short-paper

Public Access

Real-Time Scheduling of TrustZone-enabled DNN Workloads

Authors:

Mohammad Fakhruddin Babar,

Monowar HasanAuthors Info & Claims

CPSIoTSec '22: Proceedings of the 4th Workshop on CPS & IoT Security and Privacy

Pages 63 - 69

https://doi.org/10.1145/3560826.3563386

Published: 07 November 2022 Publication History

Abstract

Limited resources in embedded devices often hinder the execution of computation-heavy machine learning processes. Running deep neural network (DNN) workloads while preserving the integrity of the model parameters and without compromising temporal constraints of real-time applications, is a challenging problem. Although secure enclaves such as ARM TrustZone can ensure the integrity of applications, off-the-shelf implementations are often infeasible for DNN workloads - especially those with real-time requirements - due to additional resource and temporal constraints. This paper presents a real-time scheduling framework that enables the execution of resource-intensive DNN workloads inside TrustZone-enabled secure enclaves. Our approach reduces the resource overhead by fusing multiple layers of multiple tasks and running them all together inside the enclaves while retaining real-time grantees. We derive mathematical conditions that will allow the designer to test the feasibility of deploying DNN workload in a TrustZone-enabled system. Our comparisons with a standard fixed-priority real-time scheduler show that we can schedule up to 21.33% more tasksets in higher utilization (e.g., > 80%) scenarios.

References

[1]

Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012), 1097--1105.

[2]

Linaro. Accessed on 2021. Open portable trusted execution environment. https: //www.op-tee.org

[3]

Howard AG, Zhu M, Chen B, Kalenichenko D,WangW,Weyand T, Andreetto M, Adam H (2017) MobiLeNets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:170404861

[4]

"GlobalPlatform", TEE system architecture, 2011, [online] Available: http://www.globalplatform.org/specificationsdevice.asp.

[5]

Intel Software Guard Extensions (Intel SGX) SDK for Linux OS. http://intel.com. Accessed: 2020-06--30.

[6]

F. Mo, A. S. Shamsabadi, K. Katevas, S. Demetriou, I. Leontiadis, A. Cavallaro, and H. Haddadi, "DarkneTZ: Towards model privacy at the edge using trusted execution environments," in International Conference on Mobile Systems, Applications, and Services (MobiSys), 2020, p. 161--174.

Digital Library

[7]

P. M. VanNostrand, I. Kyriazis, M. Cheng, T. Guo, and R. J. Walls, "Confidential deep learning: Executing proprietary models on untrusted devices," in arXiv:1908.10730, 2019.

[8]

A. Gangal, M. Ye and S. Wei, "HybridTEE: Secure Mobile DNN Execution Using Hybrid Trusted Execution Environment," 2020 Asian Hardware Oriented Security and Trust Symposium (AsianHOST), 2020, pp. 1--6.

[9]

M. Sabt, M. Achemlal and A. Bouabdallah, "Trusted Execution Environment: What It is, and What It is Not," 2015 IEEE Trustcom/BigDataSE/ISPA, 2015, pp. 57--64.

Digital Library

[10]

Intel Software Guard Extensions (Intel SGX) SDK for Linux OS. http://intel.com. Accessed: 2020-06--30.

[11]

Najafabadi MM, Villanustre F, Khoshgoftaar TM, Seliya N,Wald R, Muharemagic E (2015) Deep learning applications and challenges in big data analytics. J Big Data 2(1):1

[12]

Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT Press, Cambridge

Digital Library

[13]

"OP-TEE (Open Portable Trusted Execution Environment)." https://www.op-tee. org/. Accessed: 2018-05--27.

[14]

J. Redmon, S. Divvala, R. Girshick, and A. Farhadi, "You only look once: Unified, real-time object detection," in Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 779--788

[15]

Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems, pp 1097--1105.

Digital Library

[16]

Simone Bianco, Remi Cadene, Luigi Celona, and Paolo Napoletano. 2018. Benchmark Analysis of Representative Deep Neural Network Architectures. IEEE Access 6 (2018), 64270--64277.

