BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Los_Angeles
X-LIC-LOCATION:America/Los_Angeles
BEGIN:DAYLIGHT
TZOFFSETFROM:-0800
TZOFFSETTO:-0700
TZNAME:PDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0700
TZOFFSETTO:-0800
TZNAME:PST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260730T152640Z
LOCATION:Exhibit Hall
DTSTART;TZID=America/Los_Angeles:20260728T174800
DTEND;TZID=America/Los_Angeles:20260728T174900
UID:dac_DAC 2026_sess306_WIP3274@linklings.com
SUMMARY:Swift-Healer: Firmware-Reconfigurable Self-Healing for Remote Glit
 ch-Injection on Autonomous Driving Systems
DESCRIPTION:Ali Suvizi and Joshua Iwu (Electrical and Computer Engineering
 , The George Washington University); Kostas Amberiadis (National Institute
  of Standards and Technology (NIST)); and Guru Venkataramani (Electrical a
 nd Computer Engineering, The George Washington University)\n\nAutonomous N
 avigation Systems (ANS) incorporate many safety-critical functions, such a
 s collision avoidance. Recent studies have shown how remote clock/voltage 
 glitch injections pose an imminent threat to mission-sensitive modules in 
 the autonomous navigation domain: timing/power perturbations in the percep
 tion stages can cascade into severe accuracy loss and latency drift for do
 wnstream tasks. In this paper, we present Swift-Healer, a firmware-reconfi
 gurable self-healing architecture that unifies prediction-detection module
 s and an automated healing unit to mitigate remote clock/voltage glitches,
  while satisfying the application latency constraints. Our solution levera
 ges a chiplet-based architecture that offers isolation from compromised ha
 rdware modules, while enabling self-healing in the firmware management lay
 er. Our proposed design incorporates an autonomous monitor that is a combi
 nation of a glitch predictor and a reactive detector. We implement our des
 ign on a Zynq–7000 with a hardware accelerator, where Swift-Healer predict
 s glitches within autonomous driving kernels up to two real–time loop iter
 ations earlier ≈ 0.06𝑚𝑠, thereby giving abundant time for self-healing (ty
 pically closer to 0.005 ms); if a prediction is below the confidence thres
 hold, the reactive detector flags the fault, and deploys the healing modul
 e rapidly. The system restores perception to its regular 0.03 ms latency, 
 holds steady-state power at 1.95 W, and exhibits transient peaks up to ∼2.
 44 W during the self-healing process.\n\nTrack: Student\n\n
END:VEVENT
END:VCALENDAR