Sign in
How adversarial attacks can disrupt seemingly stable accurate classifiers.
Oliver J. Sutton
Qinghua Zhou
Ivan Yu. Tyukin
Alexander N. Gorban
Alexander Bastounis
Desmond J. Higham
Published in:
CoRR (2023)
Keyphrases
</>
accurate classifiers
random forests
training data
learning algorithm
text classifiers
class probabilities
labeled data
labeled examples
support vector machine
data sets
feature extraction
pairwise
feature vectors
logistic regression
machine learning methods