Reliability of Deep Neural Networks: Impact and Open Issues
Editor’s notes: This article introduces a statistical fault injection approach to evaluate the resilience of deep-neural-network applications against permanent faults in synaptic weights, while also discussing open challenges and emerging trends. —Jyotika Athavale, Synopsys, USA —Haralampos-G. Stratigopoulos, Sorbonne Université, CNRS, LIP6, France
Authors
- Ernesto Sánchez (ORCID: https://orcid.org/0000-0002-7042-295X)
- Salvatore Eugenio Pappalardo (ORCID: https://orcid.org/0000-0002-1546-644X)
- V. Turco (ORCID: https://orcid.org/0009-0001-0754-8189)
- Alberto Bosio (ORCID: https://orcid.org/0000-0001-6116-7339)
- Annachiara Ruospo (ORCID: https://orcid.org/0000-0003-2040-9762)
Institutions
- Université Claude Bernard Lyon 1 (FR)
- École Centrale de Lyon (FR)
- Centre National de la Recherche Scientifique (FR)
- Politecnico di Torino (IT)
- Institut des Nanotechnologies de Lyon (FR)
- Institut National des Sciences Appliquées de Lyon (FR)
- École d'Ingénieurs en Chimie et Sciences du Numérique (FR)
Publication Details
- Journal
- IEEE Design and Test
- Published
- 2025-02-20
- DOI
- https://doi.org/10.1109/mdat.2025.3544125
- Primary Topic
- Adversarial Robustness in Machine Learning
- Type
- article
- Field-Weighted Citation Impact
- 0.00