Examining the Proximity of Adversarial Examples to Class Manifolds in Deep Networks.

Stefan Pócos Iveta Becková Igor Farkas

Published in: ICANN (4) (2022)

Keyphrases

data sets
learning algorithm
social networks
multi agent
network design
deep learning
neural network
feature extraction
feature space
high dimensional
euclidean space
positive examples
multi class classification
heterogeneous networks