BEGIN:VCALENDAR
VERSION:2.0
PRODID:IEEE vTools.Events//EN
CALSCALE:GREGORIAN
BEGIN:VTIMEZONE
TZID:US/Eastern
BEGIN:DAYLIGHT
DTSTART:20240310T030000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
RRULE:FREQ=YEARLY;BYDAY=2SU;BYMONTH=3
TZNAME:EDT
END:DAYLIGHT
BEGIN:STANDARD
DTSTART:20241103T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
RRULE:FREQ=YEARLY;BYDAY=1SU;BYMONTH=11
TZNAME:EST
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20240418T135036Z
UID:CCFC4A14-67E0-4869-9F58-76EC1C7A9E2D
DTSTART;TZID=US/Eastern:20240417T120000
DTEND;TZID=US/Eastern:20240417T130000
DESCRIPTION:In this talk\, I will present a detailed research topic about A
 I Cybersecurity. Our group proposed an advanced gradient-based approach fo
 r mitigation of adversarial attacks in Deep Neural Networks (DNN). The pro
 posed approach adopted a random distortion transformation defense method c
 alled RDG (Random Distortion over Grids) and we combined it with non-linea
 r defenses to thwart adversarial attacks. Extensive evaluation demonstrate
 d the efficiency of this state-of-art defense approach.\n\nCo-sponsored by
 : Fairleigh Dickinson University\n\nSpeaker(s): Dr. Meikang Qiu\, \n\nAgen
 da: \nIn this talk\, I will present a detailed research topic about AI Cyb
 ersecurity. Our group proposed an advanced gradient-based approach for mit
 igation of adversarial attacks in Deep Neural Networks (DNN). The proposed
  approach adopted a random distortion transformation defense method called
  RDG (Random Distortion over Grids) and we combined it with non-linear def
 enses to thwart adversarial attacks. Extensive evaluation demonstrated the
  efficiency of this state-of-art defense approach.\n\nRoom: M105\, Bldg: 	
 Muscarelle Center\, M105\, \, 1000 River Road \, Teaneck \, New Jersey\, U
 nited States\, 07666\, Virtual: https://events.vtools.ieee.org/m/408037
LOCATION:Room: M105\, Bldg: 	Muscarelle Center\, M105\, \, 1000 River Road 
 \, Teaneck \, New Jersey\, United States\, 07666\, Virtual: https://events
 .vtools.ieee.org/m/408037
ORGANIZER:zhao@fdu.edu
SEQUENCE:43
SUMMARY:AI Cybersecurity
URL;VALUE=URI:https://events.vtools.ieee.org/m/408037
X-ALT-DESC:Description: <br /><p>In this talk\, I will present a detailed r
 esearch topic about AI Cybersecurity. Our group proposed an advanced gradi
 ent-based approach for mitigation of adversarial attacks in Deep Neural Ne
 tworks (DNN).&nbsp\;&nbsp\;The proposed approach adopted a random distorti
 on transformation defense method called RDG (Random Distortion over&nbsp\;
 Grids) and we combined it with non-linear defenses to thwart adversarial a
 ttacks.&nbsp\;Extensive evaluation demonstrated the efficiency of this sta
 te-of-art defense approach.</p><br /><br />Agenda: <br /><p>In this talk\,
  I will present a detailed research topic about AI Cybersecurity. Our grou
 p proposed an advanced gradient-based approach for mitigation of adversari
 al attacks in Deep Neural Networks (DNN).&nbsp\;&nbsp\;The proposed approa
 ch adopted a random distortion transformation defense method called RDG (R
 andom Distortion over&nbsp\;Grids) and we combined it with non-linear defe
 nses to thwart adversarial attacks.&nbsp\;Extensive evaluation demonstrate
 d the efficiency of this state-of-art defense approach.</p>
END:VEVENT
END:VCALENDAR