[17]

Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. http://pjreddie.com/darknet/.

[18]

Anway Mukherjee, Tanmaya Mishra, Thidapat Chantem, Nathan Fisher, and Ryan Gerdes. 2019. Optimized trusted execution for hard real-time applications on COTS processors. In Proceedings of the 27th International Conference on Real- Time Networks and Systems (RTNS '19). Association for Computing Machinery, New York, NY, USA, 50--60. https://doi.org/10.1145/3356401.3356419

Digital Library

[19]

R. Liu and M. Srivastava, "Protc: Protecting drone's peripherals through arm trustzone," in Proceedings of the 3rdWorkshop on Micro Aerial Vehicle Networks, Systems, and Applications, pp. 1--6, ACM, 2017.

[20]

Lehoczky, John, Lui Sha, and Yuqin Ding. "The rate monotonic scheduling algorithm: Exact characterization and average case behavior." RTSS. Vol. 89. 1989.

[21]

Joseph Redmon. 2013--2016. Darknet: Open Source Neural Networks in C. http://pjreddie.com/darknet/.

[22]

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015.Going deeper with convolutions. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 1--9.

[23]

Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 770--778.

[24]

Gao Huang, Zhuang Liu, Laurens Van Der Maaten, and Kilian QWeinberger.2017. Densely connected convolutional networks. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. 4700--4708.

[25]

T. Alves and D. Felton. 2004. TrustZone: Integrated hardware and software security. Tech. In-Depth 3, 4 (2004), 18--24.

[26]

Sorin Manolache, Petru Eles, and Zebo Peng. 2004. Schedulability analysis of applications with stochastic task execution times. ACM Trans. Embed. Comput. Syst. 3, 4 (November 2004), 706--735. https://doi.org/10.1145/1027794.1027797

Digital Library

[27]

C. L. Liu and J. W. Layland, "Scheduling algorithms for multiprogramming in a hard-real-time environment," Journal of the ACM (JACM), vol. 20, no. 1, pp. 46--61, 1973.

[28]

Z. Chen, G. Li, K. Pattabiraman, and N. DeBardeleben. BinFI: an efficient fault injector for safety-critical machine learning systems. In International Conference for High Performance Computing, Networking, Storage and Analysis (SC), 2019.

Digital Library

[29]

G. Li, K. Pattabiraman, and N. DeBardeleben. Tensorfi: A configurable fault injector for tensorflow applications. In IEEE International Symposium on Software Reliability Engineering Workshops (ISSREW), 2018.

[30]

A. S. Rakin, Z. He, and D. Fan. Bit-flip attack: Crushing neural network with progressive bit search. In IEEE/CVF International Conference on Computer Vision, 2019.

[31]

Benali Amjoud, Ayoub, and Mustapha Amrouch. "Convolutional Neural Networks Backbones for Object Detection." Image and Signal Processing: 9th International Conference, ICISP 2020, Marrakesh, Morocco, June 4--6, 2020, Proceedings vol. 12119 282--289. 5 Jun. 2020,

[32]

Y. Xiang, Y. Wang, H. Choi, M. Karimi and H. Kim, "AegisDNN: Dependable and Timely Execution of DNN Tasks with SGX," 2021 IEEE Real-Time Systems Symposium (RTSS), 2021, pp. 68--81.

[33]

Taegyeong Lee, Zhiqi Lin, Saumay Pushp, Caihua Li, Yunxin Liu, Youngki Lee, Fengyuan Xu, Chenren Xu, Lintao Zhang, and Junehwa Song. 2019. Occlumency: Privacy-preserving Remote Deep-learning Inference Using SGX. In The 25th Annual International Conference on Mobile Computing and Networking (MobiCom '19). Association for Computing Machinery, New York, NY, USA, Article 46, 1--17. https://doi.org/10.1145/3300061.3345447

Digital Library

[34]

Multi-layer task fusion model implementation, https://github.com/CPS2RL/Scheduling-of-TrustZone-enabled-DNNWorkloads

[35]

S. Lee and S. Nirjon, "SubFlow: A Dynamic Induced-Subgraph Strategy Toward Real-Time DNN Inference and Training," 2020 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), 2020, pp. 15--29.

Cited By

Mo FTarkhani ZHaddadi H(2024)Machine Learning with Confidential Computing: A Systematization of KnowledgeACM Computing Surveys10.1145/367000756:11(1-40)Online publication date: 29-Jun-2024
https://dl.acm.org/doi/10.1145/3670007
Queyrut SSchiavoni VFelber P(2023)Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)10.1109/ICDCS57875.2023.00069(626-637)Online publication date: Jul-2023
https://doi.org/10.1109/ICDCS57875.2023.00069
Babar MHasan M(2023)Trusted Deep Neural Execution—A SurveyIEEE Access10.1109/ACCESS.2023.327419011(45736-45748)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3274190

Index Terms

Real-Time Scheduling of TrustZone-enabled DNN Workloads
1. Security and privacy
  1. Security in hardware
    1. Embedded systems security
  2. Systems security

Recommendations

Scheduling Security-Critical Real-Time Applications on Clusters

Security-critical real-time applications such as military aircraft flight control systems have mandatory security requirements in addition to stringent timing constraints. Conventional real-time scheduling algorithms, however, either disregard ...
Dynamic Scheduling of Hard Real-Time Tasks and Real-Time Threads

The authors investigate the dynamic scheduling of tasks with well-defined timing constraints. They present a dynamic uniprocessor scheduling algorithm with an O(n log n) worst-case complexity. The preemptive scheduling performed by the algorithm is ...
Efficient CUDA stream management for multi-DNN real-time inference on embedded GPUs
Abstract
Deep Neural Networks (DNNs) are widely used in Cyber–Physical Systems (CPS) that often involve multiple DNN tasks with varying real-time requirements. These tasks need to be deployed on a single embedded hardware platform with limited resources, ...

Comments

Information & Contributors

Information

Published In

cover image ACM Conferences

CPSIoTSec '22: Proceedings of the 4th Workshop on CPS & IoT Security and Privacy

November 2022

77 pages

ISBN:9781450398763

DOI:10.1145/3560826

Program Chairs:
Earlence Fernandes
University of California, San Diego, USA
,
Cristina Alcaraz
University of Malaga, Spain

Copyright © 2022 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGSAC: ACM Special Interest Group on Security, Audit, and Control

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 November 2022

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Funding Sources

NSF (National Science Foundation)

Conference

CCS '22

Sponsor:

SIGSAC

CCS '22: 2022 ACM SIGSAC Conference on Computer and Communications Security

November 7, 2022

CA, Los Angeles, USA

Upcoming Conference

CCS '24

Sponsor:
sigsac

ACM SIGSAC Conference on Computer and Communications Security

October 14 - 18, 2024

Salt Lake City , UT , USA

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
255
Total Downloads

Downloads (Last 12 months)148
Downloads (Last 6 weeks)10

Reflects downloads up to 27 Jul 2024

Other Metrics

View Author Metrics

Citations

Cited By

Mo FTarkhani ZHaddadi H(2024)Machine Learning with Confidential Computing: A Systematization of KnowledgeACM Computing Surveys10.1145/367000756:11(1-40)Online publication date: 29-Jun-2024
https://dl.acm.org/doi/10.1145/3670007
Queyrut SSchiavoni VFelber P(2023)Mitigating Adversarial Attacks in Federated Learning with Trusted Execution Environments2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS)10.1109/ICDCS57875.2023.00069(626-637)Online publication date: Jul-2023
https://doi.org/10.1109/ICDCS57875.2023.00069
Babar MHasan M(2023)Trusted Deep Neural Execution—A SurveyIEEE Access10.1109/ACCESS.2023.327419011(45736-45748)Online publication date: 2023
https://doi.org/10.1109/ACCESS.2023.3274190

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents