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_post122@linklings.com
SUMMARY:Real-Time ML-Based Defense Against Malicious Payload in Reconfigur
 able Embedded Systems
DESCRIPTION:Rye Stahle-Smith and Rasha Karakchi (University of South Carol
 ina)\n\nField-programmable gate arrays (FPGAs) in reconfigurable systems f
 ace escalating security threats from malicious bitstreams capable of causi
 ng denial-of-service, data leakage, or covert operations. Traditional dete
 ction methods often require source code or netlists, limiting their applic
 ability for real-time protection.\n\nWe present a supervised machine learn
 ing approach that directly analyzes FPGA bitstreams at the binary level, e
 nabling rapid detection without design-level access. Using byte frequency 
 analysis, truncated singular value decomposition (TSVD), and SMOTE balanci
 ng, we developed and evaluated multiple classifiers on a dataset of 122 be
 nign and malicious configurations for the Xilinx PYNQ-Z1 board. Random For
 est achieved a macro F1-score of 0.97, validating the method’s effectivene
 ss for resource-constrained devices.\n\nThe final model was deployed on PY
 NQ for integrated, on-device analysis. During the poster session, we will 
 outline our detection pipeline, dataset preparation process, and performan
 ce results, emphasizing the novelty of binary-level analysis and its impli
 cations for real-time Trojan detection in embedded systems.\n\nTag: Resear
 ch & ACM SRC Posters\n\nRegistration Category: Technical Program Reg Pass\
 n\nSession Chairs: Kento Sato (RIKEN Center for Computational Science (R-C
 CS)); Anja Gerbes (Georg-August-Universität Göttingen); and Chris Schlipal
 ius (Pawsey Supercomputing Research Centre; Commonwealth Scientific and In
 dustrial Research Organisation (CSIRO), Australia)\n\n
END:VEVENT
END:VCALENDAR
