BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260202T201258Z
LOCATION:Second Floor Atrium
DTSTART;TZID=America/Chicago:20251121T080000
DTEND;TZID=America/Chicago:20251121T120000
UID:submissions.supercomputing.org_SC25_sess620_post110@linklings.com
SUMMARY:AdversaGuard: A Distributed Data Poisoning Benchmark for Parallel 
 AI
DESCRIPTION:Yulia Kumar (Kean University, Rutgers University); Solomon Tho
 mas, Dejaun Gayle, and J. Jenny Li (Kean University); and Dov Kruger (Rutg
 ers University)\n\nThis study introduces FoodSAFE, a novel high performanc
 e computing (HPC)-based distributed data poisoning (DDP) framework designe
 d to benchmark adversarial resilience and training performance. The framew
 ork is tested across eight distinct configurations—seven distributed frame
 works and one non-distributed baseline. FoodSAFE evaluates three diverse f
 ood-related datasets and four model architectures, ranging from small neur
 al networks to large-scale transformers. The framework integrates eight ad
 vanced adversarial attacks: FGSM, PGD, DeepFool, One-Pixel, Universal, Car
 lini-Wagner, Trojan, and Boundary. It investigates how data, model, and hy
 brid parallelization strategies affect scalability, memory constraints, an
 d vulnerability under real-world conditions. Additionally, the study prese
 nts the AdversaGuard app to enable live testing of these DDP techniques. R
 esults indicate that while some architectures show greater tolerance to ad
 versarial poisoning, larger models often exhibit heightened vulnerability,
  highlighting the critical need for adaptive and scalable defense strategi
 es in modern AI systems.\n\nTag: Research & ACM SRC Posters\n\nRegistratio
 n Category: Technical Program Reg Pass\n\nSession Chairs: Kento Sato (RIKE
 N Center for Computational Science (R-CCS)); Anja Gerbes (Georg-August-Uni
 versität Göttingen); and Chris Schlipalius (Pawsey Supercomputing Research
  Centre; Commonwealth Scientific and Industrial Research Organisation (CSI
 RO), Australia)\n\n
END:VEVENT
END:VCALENDAR