Towards a Bayesian Approach for Assessing Fault Tolerance of Deep Neural Networks

摘要

This paper presents Bayesian Deep Learning based Fault Injection (BDLFI), a novel methodology for fault injection in neural networks (NNs) and more generally differentiable programs. BDLFI uses (1) Bayesian Deep Learning to model the propagation of faults, and (2) Markov Chain Monte Carlo inference to quantify the effect of faults on the outputs of a NN. We demonstrate BDLFI on two representative networks and present our results that challenge pre-existing results in the field.