https://www.mdu.se/

mdu.sePublikationer
Ändra sökning
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • 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..
Mälardalens universitet, Akademin för innovation, design och teknik, Inbyggda system. Tallinn Univ Technol, Tallinn, Estonia.;Mälardalen Univ, Västerås, Sweden..
Visa övriga samt affilieringar
2023 (Engelska)Ingår i: 2023 IEEE EUROPEAN TEST SYMPOSIUM, ETS, IEEE, 2023Konferensbidrag, Publicerat paper (Refereegranskat)
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.

Ort, förlag, år, upplaga, sidor
IEEE, 2023.
Serie
Proceedings of the European Test Symposium, ISSN 1530-1877
Nationell ämneskategori
Datavetenskap (datalogi)
Identifikatorer
URN: urn:nbn:se:mdh:diva-65162DOI: 10.1109/ETS56758.2023.10174133ISI: 001032757100041Scopus ID: 2-s2.0-85161587299ISBN: 979-8-3503-3634-4 (tryckt)OAI: oai:DiVA.org:mdh-65162DiVA, id: diva2:1822065
Konferens
28th IEEE European Test Symposium (ETS), MAY 22-26, 2023, Venice, ITALY
Tillgänglig från: 2023-12-21 Skapad: 2023-12-21 Senast uppdaterad: 2023-12-21Bibliografiskt granskad

Open Access i DiVA

Fulltext saknas i DiVA

Övriga länkar

Förlagets fulltextScopus

Person

Daneshtalab, Masoud

Sök vidare i DiVA

Av författaren/redaktören
Daneshtalab, Masoud
Av organisationen
Inbyggda system
Datavetenskap (datalogi)

Sök vidare utanför DiVA

GoogleGoogle Scholar

doi
isbn
urn-nbn

Altmetricpoäng

doi
isbn
urn-nbn
Totalt: 31 träffar
RefereraExporteraLänk till posten
Permanent länk

Direktlänk
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annat format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annat språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf