LAUSR

Sparse adversarial attack based on ℓq-norm for fooling the face anti-spoofing neural networks

Sign Up to like & get
recommendations!
1 Published in 2021 at "Journal of Electronic Imaging"

DOI: 10.1117/1.jei.30.2.023023

Abstract: Abstract. Neural networks are vulnerable to various adversarial perturbations added to the input. Highly sparse adversarial perturbations are difficult to identify, which is especially dangerous to network security. Previous research has shown that ℓ0-norm has… read more here.

Keywords: neural networks; attack; anti spoofing; sparse adversarial ... See more keywords