Robustness verification of ReLU networks via quadratic programming

Aleksei Kuvshinov, Stephan Günnemann

Publikation: Beitrag in FachzeitschriftArtikelBegutachtung

1 Zitat (Scopus)

Abstract

Neural networks are known to be sensitive to adversarial perturbations. To investigate this undesired behavior we consider the problem of computing the distance to the decision boundary (DtDB) from a given sample for a deep neural net classifier. In this work we present a procedure where we solve a convex quadratic programming (QP) task to obtain a lower bound on the DtDB. This bound is used as a robustness certificate of the classifier around a given sample. We show that our approach provides better or competitive results in comparison with a wide range of existing techniques.

OriginalspracheEnglisch
Seiten (von - bis)2407-2433
Seitenumfang27
FachzeitschriftMachine Learning
Jahrgang111
Ausgabenummer7
DOIs
PublikationsstatusVeröffentlicht - Juli 2022

Fingerprint

Untersuchen Sie die Forschungsthemen von „Robustness verification of ReLU networks via quadratic programming“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren