Improved Detection of Adversarial Attacks via Penetration Distortion Maximization

Rozenberg Shai
Rozenberg Shai
Cited by: 0|Bibtex|Views9
Other Links: arxiv.org

Abstract:

This paper is concerned with the defense of deep models against adversarial attacks. We developan adversarial detection method, which is inspired by the certificate defense approach, and capturesthe idea of separating class clusters in the embedding space to increase the margin. The resultingdefense is intuitive, effective, scalable, an...More

Code:

Data:

Full Text
Your rating :
0

 

Tags
Comments