BEGIN:VCALENDAR
VERSION:2.0
PRODID:https://github.com/derhansen/sf_event_mgt
METHOD:PUBLISH
BEGIN:VEVENT
UID:8055-12628@ak-artcomp.gi.de
CLASS: PUBLIC
SUMMARY:Workshop „Adversarial Examples“ mit Dr. Fabian Offert (University o
 f California, Santa Barbara)
DESCRIPTION:Adversarial examples are images that elude their classification
  by deep neural networks. They exploit certain known weaknesses of these ne
 tworks — for instance a preference for texture over shape — by introducing 
 invisible changes to an image on the pixel level. Such images can then beco
 me instruments for stress-testing artificial intelligence systems, tools of
  resistance against social surveillance and control, or even media of artis
 tic expression. This workshop introduces participants to the theory and pra
 ctice of adversarial examples. With only a few lines of code, we will creat
 e images that confuse many well-known neural network architectures, and exp
 lore the limits of current-generation artificial intelligence systems.
DTSTAMP:20260706T103721Z
DTSTART:20210302T130000Z
DTEND:20260302T150000Z
END:VEVENT
END:VCALENDAR