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:20260728T174500
DTEND;TZID=America/Los_Angeles:20260728T174500
UID:dac_DAC 2026_sess306_LBR068@linklings.com
SUMMARY:Late Breaking Results: ROAST: Reverse-training Offset Attack on Sp
 atial Sampling Topologies
DESCRIPTION:Shayan Gerami (Student), Sepehr Tabrizchi (University of Illin
 ois Chicago), Shaahin Angizi (New Jersey Institute of Technology), and Arm
 an Roohi (University of Illinois Chicago)\n\nLocal Binary Pattern Network 
 (LBPNet) concentrates representational power in a small set of learned spa
 tial sampling offsets, creating a high-leverage fault surface. We propose 
 ROAST, a white-box reverse-training attack that updates only offsets to ma
 ximize the loss, then maps adversarial offsets to a minimal-bit-flip sched
 ule using truncated Hamming distance on FP32 encodings. On MNIST and SVHN,
  ROAST induces >70% and 64% accuracy drops while flipping only ~4–5% of of
 fset bits, outperforming BFA in damage-per-bit and avoiding border-saturat
 ion artifacts.\n\nTrack: Student\n\n
END:VEVENT
END:VCALENDAR