Search Results for author:
Found 5 papers, 2 papers with code
Abstract Interpretation-Based Feature Importance for SVMs
We leverage this abstraction in two ways: (1) to enhance the interpretability of SVMs by deriving a novel feature importance measure, called abstract feature importance (AFI), that does not depend in any way on a given dataset of the accuracy of the SVM and is very fast to compute, and (2) for verifying stability, notably individual fairness, of SVMs and producing concrete counterexamples when the verification fails.
Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbations
Semantic perturbations can significantly change the saliency-map.
A Review of Formal Methods applied to Machine Learning
We review state-of-the-art formal methods applied to the emerging field of the verification of machine learning systems.
Fair Training of Decision Tree Classifiers
We study the problem of formally verifying individual fairness of decision tree ensembles, as well as training tree models which maximize both accuracy and individual fairness.
Perfectly Parallel Fairness Certification of Neural Networks
Recently, there is growing concern that machine-learning models, which currently assist or even automate decision making, reproduce, and in the worst case reinforce, bias of the training data.
