Can Adversarial Training Be Manipulated By Non-Robust Features?

Lue Tao Lei Feng Hongxin Wei Jinfeng Yi Sheng-Jun Huang Songcan Chen

Published in: CoRR (2022)

Keyphrases

feature vectors
prior knowledge
training process
feature space
low level
image features
rotational invariant
test set
feature extraction
supervised learning
co occurrence
training examples
training set
multi agent
salient features
robust estimation
multiscale