Journal Home Online First Current Issue Archive For Authors Journal Information 中文版

Strategic Study of CAE >> 2021, Volume 23, Issue 2 doi: 10.15302/J-SSCAE-2021.02.013

Deep Learning and Industrial Internet Security: Application and Challenges

School of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing 100081, China

Funding project:中国工程院咨询项目“新一代工业互联网安全技术发展战略研究” (2020-XZ-02) Received: 2021-01-20 Revised: 2021-03-06 Available online: 2021-03-19

Next Previous

Abstract

Industrial Internet security is crucial for strengthening the manufacturing and network sectors of China. Deep learning, owing to its strong expression ability, good adaptability, and high portability, can support the establishment of an industrial Internet security system and method that is intelligent and autonomous. Therefore, it is of great value to promote the integrated innovation of deep learning and industrial Internet security. In this study, we analyze the development demand for industrial Internet security from the perspective of macro industrial environment, security technology, and deep learning system, and summarize the application status of deep learning to industrial Internet security in terms of device, control, network, application, and data layers. The security challenges faced by deep learning application to industrial Internet security primarily lie in model training and prediction, and key research directions include interpretability of deep neural networks, cost control of sample collection and calculation, imbalance of sample sets, reliability of model results, tradeoff between availability and security. Furthermore, some suggestion are proposed: a dynamic defense system in depth should be established in terms of overall security strategy; an application-driven and frontier exploration integrated method should be adopted to achieve breakthroughs regarding key technologies; and resources input should be raised for interdisciplinary fields to establish an industry–university–research institute joint research ecosystem.

Figures

Fig. 1

Fig. 2

References

[ 1 ] Li R Q, Wei S, Cheng Y H, et al. Research on typical application scenarios and standard system of artificial intelligence technology in intelligent manufacturing [J]. Strategic Study of CAE, 2018, 20(4): 112–117. Chinese. link1

[ 2 ] Li J H. Cyber security meets artificial intelligence: A survey [J]. Frontiers of Information Technology & Electronic Engineering, 2018, 19(12): 1462–1474. link1

[ 3 ] Amanullah M A, Habeeb R A A, Nasaruddin F H, et al. Deep learning and big data technologies for IoT security [J]. Computer Communications, 2020, 151(1): 495–517. link1

[ 4 ] Ha T, Dang T K, Le H, et al. Security and privacy issues in deep learning: A brief review [J]. SN Computer Science, 2020, 1(5): 1–15. link1

[ 5 ] Tsai S Y, Chang J Y. Parametric study and design of deep learning on leveling system for smart manufacturing [C]. Hsinchu: 2018 IEEE International Conference on Smart Manufacturing, Industrial & Logistics Engineering (SMILE), 2018. link1

[ 6 ] Wang J J, Ma Y L, Zhang L B, et al. Deep learning for smart manufacturing: Methods and applications [J]. Journal of Manufacturing Systems, 2018, 48(C): 144–156. link1

[ 7 ] Yu X H, Liu M, Jiang X H, et al. Industrial Internet architecture 2.0 [J]. Computer Integrated Manufacturing Systems, 2019, 25(12): 2983–2996. Chinese. link1

[ 8 ] Liu Y X, Wang J, Li J Q, et al. Zero-bias deep learning for accurate identification of Internet of things (IoT) devices [J]. IEEE Internet of Things Journal, 2020, 11(4): 2627–2634. link1

[ 9 ] Xu X J, Liu C, Feng Q, et al. Neural network-based graph embedding for cross-platform binary code similarity detection [C]. Dallas: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, 2017. link1

[10] Potluri S, Diedrich S. Deep learning based efficient anomaly detection for securing process control systems against injection attacks [C]. Vancouver: 2019 IEEE 15th International Conference on Automation Science and Engineering (CASE), 2019. link1

[11] Kyadige A, Ethan M, Rudd B K, et al. Learning from context: A multi-view deep learning architecture for malware detection [C]. San Francisco: 2020 IEEE Security and Privacy Workshops (SPW), 2020. link1

[12] Kozik R. Distributing extreme learning machines with apache spark for NetFlow-based malware activity detection [J]. Pattern Recognition Letters, 2018, 101: 14–20. link1

[13] Ferdowsi A, Saad W. Deep Learning-based dynamic watermarking for secure signal authentication in the Internet of things [C]. Kansas City: 2018 IEEE International Conference on Communications (ICC), 2018. link1

[14] Roy B, Cheung H. A deep learning approach for intrusion detection in Internet of things using bi-directional long short-term memory recurrent neural network [C]. Sydney: 2018 28th International Telecommunication Networks and Applications Conference, 2018. link1

[15] Wang X M, Zhang T, Wu R P, et al. CPGVA: Code property graph based vulnerability analysis by deep learning [C]. Stockholm: 2018 10th International Conference on Advanced Infocomm Technology (ICAIT), 2018. link1

[16] Masi I, Wu Y, Hassner T, et al. Deep face recognition: A survey [C]. Parana: 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 2018. link1

[17] Bernardi M, Cimitile M, Martinelli F, et al. Keystroke analysis for user identification using deep neural networks [C]. Budapest: 2019 International Joint Conference on Neural Networks (IJCNN), 2019. link1

[18] Yang C, Shen W M, Wang X B. The Internet of things in manufacturing: Key issues and potential applications [J]. IEEE Systems, Man, and Cybernetics Magazine, 2018, 4(1): 6–15. link1

[19] Yin B, Yin H, Wu Y L, et al. FDC: A secure federated deep learning mechanism for data collaborations in the Internet of things [J]. IEEE Internet of Things Journal, 2020, 7(7): 6348– 6359. link1

[20] Saha A, Subramany A, Pirsiavash H. Hidden trigger backdoor attacks [EB/OL]. (2020-07-15) [2020-12-15]. https://www.csee. umbc.edu/~hpirsiav/papers/hidden_aaai20.pdf. link1

[21] Hidano S, Murakami T, Katsumata S, et al. Exposing private user behaviors of collaborative filtering via model inversion techniques [J]. Proceedings on Privacy Enhancing Technologies, 2020 (3): 264–283. link1

[22] Boloor A, He X, Gill C, et al. Simple physical adversarial examples against end-to-end autonomous driving models [C]. Las Vegas: 2019 IEEE International Conference on Embedded Software and Systems (ICESS), 2019. link1

[23] Shafique M, Naseer M, Theocharides T, et al. Robust machine learning systems: Challenges current trends perspectives and the road ahead [J]. Design & Test IEEE, 2020, 37(2): 30–57. link1

[24] Wan M, Han M, Li L, et al. Effects of and defenses against adversarial attacks on a traffic light classification CNN [C]. New York: Proceedings of the 2020 ACM Southeast Conference, 2020. link1

[25] Buda M, Maki A, Mazurowski M A. A systematic study of the class imbalance problem in convolutional neural networks [J]. Neural Networks, 2017, 106: 249–259. link1

Related Research