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:20211208T164413Z
LOCATION:Level 2 - Lobby
DTSTART;TZID=America/Los_Angeles:20211208T180000
DTEND;TZID=America/Los_Angeles:20211208T190000
UID:dac_DAC 2021_sess244_LBR135@linklings.com
SUMMARY:Physical Adversarial Attacks of Diffractive Deep Neural Networks
DESCRIPTION:Late Breaking Results Poster, Networking Reception\n\nPhysical
  Adversarial Attacks of Diffractive Deep Neural Networks\n\nLi, Yu\n\nDiff
 ractive Deep Neural Network (D2NNs) can work as a neural network with the 
 diffraction of light and have demonstrated significant performance improve
 ments in energy efficiency in broad security-sensitive applications. In th
 is work, we develop the first adversarial attack formulations over optical
  physical meanings over optical domains, i.e. Phase attack, Amplitude atta
 ck, and Complex-domain attack, which can be realized in D2NNs system using
  amplitude and phase modulators. We demonstrate that the proposed Complex 
 Fast Gradient Sign Method can successfully generate minimal-changed physic
 ally feasible adversarial examples targeting pre-trained D2NNs model on MN
 IST-10 dataset, which bring down its accuracy to <20% from 95.4%.\n\nVirtu
 al Program: Presented In-Person
END:VEVENT
END:VCALENDAR