BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Adversarial Machine Learning - Andrew Coalter\, Sidney Sussex Coll
 ege
DTSTART:20190130T190000Z
DTEND:20190130T193000Z
UID:TALK119407@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:Machine learning models\, including neural networks\, have bee
 n shown to be vulnerable to malicious inputs designed to compromise their 
 integrity. These adversarial examples manipulate system behaviours in orde
 r to cause undesirable outputs. \n\nThis talk will discuss this problem\, 
 its ramifications\, an explantation of how these adversarial examples are 
 generated and an overview of the methods used to try and fight this proble
 m. 
LOCATION:Wolfson Hall\, Churchill College
END:VEVENT
END:VCALENDAR