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.
Pros and Cons of Fault Injection Approaches for the Reliability Assessment of Deep Neural Networks / Ruospo, Annachiara; Matana Luza, Lucas; Bosio, Alberto; Traiola, Marcello; Dilillo, Luigi; Ernesto, Sanchez. - ELETTRONICO. - (2021), pp. 1-5. (Intervento presentato al convegno LATS 2021 : IEEE Latin-American Test Symposium tenutosi a Punta del Este, Uruguay nel Oct 27, 2021 - Oct 29, 2021) [10.1109/LATS53581.2021.9651807].
Pros and Cons of Fault Injection Approaches for the Reliability Assessment of Deep Neural Networks
Annachiara Ruospo;Ernesto Sanchez
2021
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.File | Dimensione | Formato | |
---|---|---|---|
2021_LATS_CR.pdf
non disponibili
Descrizione: Articolo Principale
Tipologia:
2. Post-print / Author's Accepted Manuscript
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
123.83 kB
Formato
Adobe PDF
|
123.83 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pros_and_Cons_of_Fault_Injection_Approaches_for_the_Reliability_Assessment_of_Deep_Neural_Networks.pdf
non disponibili
Tipologia:
2a Post-print versione editoriale / Version of Record
Licenza:
Non Pubblico - Accesso privato/ristretto
Dimensione
333.39 kB
Formato
Adobe PDF
|
333.39 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2923487