Enregistré dans:
Détails bibliographiques
Auteurs principaux: Esposito, Giuseppe, Guerrero-Balaguera, Juan David, Condia, Josie Esteban Rodriguez, Reorda, Matteo Sonza
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2412.08466
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866913608035729408
author Esposito, Giuseppe
Guerrero-Balaguera, Juan David
Condia, Josie Esteban Rodriguez
Reorda, Matteo Sonza
author_facet Esposito, Giuseppe
Guerrero-Balaguera, Juan David
Condia, Josie Esteban Rodriguez
Reorda, Matteo Sonza
contents The reliability of Neural Networks has gained significant attention, prompting efforts to develop SW-based hardening techniques for safety-critical scenarios. However, evaluating hardening techniques using application-level fault injection (FI) strategies, which are commonly hardware-agnostic, may yield misleading results. This study for the first time compares two FI approaches (at the application level (APP) and instruction level (ISA)) to evaluate deep neural network SW hardening strategies. Results show that injecting permanent faults at ISA (a more detailed abstraction level than APP) changes completely the ranking of SW hardening techniques, in terms of both reliability and accuracy. These results highlight the relevance of using an adequate analysis abstraction for evaluating such techniques.
format Preprint
id arxiv_https___arxiv_org_abs_2412_08466
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Evaluating Different Fault Injection Abstractions on the Assessment of DNN SW Hardening Strategies
Esposito, Giuseppe
Guerrero-Balaguera, Juan David
Condia, Josie Esteban Rodriguez
Reorda, Matteo Sonza
Neural and Evolutionary Computing
The reliability of Neural Networks has gained significant attention, prompting efforts to develop SW-based hardening techniques for safety-critical scenarios. However, evaluating hardening techniques using application-level fault injection (FI) strategies, which are commonly hardware-agnostic, may yield misleading results. This study for the first time compares two FI approaches (at the application level (APP) and instruction level (ISA)) to evaluate deep neural network SW hardening strategies. Results show that injecting permanent faults at ISA (a more detailed abstraction level than APP) changes completely the ranking of SW hardening techniques, in terms of both reliability and accuracy. These results highlight the relevance of using an adequate analysis abstraction for evaluating such techniques.
title Evaluating Different Fault Injection Abstractions on the Assessment of DNN SW Hardening Strategies
topic Neural and Evolutionary Computing
url https://arxiv.org/abs/2412.08466