https://www.mdu.se/

mdu.sePublications
Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
DeepVigor: VulnerabIlity Value RanGes and FactORs for DNNs' Reliability Assessment
Tallinn Univ Technol, Tallinn, Estonia..
Tallinn Univ Technol, Tallinn, Estonia..
Tallinn Univ Technol, Tallinn, Estonia..
Mälardalen University, School of Innovation, Design and Engineering, Embedded Systems. Tallinn Univ Technol, Tallinn, Estonia.;Mälardalen Univ, Västerås, Sweden..
Show others and affiliations
2023 (English)In: 2023 IEEE EUROPEAN TEST SYMPOSIUM, ETS, IEEE, 2023Conference paper, Published paper (Refereed)
Abstract [en]

Deep Neural Networks (DNNs) and their accelerators are being deployed ever more frequently in safety-critical applications leading to increasing reliability concerns. A traditional and accurate method for assessing DNNs' reliability has been resorting to fault injection, which, however, suffers from prohibitive time complexity. While analytical and hybrid fault injection-/analyticalbased methods have been proposed, they are either inaccurate or specific to particular accelerator architectures. In this work, we propose a novel accurate, fine-grain, metric-oriented, and accelerator-agnostic method called DeepVigor that provides vulnerability value ranges for DNN neurons' outputs. An outcome of DeepVigor is an analytical model representing vulnerable and non-vulnerable ranges for each neuron that can be exploited to develop different techniques for improving DNNs' reliability. Moreover, DeepVigor provides reliability assessment metrics based on vulnerability factors for bits, neurons, and layers using the vulnerability ranges. The proposed method is not only faster than fault injection but also provides extensive and accurate information about the reliability of DNNs, independent from the accelerator. The experimental evaluations in the paper indicate that the proposed vulnerability ranges are 99.9% to 100% accurate even when evaluated on previously unseen test data. Also, it is shown that the obtained vulnerability factors represent the criticality of bits, neurons, and layers proficiently. DeepVigor is implemented in the PyTorch framework and validated on complex DNN benchmarks.

Place, publisher, year, edition, pages
IEEE, 2023.
Series
Proceedings of the European Test Symposium, ISSN 1530-1877
National Category
Computer Sciences
Identifiers
URN: urn:nbn:se:mdh:diva-65162DOI: 10.1109/ETS56758.2023.10174133ISI: 001032757100041Scopus ID: 2-s2.0-85161587299ISBN: 979-8-3503-3634-4 (print)OAI: oai:DiVA.org:mdh-65162DiVA, id: diva2:1822065
Conference
28th IEEE European Test Symposium (ETS), MAY 22-26, 2023, Venice, ITALY
Available from: 2023-12-21 Created: 2023-12-21 Last updated: 2023-12-21Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full textScopus

Authority records

Daneshtalab, Masoud

Search in DiVA

By author/editor
Daneshtalab, Masoud
By organisation
Embedded Systems
Computer Sciences

Search outside of DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetric score

doi
isbn
urn-nbn
Total: 28 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf