Emulating the Effects of Radiation-Induced Soft-Errors for the Reliability Assessment of Neural Networks - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Journal Articles IEEE Transactions on Emerging Topics in Computing Year : 2022

Emulating the Effects of Radiation-Induced Soft-Errors for the Reliability Assessment of Neural Networks

Abstract

Convolutional Neural Networks (CNNs) are currently one of the most widely used predictive models in machine learning. Recent studies have demonstrated that hardware faults induced by radiation fields, including cosmic rays, may significantly impact the CNN inference leading to wrong predictions. Therefore, ensuring the reliability of CNNs is crucial, especially for safety-critical systems. In the literature, several works propose reliability assessments of CNNs mainly based on statistically injected faults. This work presents a software emulator capable of injecting real faults retrieved from radiation tests. Specifically, from the device characterisation of a DRAM memory, we extracted event rates and fault models. The software emulator can reproduce their incidence and access their effect on CNN applications with a reliability assessment precision close to the physical one. Radiation-based physical injections and emulator-based injections are performed on three CNNs (LeNet-5) exploiting different data representations. Their outcomes are compared, and the software results evidence that the emulator is able to reproduce the faulty behaviours observed during the radiation tests for the targeted CNNs. This approach leads to a more concise use of radiation experiments since the extracted fault models can be reused to explore different scenarios (e.g., impact on a different application).
Fichier principal
Vignette du fichier
2021___TETC___Emulating_the_Effects_of_Radiation_Induced_Soft_Errors_for_the_Reliability_Assessment_of_Neural_Networks___HAL_Version.pdf (1.17 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

lirmm-03382380 , version 1 (18-11-2021)

Identifiers

Cite

Lucas Matana Luza, Annachiara Ruospo, Daniel Soderstrom, Carlo Cazzaniga, Maria Kastriotou, et al.. Emulating the Effects of Radiation-Induced Soft-Errors for the Reliability Assessment of Neural Networks. IEEE Transactions on Emerging Topics in Computing, 2022, 10 (4), pp.1867-1882. ⟨10.1109/TETC.2021.3116999⟩. ⟨lirmm-03382380⟩
74 View
201 Download

Altmetric

Share

Gmail Facebook X LinkedIn More