Towards Machine Learning Models that We Can Trust: Testing, Improving, and Explaining Robustness.

Maura Pintor Ambra Demontis Battista Biggio

Published in: ESANN (2023)

Keyphrases

machine learning models
machine learning algorithms
spam filtering
machine learning approaches
machine learning
predictive model
trust model
learning models
learning algorithm
email
support vector machine
machine learning methods
training data
support vector
image classification
test data