BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Date iCal//NONSGML kigkonsult.se iCalcreator 2.20.4//
METHOD:PUBLISH
X-WR-CALNAME;VALUE=TEXT:ÌÇÐÄÔ­´´
BEGIN:VTIMEZONE
TZID:America/New_York
BEGIN:STANDARD
DTSTART:20221106T020000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
BEGIN:DAYLIGHT
DTSTART:20230312T020000
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
END:DAYLIGHT
END:VTIMEZONE
BEGIN:VEVENT
UID:calendar.463491.field_event_date.0@www.wright.edu
DTSTAMP:20260220T012221Z
CREATED:20221026T183841Z
DESCRIPTION:Abstract:Despite their remarkable inference ability\, machine l
 earning models are faced with the inherent learning-security challenge of 
 lacking adversarial robustness. In other words\, they are vulnerable to ad
 versarial attacks that can easily fool the models into misclassification b
 y adding small perturbations to the input data. Accordingly\, understandin
 g machine learning security in adversarial settings has significantly emer
 ged as a mainstream topic in AI domain. Most of the current research works
  in this line follow either adversarial or defensive perspectives to analy
 ze methodologies of each other and develop strategies to overcome the oppo
 nents. However\, few of them go beyond adversary\, and turn these attacks 
 into applications for social good. This talk will cover some of our repres
 entative works that advance adversarial vulnerability of machine learning 
 for supporting real-world tasks. If unable to attend in person\, sign up f
 or the webinar. Register Here
DTSTART;TZID=America/New_York:20221103T110000
DTEND;TZID=America/New_York:20221103T120000
LAST-MODIFIED:20221026T193115Z
LOCATION:152C Russ Engineering
SUMMARY:CSE Department Speaker Series - Adversary for Social Good: Turning 
 Adversarial Attacks into Applications by Lingwei Chen Ph.D.
URL;TYPE=URI:/events/cse-department-speaker-series-ad
 versary-social-good-turning-adversarial-attacks-applications
END:VEVENT
END:VCALENDAR