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 using trusted execution environments (TEEs) to build trustworthy neural network ex...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10121428/ |
| _version_ | 1797826597160484864 |
|---|---|
| author | Mohammad Fakhruddin Babar Monowar Hasan |
| author_facet | Mohammad Fakhruddin Babar Monowar Hasan |
| author_sort | Mohammad Fakhruddin Babar |
| collection | DOAJ |
| description | 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 using trusted execution environments (TEEs) to build trustworthy neural network execution. This paper comprehensively surveys 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. We intend that this review will assist researchers and practitioners in understanding the state-of-the-art and identifying research problems. |
| first_indexed | 2024-04-09T12:34:56Z |
| format | Article |
| id | doaj.art-fff56a44072c49808e76c54f3d21c969 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-09T12:34:56Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-fff56a44072c49808e76c54f3d21c9692023-05-15T23:00:19ZengIEEEIEEE Access2169-35362023-01-0111457364574810.1109/ACCESS.2023.327419010121428Trusted Deep Neural Execution—A SurveyMohammad Fakhruddin Babar0https://orcid.org/0000-0003-3557-8809Monowar Hasan1https://orcid.org/0000-0002-2657-0402School of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USASchool of Electrical Engineering and Computer Science, Washington State University, Pullman, WA, USAThe 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 using trusted execution environments (TEEs) to build trustworthy neural network execution. This paper comprehensively surveys 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. We intend that this review will assist researchers and practitioners in understanding the state-of-the-art and identifying research problems.https://ieeexplore.ieee.org/document/10121428/Neural networkDNNtrusted executionTEETrustZoneSGX |
| spellingShingle | Mohammad Fakhruddin Babar Monowar Hasan Trusted Deep Neural Execution—A Survey IEEE Access Neural network DNN trusted execution TEE TrustZone SGX |
| title | Trusted Deep Neural Execution—A Survey |
| title_full | Trusted Deep Neural Execution—A Survey |
| title_fullStr | Trusted Deep Neural Execution—A Survey |
| title_full_unstemmed | Trusted Deep Neural Execution—A Survey |
| title_short | Trusted Deep Neural Execution—A Survey |
| title_sort | trusted deep neural execution x2014 a survey |
| topic | Neural network DNN trusted execution TEE TrustZone SGX |
| url | https://ieeexplore.ieee.org/document/10121428/ |
| work_keys_str_mv | AT mohammadfakhruddinbabar trusteddeepneuralexecutionx2014asurvey AT monowarhasan trusteddeepneuralexecutionx2014asurvey |