How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples

Ozbulak, Utku; De Neve, Wesley; Van Messem, Arnout

Paper published in a book (Scientific congresses and symposiums)

Ozbulak, Utku; De Neve, Wesley; Van Messem, Arnout

2018 • In NeuRIPS 2018: 32nd Conference on Neural Information Processing Systems; Workshop on Security in Machine Learning (SECML2018)

Peer reviewed

Permalink
https://hdl.handle.net/2268/257831

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

007_2018_OzbulakDeNeveVanMessem.pdf

Publisher postprint (1.1 MB)

Request a copy

All documents in ORBi are protected by a user license.

Send to

RIS BibTex APA Chicago Permalink X Linkedin

Details

Disciplines :

Computer science

Author, co-author :

Ozbulak, Utku

De Neve, Wesley

Van Messem, Arnout ; Université de Liège - ULiège > Département de mathématique > Statistique applquée aux sciences

Language :

English

Title :

How the Softmax Output is Misleading for Evaluating the Strength of Adversarial Examples

Publication date :

2018

Event name :

32nd Conference on Neural Information Processing Systems (NeurIPS): Workshop on Security in Machine Learning (SECML)

Event place :

Montreal, Canada

Event date :

2018

Audience :

International

Main work title :

NeuRIPS 2018: 32nd Conference on Neural Information Processing Systems; Workshop on Security in Machine Learning (SECML2018)

Peer reviewed :

Peer reviewed

Additional URL :

https://arxiv.org/abs/1811.08577

Available on ORBi :

since 10 March 2021

Statistics

Number of views

36 (3 by ULiège)

Number of downloads

2 (1 by ULiège)

More statistics