Timezone: »

 
Poster
Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation
Matthias Hein · Maksym Andriushchenko

Mon Dec 04 06:30 PM -- 10:30 PM (PST) @ Pacific Ballroom #29
in Posters Mon »

Recent work has shown that state-of-the-art classifiers are quite brittle, in the sense that a small adversarial change of an originally with high confidence correctly classified input leads to a wrong classification again with high confidence. This raises concerns that such classifiers are vulnerable to attacks and calls into question their usage in safety-critical systems. We show in this paper for the first time formal guarantees on the robustness of a classifier by giving instance-specific \emph{lower bounds} on the norm of the input manipulation required to change the classifier decision. Based on this analysis we propose the Cross-Lipschitz regularization functional. We show that using this form of regularization in kernel methods resp. neural networks improves the robustness of the classifier without any loss in prediction performance.

Keywords: Deep Learning · Classification · Regularization
[ Code]  [ Paper] 

Author Information

Matthias Hein (Saarland University)
Maksym Andriushchenko (Saarland University)

More from the Same Authors