BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//https://caida.ubc.ca//NONSGML iCalcreator 2.41.92//
CALSCALE:GREGORIAN
METHOD:PUBLISH
UID:64383533-6266-4638-a161-626632643963
X-WR-RELCALID:efc09d74-9c93-479e-a94f-485231ddccde
X-WR-TIMEZONE:America/Vancouver
X-WR-CALNAME:TrustML in Power Grids: Security\, Robustness\, and Statistica
 l Risks - Hao Zhu\, Associate Professor\, University of Texas at Austin
BEGIN:VTIMEZONE
TZID:America/Vancouver
TZUNTIL:20270314T100000Z
BEGIN:STANDARD
TZNAME:PST
DTSTART:20241103T020000
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
RDATE:20251102T020000
RDATE:20261101T020000
END:STANDARD
BEGIN:DAYLIGHT
TZNAME:PDT
DTSTART:20250309T020000
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
RDATE:20260308T020000
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:1a57660c-b4db-4826-b9bd-b827b4eff576
DTSTAMP:20260530T141032Z
CLASS:PUBLIC
CREATED:20250710T213800Z
DESCRIPTION:Abstract: AI/ML advances are increasingly transforming the para
 digm in the operations and control of the electric power grids. Nonetheles
 s\, as a critical infrastructure\, power grids need to ensure the AI/ML so
 lutions are as trustworthy as they are intelligent. In this talk\, I will 
 discuss a few recent research directions to achieve reliable\, secure\, an
 d risk-aware applications of AI/ML to power grids. Our ICML work\, LEVIS: 
 Large Exact Verifiable Input Spaces for Neural Networks\, will be highligh
 ted. LEVIS aims to analyze the robustness of neural by identifying the lar
 gest reliable input space…
DTSTART;TZID=America/Vancouver:20250715T160000
DTEND;TZID=America/Vancouver:20250715T170000
LAST-MODIFIED:20250710T220042Z
LOCATION:UBC Vancouver Campus\, Fried Kaiser (KAIS) building\, Room 2020/20
 30\, 2332 Main Mall
SUMMARY:TrustML in Power Grids: Security\, Robustness\, and Statistical Ris
 ks - Hao Zhu\, Associate Professor\, University of Texas at Austin
TRANSP:OPAQUE
URL:https://caida.ubc.ca/event/trustml-power-grids-security-robustness-and-
 statistical-risks-hao-zhu-associate-professor
END:VEVENT
END:VCALENDAR