ASIC Tape-Out of the First Side-Channel-Protected Neural Network Design
IEEE Design & Test · 2026-06 · 43 (3) · 14-22
DOI: 10.1109/mdat.2026.3670063 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Design & Test, 2026-06. Verfasst von Anuj Dubey und 2 weiteren Autor:innen. Die Arbeit nennt 14 Literaturangaben. Gefördert von: Semiconductor Research Corporation.
Abstract (Originalsprache)
Editor’s notes: Edge AI faces data theft via sde-channel attacks. This work is the first ML classifier ASIC built entirely with open-source tools to secure AI at the silicon level. —Ramesh Karri, New York University, USA
Förderung
- Semiconductor Research Corporation
Zitieren
APA
Dubey, A., Aysu, A., & Cammarota, R. (2026). ASIC Tape-Out of the First Side-Channel-Protected Neural Network Design. IEEE Design & Test, 43(3), 14-22. https://doi.org/10.1109/mdat.2026.3670063
Vancouver
Dubey A, Aysu A, Cammarota R. ASIC Tape-Out of the First Side-Channel-Protected Neural Network Design. IEEE Design & Test. 2026;43(3):14-22. doi:10.1109/mdat.2026.3670063
BibTeX
@article{Dubey2026,
author = {Dubey, Anuj and Aysu, Aydin and Cammarota, Rosario},
title = {ASIC Tape-Out of the First Side-Channel-Protected Neural Network Design},
journal = {IEEE Design & Test},
year = {2026},
volume = {43},
number = {3},
pages = {14--22},
doi = {10.1109/mdat.2026.3670063}
}
EUVIMED