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:20240626T180034Z
LOCATION:Level 2 Lobby
DTSTART;TZID=America/Los_Angeles:20240626T180000
DTEND;TZID=America/Los_Angeles:20240626T190000
UID:dac_DAC 2024_sess256_LBR106@linklings.com
SUMMARY:Late Breaking Results: Extracting QNNs from NISQ Computers via Ens
 emble Learning
DESCRIPTION:Late Breaking Results Poster\n\nZhenxiao Fu and Fan Chen (Indi
 ana University, Bloomington)\n\nThe recent success of Quantum Neural Netwo
 rks (QNNs) prompts model extraction attacks on cloud platforms, even under
  black-box constraints. These attacks repeatedly query the victim QNN with
  malicious inputs. However, existing extraction attacks tailored for class
 ical models yield local substitute QNNs with limited performance due to NI
 SQ computer noise. Drawing from bagging-based ensemble learning, which use
 s independent weak learners to learn from noisy data, we introduce a novel
  QNN extraction approach. Our experimental results show this quantum ensem
 ble learning approach improves local QNN accuracy by up to 15.09% compared
  to previous techniques.
END:VEVENT
END:VCALENDAR