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

Subho S. Banerjee, James Cyriac, Saurabh Jha, Zbigniew T. Kalbarczyk, Ravishankar K. Iyer

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

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.

Original languageEnglish (US)
Title of host publicationProceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages25-26
Number of pages2
ISBN (Electronic)9781728130286
DOIs
StatePublished - Jun 2019
Event49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019 - Portland, United States
Duration: Jun 24 2019Jun 27 2019

Publication series

NameProceedings - 49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019

Conference

Conference49th Annual IEEE/IFIP International Conference on Dependable Systems and Networks - Supplemental Volume, DSN-S 2019
Country/TerritoryUnited States
CityPortland
Period6/24/196/27/19

Keywords

  • Fault Injection
  • Neural Networks

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Information Systems
  • Information Systems and Management
  • Computer Networks and Communications

Fingerprint

Dive into the research topics of 'Towards a Bayesian Approach for Assessing Fault Tolerance of Deep Neural Networks'. Together they form a unique fingerprint.

Cite this