Trusted Deep Neural Execution - A Survey

The growing use of deep neural networks (DNNs) in various applications has raised concerns about the security and privacy of model parameters and runtime execution. To address these concerns, researchers have proposed the use of trusted execution environments (TEEs) to build trustworthy neural netwo...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2023-01, Vol.11, p.1-1
Main Authors: Babar, Mohammad Fakhruddin, Hasan, Monowar
Format: Article
Language:English
Subjects:
Artificial neural networks
Codes
Computational modeling
Data models
DNN
Neural Network
Neural networks
Program processors
SGX
Surveys
TEE
Trust computing
Trusted Execution
TrustZone
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The growing use of deep neural networks (DNNs) in various applications has raised concerns about the security and privacy of model parameters and runtime execution. To address these concerns, researchers have proposed the use of trusted execution environments (TEEs) to build trustworthy neural network execution. This paper provides a comprehensive survey of the literature on trusted neural networks, viz., answering how to efficiently execute neural models inside trusted enclaves . We review the various TEE architectures and techniques employed to achieve secure neural network execution and provide a classification of existing work. Additionally, we discuss the challenges and present a few open issues. It is our intent that this review will assist researchers and practitioners to understand the state-of-the-art and identify research problems.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2023.3274190