A journal of IEEE and CAA , publishes high-quality papers in English on original theoretical/experimental research and development in all areas of automation
Advanced Search
Volume 6 Issue 6
Nov.  2019

IEEE/CAA Journal of Automatica Sinica

  • JCR Impact Factor: 15.3, Top 1 (SCI Q1)
    CiteScore: 23.5, Top 2% (Q1)
    Google Scholar h5-index: 77， TOP 5
Turn off MathJax
Article Contents
Article Navigation >  IEEE/CAA Journal of Automatica Sinica  > 2019  >  6(6): 1404-1416
Haifeng Niu, Avimanyu Sahoo, Chandreyee Bhowmick and S. Jagannathan, "An Optimal Hybrid Learning Approach for Attack Detection in Linear Networked Control Systems," IEEE/CAA J. Autom. Sinica, vol. 6, no. 6, pp. 1404-1416, Nov. 2019. doi: 10.1109/JAS.2019.1911762
Citation: Haifeng Niu, Avimanyu Sahoo, Chandreyee Bhowmick and S. Jagannathan, "An Optimal Hybrid Learning Approach for Attack Detection in Linear Networked Control Systems," IEEE/CAA J. Autom. Sinica, vol. 6, no. 6, pp. 1404-1416, Nov. 2019. doi: 10.1109/JAS.2019.1911762
shu

An Optimal Hybrid Learning Approach for Attack Detection in Linear Networked Control Systems

doi: 10.1109/JAS.2019.1911762
Funds:  This work was supported in part by the National Science Foundation (IIP 1134721, ECCS 1406533, CMMI 1547042)
More Information
    Abstract
  • A novel learning-based attack detection and estimation scheme is proposed for linear networked control systems (NCS), wherein the attacks on the communication network in the feedback loop are expected to increase network induced delays and packet losses, thus changing the physical system dynamics. First, the network traffic flow is modeled as a linear system with uncertain state matrix and an optimal Q-learning based control scheme over finite-horizon is utilized to stabilize the flow. Next, an adaptive observer is proposed to generate the detection residual, which is subsequently used to determine the onset of an attack when it exceeds a predefined threshold, followed by an estimation scheme for the signal injected by the attacker. A stochastic linear system after incorporating network-induced random delays and packet losses is considered as the uncertain physical system dynamics. The attack detection scheme at the physical system uses the magnitude of the state vector to detect attacks both on the sensor and the actuator. The maximum tolerable delay that the physical system can tolerate due to networked induced delays and packet losses is also derived. Simulations have been performed to demonstrate the effectiveness of the proposed schemes.

     

    • FullText(HTML)
  • loading
    • References(24)
  • [1]
    P. Lee, A. Clark, L. Bushnell, and R. Poovendran, " A passivity framework for modeling and mitigating wormhole attacks on networked control systems,” IEEE Trans. Automatic Control, vol. 59, no. 12, pp. 3224–3237, 2014. doi: 10.1109/TAC.2014.2351871
    [2]
    Z. Lu, W. Wang, and C. Wang, " Modeling, evaluation and detection of jamming attacks in time-critical wireless applications,” IEEE Trans. Mobile Computing, vol. 13, no. 8, pp. 1746–1759, 2014. doi: 10.1109/TMC.2013.146
    [3]
    M. Zhu and S. Martínez, " On the performance analysis of resilient networked control systems under replay attacks,” IEEE Trans. Automatic Control, vol. 59, no. 3, pp. 804–808, 2014. doi: 10.1109/TAC.2013.2279896
    [4]
    A. Teixeira, I. Shames, H. Sandberg, and K. H. Johansson, " A secure control framework for resource-limited adversaries,” Automatica, vol. 51, pp. 135–148, 2015. doi: 10.1016/j.automatica.2014.10.067
    [5]
    H. Sandberg, S. Amin, and K. H. Johansson, " Cyberphysical security in networked control systems: An introduction to the issue,” IEEE Control Systems, vol. 35, no. 1, pp. 20–23, 2015. doi: 10.1109/MCS.2014.2364708
    [6]
    D. W. Browning, " Flow control in high-speed communication networks,” IEEE Trans. Communications, vol. 42, no. 7, pp. 2480–2489, 1994. doi: 10.1109/26.297859
    [7]
    C.-p. Li and E. Modiano, " Receiver-based flow control for networks in overload,” IEEE/ACM Trans. Networking, vol. 23, no. 2, pp. 616–630, 2015. doi: 10.1109/TNET.2014.2302445
    [8]
    H. Xu, S. Jagannathan, and F. L. Lewis, " Stochastic optimal control of unknown linear networked control system in the presence of random delays and packet losses,” Automatica, vol. 48, no. 6, pp. 1017–1030, 2012. doi: 10.1016/j.automatica.2012.03.007
    [9]
    Y. Chen, S. Kar, and J. M. Moura, " Cyber-physical systems: Dynamic sensor attacks and strong observability, ” in Proc. IEEE Int. Conf. Acoustics, Speech and Signal Processing, pp. 1752–1756.
    [10]
    H. Fawzi, P. Tabuada, and S. Diggavi, " Security for control systems under sensor and actuator attacks, ” in Proc. 51st IEEE Annual Conf. Decision and Control (CDC), , pp. 3412–3417.
    [11]
    Y. Mo and B. Sinopoli, " Secure control against replay attacks,” in Proc. 47th IEEE Annual Allerton Conf. Communication, Control, and Computing, Allerton, pp. 911–918, 2009.
    [12]
    Q. Zhao, H. Xu, and J. Sarangapani, " Finite-horizon near optimal adaptive control of uncertain linear discrete-time systems,” Optimal Control Applications and Methods, vol. 36, no. 6, pp. 853–872, 2015. doi: 10.1002/oca.2143
    [13]
    H. Niu and S. Jagannathan, " Optimal defense and control for cyberphysical systems,” in Proc. 2015 IEEE Symposium Series on Computational Intelligence, pp. 634–639.
    [14]
    A. Sahoo, V. Narayanan, and S. Jagannathan, " Optimal event-triggered control of uncertain linear networked control systems: A co-design approach,” in Proc. 2017 IEEE Symposium Series on Computational Intelligence (SSCI), pp. 1–6.
    [15]
    V. Narayanan and S. Jagannathan, " Event-triggered distributed control of nonlinear interconnected systems using online reinforcement learning with exploration,” IEEE Trans. Cybernetics, vol. 48, no. 9, pp. 2510–2519, 2018. doi: 10.1109/TCYB.2017.2741342
    [16]
    A. Sahoo and S. Jagannathan, " Stochastic optimal regulation of nonlinear networked control systems by using event-driven adaptive dynamic programming,” IEEE Trans. Cybernetics, vol. 47, no. 2, pp. 425–438, 2017.
    [17]
    H. Niu, C. Bhowmick, and S. Jagannathan, " Attack detection and approximation in nonlinear networked control systems using neural networks,” IEEE Trans. Neural Networks and Learning Systems, 2019. doi: 10.1109/TNNLS.2019.2900430
    [18]
    F. Pasqualetti, F. Dörfler, and F. Bullo, " Attack detection and identi-fication in cyber-physical systems,” IEEE Trans. Automatic Control, vol. 58, no. 11, pp. 2715–2729, 2013. doi: 10.1109/TAC.2013.2266831
    [19]
    F. L. Lewis, D. Vrabie, and V. L. Syrmos, Optimal Control. John Wiley & Sons, 2012.
    [20]
    P. Tague, D. Slater, R. Poovendran, and G. Noubir, " Linear programming models for jamming attacks on network traffic flows, ” in Proc. 6th Int. Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks and Workshops, pp. 207–216.
    [21]
    P. N. Raj and P. B. Swadas, " Dpraodv: a dyanamic learning system against blackhole attack in aodv based manet,” arXiv preprint arXiv:0909.2371, 2009.
    [22]
    J. Sarangapani, Neural Network Control of Nonlinear Discrete-time Systems, vol. 21. CRC press, 2006.
    [23]
    V. Narayanan and S. Jagannathan, " Distributed adaptive optimal regulation of uncertain large-scale interconnected systems using hybrid qlearning approach,” IET Control Theory &Applications, vol. 10, no. 12, pp. 1448–1457, 2016.
    [24]
    H. Xu, S. