BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250626T233528Z
LOCATION:B302-B305
DTSTART;TZID=America/New_York:20241120T100000
DTEND;TZID=America/New_York:20241120T170000
UID:submissions.supercomputing.org_SC24_sess533_post216@linklings.com
SUMMARY:Parallel Verification of Neural Networks Applied to Medical Imagin
 g
DESCRIPTION:Jonathan Andreasen (Georgia Tech Research Institute), Diego Ma
 nzanas Lopez and Taylor Johnson (Vanderbilt University), and Yatis Dodia (
 Georgia Tech Research Institute)\n\nNeural network verification provides m
 odel robustness guarantees in the presence of noise. We generate verificat
 ion specifications for medical imaging models based on the U-Net architect
 ure and solve pixel-by-pixel verification problems on a massive scale. Eff
 iciency of this NP-complete problem is studied using α,β-CROWN. We impleme
 nt parallelization per pixel and demonstrate orders-of-magnitude speedup a
 llowing faster characterization or increased timeout values for greater so
 lving capability.\n\nRegistration Category: Tech Program Reg Pass, Exhibit
 s Reg Pass\n\nSession Chairs: Ayesha Afzal (Friedrich-Alexander University
 , Erlangen-Nuremberg; Erlangen National High Performance Computing Center)
 ; Sally Ellingson (University of Kentucky); and Alan Sussman (University o
 f Maryland)\n\n
END:VEVENT
END:VCALENDAR