Layerwise Security Protection for Deep Neural Networks in Industrial Cyber Physical Systems
- 1 March 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (12) , 8797-8806
Abstract
Although deep neural networks (DNNs) have been increasingly applied in industrial cyber physical systems (ICPSs), they are vulnerable to security attacks due to the tight interaction between cyber elements and physical elements. In this article, we aim to protect the core IP of DNNs, i.e., the model weights, against security attacks. Different from conventional approaches, a layerwise protection framework is proposed to ensure the confidentiality of DNN model weights during the inference procedure such that the security quality is maximized, while satisfying the latency constraint of the DNN task. Based on the layerwise execution characteristics of DNN tasks, the encrypted layer-related weights are decrypted and fed to the next layer of DNN in plaintext. CPU-field programmable gate array (FPGA) coscheduling is considered to accelerate the execution of confidentiality protection, where CPU is utilized to conduct the decryption of weights and FPGA is used to perform the layer execution of DNN. Considering to provide optimal confidential protection for each layer, the problem is transformed into a quality of security maximization problem subject to layerwise execution constraint and deadline constraint of the DNN application. Due to the problem being NP-hard, a fast approximation algorithm is proposed to obtain the near-optimal solution under given real-time and security constraints. Extensive experiments and a real-life ICPS application evaluate the efficiency of the proposed techniques.Keywords
Funding Information
- National Natural Science Foundation of China (62072076)
- Natural Science Foundation of Guangdong Province (2021A1515011946)
This publication has 22 references indexed in Scilit:
- Energy-Aware Design of Stochastic Applications With Statistical Deadline and Reliability GuaranteesIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2018
- Stealing Hyperparameters in Machine Learning2018
- Fault injection attack on deep neural network2017
- Design optimization for security- and safety-critical distributed real-time applicationsMicroprocessors and Microsystems, 2017
- Design Automation of Cyber-Physical Systems: Challenges, Advances, and OpportunitiesIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2016
- Very deep convolutional neural network based image classification using small training sample size2015
- Industry 4.0Business & Information Systems Engineering, 2014
- Novel Low-Power and Highly Reliable Radiation Hardened Memory Cell for 65 nm CMOS TechnologyIEEE Transactions on Circuits and Systems I: Regular Papers, 2014
- A scalable GPU-based approach to accelerate the multiple-choice knapsack problem2012
- Adaptive scheduling server for power-aware real-time tasksACM Transactions on Embedded Computing Systems, 2004