Improved Detection of Adversarial Attacks via Penetration Distortion Maximization

11/03/2019
by   Shai Rozenberg, et al.
0

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, and can be integrated into any given neural classificationmodel. Our method demonstrates state-of-the-art (detection) performance under all threat models.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset