BEGIN:VCALENDAR
CALSCALE:GREGORIAN
VERSION:2.0
METHOD:PUBLISH
PRODID:-//Drupal iCal API//EN
X-WR-TIMEZONE:America/New_York
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
DTSTART:20070311T020000
TZNAME:EDT
TZOFFSETTO:-0400
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
DTSTART:20071104T020000
TZNAME:EST
TZOFFSETTO:-0500
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
SEQUENCE:1
X-APPLE-TRAVEL-ADVISORY-BEHAVIOR:AUTOMATIC
UID:250561
DTSTAMP:20261102T120125Z
DTSTART;TZID=America/New_York:20261112T160000
DTEND;TZID=America/New_York:20261112T165000
URL;TYPE=URI:https://www.wpi.edu/news/calendar/events/ece-graduate-seminar-
 lecture-speaker-professor-marco-donato-ece-department-tufts-university
SUMMARY:ECE Graduate Seminar Lecture\, Speaker: Professor Marco Donato\, EC
 E Department\, Tufts University
DESCRIPTION:Title:\nEnabling adversarial detection and robust inference for
  energy-efficient and secure edge AI\nAbstract:\nFine-tuning pretrained mo
 dels has become a widespread solution to deploy vision AI systems. The mai
 n reason that makes this approach popular is the fact that it provides an 
 efficient\, low-cost avenue to adapt generic convolutional models to vario
 us vision tasks from image recognition\, to object detection and semantic 
 segmentation. Unfortunately\, securing a model against adversarial attacks
  has not followed the same trend\, and model strengthening remains expensi
 ve and specialized.\nIn this talk I will first introduce an energy-efficie
 nt solution for multi-task inference at the edge. I will then present a no
 vel approach that applies a similar task adaptation technique to adversari
 al sample detection and robustness. Finally\, I will show some hardware op
 timizations that can be applied to efficiently deploy these models on reso
 urce-constrained devices for edge AI.\n\n  \n\n\nSpeaker:\nMarco Donato\nA
 ssistant Professor\, Department of Electrical and Computer Engineering\, T
 ufts University\nBio:\nMarco Donato is an Assistant Professor in the Depar
 tment of Electrical and Computer Engineering with a secondary appointment 
 in Computer Science at Tufts University. Prior to joining Tufts\, he was a
  Postdoctoral Fellow in the John A. Paulson School of Engineering and Appl
 ied Sciences at Harvard University. He earned a Ph.D. in Electrical Scienc
 es and Computer Engineering from Brown University and holds a M.Sc. and B.
 Sc. degree from the University of La Sapienza in Rome\, Italy.\nDr. Donato
  is the head of the Tufts Emerging Circuits and Systems (TECS) Lab\, where
  he leads a team working at the intersection of VLSI circuits and computer
  architecture to design energy-efficient\, reliable\, and secure computing
  systems. Their research focuses on developing cross-stack co-design metho
 dologies\, with particular emphasis on heterogeneous memory integration an
 d non-volatile memories. Their goal is to enable the integration of emergi
 ng technologies to address the challenges of technology scaling and growin
 g application complexity in modern computing systems.\nHost: Professor Joh
 n McNeill
END:VEVENT
END:VCALENDAR