Efficient Statistical Assessment of Neural Network Corruption Robustness

Karim TIT · Teddy Furon · Mathias ROUSSET

Keywords: [ Deep Learning ] [ Robustness ]

[ Abstract ]
[ OpenReview
Thu 9 Dec 4:30 p.m. PST — 6 p.m. PST


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 non-asymptotic 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.

Chat is not available.