Robust Explanations for Private Support Vector Machines

no code implementations • 7 Feb 2021 • Rami Mochaourab, Sugandh Sinha, Stanley Greenstein, Panagiotis Papapetrou

For such classifiers, counterfactual explanations need to be robust against the uncertainties in the SVM weights in order to ensure, with high confidence, that the classification of the data instance to be explained is different than its explanation.

counterfactual