event/auditing-large-language-model-ecosystems-from-model-outputs-to-agentic-system-deployment/
LOCATION:Petty Building – Room 219\, 317 College Ave\, Greensboro\, North Carolina\, 27412\, United States
CATEGORIES:Ashby Dialogue Series,Rethinking the Algorithm,uncg_main
ATTACH;FMTTYPE=image/jpeg:https://cas.uncg.edu/wp-content/uploads/2025/09/TLC-copy_Ignacio-Lopez-1.jpg
END:VEVENT
END:VCALENDAR