Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability

Ozbulak, Utku; Peck, Jonathan; De Neve, Wesley; Goossens, Bart; Saeys, Yvan; Van Messem, Arnout

Paper published on a website (Scientific congresses and symposiums)

Ozbulak, Utku; Peck, Jonathan; De Neve, Wesley et al.

2020 • 37th International Conference on Machine Learning; Workshop on Uncertainty & Robustness in Deep Learning (ICML UDL 2020)

Peer reviewed

Permalink
https://hdl.handle.net/2268/257838

Files (1)Send to Details Statistics Bibliography Similar publications

Files

Full Text

014_2020_OzbulakPeckDeNeveGoossensSaeysVanMessem.pdf

Publisher postprint (3.52 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
Mathematics

Author, co-author :

Ozbulak, Utku

Peck, Jonathan

De Neve, Wesley

Goossens, Bart

Saeys, Yvan

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

Language :

English

Title :

Regional Image Perturbation Reduces $L_p$ Norms of Adversarial Examples While Maintaining Model-to-model Transferability

Publication date :

2020

Event name :

37th International Conference on Machine Learning; Workshop on Uncertainty & Robustness in Deep Learning (ICML UDL 2020)

Event place :

Vienna, Austria

Event date :

2020

Audience :

International

Peer reviewed :

Peer reviewed

Source :

arxiv

Additional URL :

https://arxiv.org/abs/2007.03198

Available on ORBi :

since 10 March 2021

Statistics

Number of views

39 (2 by ULiège)

Number of downloads

2 (1 by ULiège)

More statistics