Model‐Inversion‐Resistant Physical Unclonable Neural Network Using Vertical NAND Flash Memory
Advanced Science · 2026-05 · 13 (25)
DOI: 10.1002/advs.74517 ↗Kurz gefasst
Fachartikel in der Zeitschrift Advanced Science, online erschienen am 27.02.2026. Verfasst von Sung-Ho Park und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Electrical and Computer Engineering and Inter-university Semiconductor Research Center, Seoul National University, Seoul, Republic of K…. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Research Foundation of Korea, MSIT, Seoul National University (BK21 FOUR Program) SK hynix Inc.
Abstract (Originalsprache)
The growing use of neural networks in privacy‐sensitive applications necessitates architectures that inherently protect both data and model integrity. We present a model‐inversion‐resistant physical unclonable neural network (PUNN) implemented on commercial vertical NAND (V‐NAND) flash memory. A physical unclonable layer generated through weak gate‐induced drain‐leakage erase exploits intrinsic device‐level variations to create chip‐unique conductance patterns that are concealable and unreproducible. Training is achieved using the forward‐forward (FF) algorithm, which eliminates the need for backward propagation and is fully compatible with the common‐source‐line structure of V‐NAND arrays. The resulting V‐NAND FF‐PUNN demonstrates hardware‐rooted resistance to model‐cloning and model‐inversion attacks, maintaining high accuracy under forward‐only learning. When the trained network weights are transferred to another chip, inference accuracy collapses due to chip‐specific randomness, confirming intrinsic non‐clonability. Furthermore, when applied to the MIT‐BIH electrocardiogram dataset, the system achieves competitive classification accuracy on real health data while entirely blocking data reconstruction by model‐inversion. This work establishes a scalable framework for secure, energy‐efficient, and privacy‐preserving neural computing directly on commercial flash memory.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Electrical and Computer Engineering and Inter-university Semiconductor Research Center, Seoul National University, Seoul, Republic of Korea.
- Research and Development Division, SK hynix Inc., Icheon, Republic of Korea.
ORCID-Profile: Jong-Ho Lee
Förderung
- National Research Foundation of Korea
- MSIT
- Seoul National University (BK21 FOUR Program) SK hynix Inc
Zitieren
APA
Park, S. H., Koo, R. H., Ko, J., Im, J., Yang, Y., Oh, M., Shin, D., Jung, G., & Lee, J. H. (2026). Model‐Inversion‐Resistant Physical Unclonable Neural Network Using Vertical NAND Flash Memory. Advanced Science, 13(25). https://doi.org/10.1002/advs.74517
Vancouver
Park SH, Koo RH, Ko J, Im J, Yang Y, Oh M, et al. Model‐Inversion‐Resistant Physical Unclonable Neural Network Using Vertical NAND Flash Memory. Advanced Science. 2026;13(25). doi:10.1002/advs.74517
BibTeX
@article{Park2026,
author = {Park, Sung-Ho and Koo, Ryun-Han and Ko, Jonghyun and Im, Jiseong and Yang, Yeongheon and Oh, Mingyun and Shin, Dongbeen and Jung, Gyuweon and Lee, Jong-Ho},
title = {Model‐Inversion‐Resistant Physical Unclonable Neural Network Using Vertical NAND Flash Memory},
journal = {Advanced Science},
year = {2026},
volume = {13},
number = {25},
doi = {10.1002/advs.74517}
}
EUVIMED