BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:Asia/Shanghai
BEGIN:STANDARD
DTSTART:19910915T010000
TZOFFSETFROM:+0900
TZOFFSETTO:+0800
TZNAME:CST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260519T040929Z
UID:AA6E8C07-CBAE-49A0-8965-17F2FE5DB376
DTSTART;TZID=Asia/Shanghai:20260520T163000
DTEND;TZID=Asia/Shanghai:20260520T170000
DESCRIPTION:AI systems are now deployed as part of complex ecosystems rathe
 r than as standalone models. Their trustworthiness depends not only on mod
 el capabilities but also on the surrounding APIs\, tools\, platforms\, and
  agent interactions in real-world use. We will introduce recent work on me
 asuring and auditing trust\, safety\, and reliability in AI ecosystems. We
  will first discuss shadow APIs\, third-party LLM services that claim to p
 rovide access to frontier models\, and show how they can raise reliability
  and reproducibility risks. We will then present a measurement study of Mo
 ltbook\, a social network designed for AI agents\, focusing on agent disco
 urse\, toxic and manipulative content\, and temporal risk patterns. Finall
 y\, we will discuss to understand the bidirectional risks between AI agent
 s and the real world.\n\nRoom: 4-7151\, Bldg: Hongli Building\, No.28\, We
 st Xianning Road\, Xi'an\, Shaanxi\, China\, 710049
LOCATION:Room: 4-7151\, Bldg: Hongli Building\, No.28\, West Xianning Road\
 , Xi'an\, Shaanxi\, China\, 710049
ORGANIZER:chaoshen@mail.xjtu.edu.cn
SEQUENCE:4
SUMMARY:Measurement and Audit of Trust\, Safety\, and Reliability in AI Eco
 systems
URL;VALUE=URI:https://events.vtools.ieee.org/m/560364
X-ALT-DESC:Description: <br /><p>AI systems are now deployed as part of com
 plex ecosystems rather than as standalone models. Their trustworthiness de
 pends not only on model capabilities but also on the surrounding APIs\, to
 ols\, platforms\, and agent interactions in real-world use. We will introd
 uce recent work on measuring and auditing trust\, safety\, and reliability
  in AI ecosystems. We will first discuss shadow APIs\, third-party LLM ser
 vices that claim to provide access to frontier models\, and show how they 
 can raise reliability and reproducibility risks. We will then present a me
 asurement study of Moltbook\, a social network designed for AI agents\, fo
 cusing on agent discourse\, toxic and manipulative content\, and temporal 
 risk patterns. Finally\, we will discuss to understand the bidirectional r
 isks between AI agents and the real world.</p>
END:VEVENT
END:VCALENDAR