Pros and Cons of Fault Injection Approaches for the Reliability Assessment of Deep Neural Networks - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier
Conference Papers Year : 2021

Pros and Cons of Fault Injection Approaches for the Reliability Assessment of Deep Neural Networks

Abstract

In the last years, the adoption of Artificial Neural Networks (ANNs) in safety-critical applications has required an in-depth study of their reliability. For this reason, the research community has shown a growing interest in understanding the robustness of artificial computing models to hardware faults. Indeed, several recent studies have demonstrated that hardware faults induced by an external perturbation or due to silicon wear out and aging effects can significantly impact the ANN inference leading to wrong predictions. This work classifies and analyses the principal reliability assessment methodologies based on Fault Injection at different abstraction levels and with different procedures. Some of the most representative academic and industrial works proposed in the literature are described and the principal advantages, and drawbacks are highlighted.
Fichier principal
Vignette du fichier
2021___LATS___Pros_and_Cons_of_Fault_Injection_Approaches_for_the_Reliability_Assessment_of_Deep_Neural_Networks___HAL_Version.pdf (103.94 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

lirmm-03435567 , version 1 (18-11-2021)

Identifiers

Cite

Annachiara Ruospo, Lucas Matana Luza, Alberto Bosio, Marcello Traiola, Luigi Dilillo, et al.. Pros and Cons of Fault Injection Approaches for the Reliability Assessment of Deep Neural Networks. LATS 2021 - IEEE 22nd Latin American Test Symposium, Oct 2021, Punta del Este, Uruguay. pp.1-5, ⟨10.1109/LATS53581.2021.9651807⟩. ⟨lirmm-03435567⟩
110 View
363 Download

Altmetric

Share

More