<br />
<b>Warning</b>:  Use of undefined constant ‘doing_it_wrong_trigger_error’ - assumed '‘doing_it_wrong_trigger_error’' (this will throw an Error in a future version of PHP) in <b>/home/users/mest/lastsunday-htdocs/wp-includes/functions.php</b> on line <b>10</b><br />
<br />
<b>Warning</b>:  Use of undefined constant ‘__return_false’ - assumed '‘__return_false’' (this will throw an Error in a future version of PHP) in <b>/home/users/mest/lastsunday-htdocs/wp-includes/functions.php</b> on line <b>10</b><br />
<br />
<b>Warning</b>:  Cannot modify header information - headers already sent by (output started at /home/users/mest/lastsunday-htdocs/wp-includes/functions.php:10) in <b>/home/users/mest/lastsunday-htdocs/wp-content/plugins/events-manager/em-ical.php</b> on line <b>70</b><br />
<br />
<b>Warning</b>:  Cannot modify header information - headers already sent by (output started at /home/users/mest/lastsunday-htdocs/wp-includes/functions.php:10) in <b>/home/users/mest/lastsunday-htdocs/wp-content/plugins/events-manager/em-ical.php</b> on line <b>71</b><br />
BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//6.6.3//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:75@mestcenter.org
DTSTART;TZID=America/New_York:20220216T120000
DTEND;TZID=America/New_York:20220216T130000
DTSTAMP:20240905T133002Z
URL:https://mestcenter.org/training/webinar-securing-neural-networks-again
 st-side-channel-attacks-with-hardware-masking/
SUMMARY:Webinar: Securing Neural Networks Against Side-Channel Attacks with
  Hardware Masking
DESCRIPTION:To watch the recorded webinar\, click on the recording.\nPlay V
 ideo\nSpeaker: \nDr. Aydin Aysu\, North Carolina State University\nAbstra
 ct:\nIntellectual Property (IP) thefts of trained machine learning (ML) mo
 dels through side-channel attacks on inference engines are becoming a majo
 r threat.  Indeed\, several recent works have shown reverse engineering o
 f the model internals using such attacks\, but the research on building de
 fenses is largely unexplored.  There is a critical need to efficiently an
 d securely transform those defenses from cryptography to ML frameworks.  
 A common defense technique is called masking\, which randomizes all inter
 mediate computations while preserving the same functionality.  Although m
 asking is well-known for cryptography its extension to ML is non-trivial.
   In this talk\, I will explain different mechanisms to mask neural netwo
 rks in hardware and describe related opportunities and challenges.  I wil
 l first discuss how a straightforward masking adaptation leaks side-channe
 l information on neural networks and how to address this vulnerability. 
  I will then describe a fundamentally new approach that redefines neural n
 etworks to make them easier to mask in hardware.\nSpeaker Bio:\nDr.  Aydi
 n Aysu is currently an assistant professor and Bennett Faculty Fellow at
  the Electrical and Computer Engineering Department of North Carolina Stat
 e University\, where he leads HECTOR: Hardware Cybersecurity Research Lab.
   He got his M.S from Sabanci University in Istanbul\, Turkey\, and his P
 h.D. from Virginia Tech. Before joining NC State\, he was a post-doctoral 
 researcher at the University of Texas at Austin.  Dr. Aysu's interests a
 re broadly on hardware security research and cybersecurity education.  He
  has won the 2019 NC State Faculty Development Award\, 2019 NSF Research I
 nitiative (CRII) award\, the 2020 Bennett Faculty award\, and the 2020 NSF
  CAREER award.  His papers have been nominated for the best paper award
  both at 2018 and 2019 IEEE HOST conferences and have won the best paper a
 ward at 2019 GLS-VLSI and 2020 DATE conferences.  He is an IEEE senior me
 mber. \n \nZoom Information:\nJoin Zoom Meeting\nhttps://ufl.zoom.us/j/904
 047693\n\nMeeting ID: 904 047 693\n\nOne tap mobile\n+16465588656\,\,90404
 7693# US (New York)\n+16699006833\,\,904047693# US (San Jose)\n\nDial by y
 our location\n+1 646 558 8656 US (New York)\n+1 669 900 6833 US (San Jose)
 \nMeeting ID: 904 047 693\nFind your local number: https://ufl.zoom.us/u/a
 b5VOI6m6G\n\nJoin by SIP\n904047693@zoomcrc.com\n\nJoin by H.323\n162.255.
 37.11 (US West)\n162.255.36.11 (US East)\n221.122.88.195 (China)\n115.114.
 131.7 (India Mumbai)\n115.114.115.7 (India Hyderabad)\n213.19.144.110 (EME
 A)\n103.122.166.55 (Australia)\n209.9.211.110 (Hong Kong)\n64.211.144.160 
 (Brazil)\n69.174.57.160 (Canada)\n207.226.132.110 (Japan)\nMeeting ID: 904
  047 693\n\nJoin by Skype for Business\nhttps://ufl.zoom.us/skype/90404769
 3
ATTACH;FMTTYPE=image/jpeg:https://mestcenter.org/wp-content/uploads/2022/0
 1/aysu-journal-bio-image.jpg
CATEGORIES:Home Page,Webinars
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20211107T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR