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:20260402T024534Z
LOCATION:3003\, Level 3
DTSTART;TZID=America/Los_Angeles:20250623T103000
DTEND;TZID=America/Los_Angeles:20250623T104500
UID:dac_DAC 2025_sess152_RESEARCH264@linklings.com
SUMMARY:AmpereBleed: Exploiting On-chip Current Sensors for Circuit-Free A
 ttacks on ARM-FPGA SoCs
DESCRIPTION:Xin Zhang, Yi Yang, Jiajun Zou, and Qingni Shen (Peking Univer
 sity); Zhi Zhang and Yansong Gao (University of Western Australia); Zhongh
 ai Wu (Peking University); and Trevor E. Carlson (National University of S
 ingapore)\n\nFPGAs offer superior energy efficiency and performance in par
 allel computing but are vulnerable to remote power side-channel attacks. E
 xisting attacks rely on assumptions of co-resident crafted circuits and sh
 ared power delivery networks, limiting their practicality in real-world sc
 enarios. In this paper, we present AmpereBleed, a novel current-based side
 -channel attack that exploits widely available INA226 sensors in ARM-FPGA 
 SoCs, bypassing the aforementioned two assumptions. AmpereBleed achieves 2
 61x greater variations to victim activities compared to the popular ring o
 scillator (RO) circuit, fingerprints DNN models on the Xilinx Deep Learnin
 g Processor Unit (DPU) with 99.7% accuracy, and distinguishes Hamming weig
 hts of RSA-1024 keys.\n\nTopics: Security\n\nTracks: SEC3: Hardware Securi
 ty: Attack & Defense\n\nSession Chairs: Michael Zuzak (Rochester Institute
  of Technology) and Prabuddha Chakraborty (University of Maine)\n\n
END:VEVENT
END:VCALENDAR