SeDA: Secure and Efficient DNN Accelerators with Hardware/Software Synergy

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xuan, Wei, Wang, Zhongrui, Feng, Lang, Lin, Ning, Xuan, Zihao, Fu, Rongliang, Ho, Tsung-Yi, Jiao, Yuzhong, Liang, Luhong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915463769882624
author Xuan, Wei
Wang, Zhongrui
Feng, Lang
Lin, Ning
Xuan, Zihao
Fu, Rongliang
Ho, Tsung-Yi
Jiao, Yuzhong
Liang, Luhong
author_facet Xuan, Wei
Wang, Zhongrui
Feng, Lang
Lin, Ning
Xuan, Zihao
Fu, Rongliang
Ho, Tsung-Yi
Jiao, Yuzhong
Liang, Luhong
contents Ensuring the confidentiality and integrity of DNN accelerators is paramount across various scenarios spanning autonomous driving, healthcare, and finance. However, current security approaches typically require extensive hardware resources, and incur significant off-chip memory access overheads. This paper introduces SeDA, which utilizes 1) a bandwidth-aware encryption mechanism to improve hardware resource efficiency, 2) optimal block granularity through intra-layer and inter-layer tiling patterns, and 3) a multi-level integrity verification mechanism that minimizes, or even eliminates, memory access overheads. Experimental results show that SeDA decreases performance overhead by over 12% for both server and edge neural processing units (NPUs), while ensuring robust scalability.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18924
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle SeDA: Secure and Efficient DNN Accelerators with Hardware/Software Synergy
Xuan, Wei
Wang, Zhongrui
Feng, Lang
Lin, Ning
Xuan, Zihao
Fu, Rongliang
Ho, Tsung-Yi
Jiao, Yuzhong
Liang, Luhong
Hardware Architecture
Ensuring the confidentiality and integrity of DNN accelerators is paramount across various scenarios spanning autonomous driving, healthcare, and finance. However, current security approaches typically require extensive hardware resources, and incur significant off-chip memory access overheads. This paper introduces SeDA, which utilizes 1) a bandwidth-aware encryption mechanism to improve hardware resource efficiency, 2) optimal block granularity through intra-layer and inter-layer tiling patterns, and 3) a multi-level integrity verification mechanism that minimizes, or even eliminates, memory access overheads. Experimental results show that SeDA decreases performance overhead by over 12% for both server and edge neural processing units (NPUs), while ensuring robust scalability.
title SeDA: Secure and Efficient DNN Accelerators with Hardware/Software Synergy
topic Hardware Architecture
url https://arxiv.org/abs/2508.18924