Paper published in a book (Scientific congresses and symposiums)
Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
Ozbulak, Utku; Van Messem, Arnout; De Neve, Wesley
2019In 2019 International Joint Conference on Neural Networks (IJCNN)
Peer reviewed
 

Files


Full Text
008_2019_OzbulakVanMessemDeNeve.pdf
Publisher postprint (679.1 kB)
Request a copy

All documents in ORBi are protected by a user license.

Send to



Details



Disciplines :
Computer science
Author, co-author :
Ozbulak, Utku
Van Messem, Arnout  ;  Université de Liège - ULiège > Département de mathématique > Statistique applquée aux sciences
De Neve, Wesley
Language :
English
Title :
Not All Adversarial Examples Require a Complex Defense: Identifying Over-optimized Adversarial Examples with IQR-based Logit Thresholding
Publication date :
2019
Event name :
International Joint Conference on Neural Networks 2019 (IJCNN)
Event organizer :
IEEE
Event place :
Budapest, Hungary
Event date :
2019
Audience :
International
Main work title :
2019 International Joint Conference on Neural Networks (IJCNN)
Pages :
1-8
Peer reviewed :
Peer reviewed
Available on ORBi :
since 10 March 2021

Statistics


Number of views
31 (5 by ULiège)
Number of downloads
1 (1 by ULiège)

Scopus citations®
 
0
Scopus citations®
without self-citations
0
OpenCitations
 
0

Bibliography


Similar publications



Contact ORBi