FE-DaST: Fast and effective data-free substitute training for black-box adversarial attacks

Title
FE-DaST: Fast and effective data-free substitute training for black-box adversarial attacks
Authors
Keywords
Image classification, Data-free substitute training, Adversarial framework, Black-box adversarial attacks, Information entropy
Journal
COMPUTERS & SECURITY
Volume 113, Issue -, Pages 102555
Publisher
Elsevier BV
Online
2021-11-20
DOI
10.1016/j.cose.2021.102555

Ask authors/readers for more resources

Reprint

Contact the author

Add your recorded webinar

Do you already have a recorded webinar? Grow your audience and get more views by easily listing your recording on Peeref.

Upload Now

Ask a Question. Answer a Question.

Quickly pose questions to the entire community. Debate answers and get clarity on the most important issues facing researchers.

Get Started