Skip to Main content Skip to Navigation
New interface
Conference papers

Efficient Statistical Assessment of Neural Network Corruption Robustness

Karim Tit 1 Teddy Furon 2 Mathias Rousset 3, 4 
2 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
4 SIMSMART - SIMulation pARTiculaire de Modèles Stochastiques
IRMAR - Institut de Recherche Mathématique de Rennes, Inria Rennes – Bretagne Atlantique
Abstract : We quantify the robustness of a trained network to input uncertainties with a stochastic simulation inspired by the field of Statistical Reliability Engineering. The robustness assessment is cast as a statistical hypothesis test: the network is deemed as locally robust if the estimated probability of failure is lower than a critical level. The procedure is based on an Importance Splitting simulation generating samples of rare events. We derive theoretical guarantees that are nonasymptotic w.r.t. sample size. Experiments tackling large scale networks outline the efficiency of our method making a low number of calls to the network function.
Document type :
Conference papers
Complete list of metadata
Contributor : Teddy Furon Connect in order to contact the contributor
Submitted on : Friday, October 29, 2021 - 3:22:09 PM
Last modification on : Saturday, August 6, 2022 - 3:32:55 AM


Files produced by the author(s)


  • HAL Id : hal-03407011, version 2


Karim Tit, Teddy Furon, Mathias Rousset. Efficient Statistical Assessment of Neural Network Corruption Robustness. NeurIPS 2021 - 35th Conference on Neural Information Processing Systems, Dec 2021, Sydney (virtual), Australia. ⟨hal-03407011v2⟩



Record views


Files downloads