BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability - Joerg Simon Wicker - js@mrezha.wicker.nz

Channel Apps

Channel About Photos Files Calendar Wikis Cards Gallery

System Apps

Directory Help Language Random Channel Report Bug Search

Joerg Simon Wicker

js@mrezha.wicker.nz

Ig Nobel Prize In Chemisty 2021 - Machine Learning Group - School of Computer Science - University of Auckland

Location:: Auckland

New Zealand

Hometown:: Auckland

Homepage:: https://wickerlab.org - https://wicker.nz - https://ml.auckland.ac.nz

Image/photo

BAARD: Blocking Adversarial Examples by Testing for Applicability, Reliability and Decidability

Sat, 27 May 2023 09:15:00 +1200 last edited: Fri, 26 May 2023 21:03:08 +1200

Joerg Simon Wicker

js@mrezha.wicker.nz

Luke will be giving a talk on the connections between the concept of Applicability Domain in #Cheminformatics and adversarial defenses in #MachineLearning - at #PAKDD2023 in Osaka.

There are interesting connections between those areas, and Luke will be discussing the potential of an applicability domain algorithm to detect adversarial examples.

Hear more about it in Luke's talk today, Friday, May 27, in Session 5A starting at 3:30pm!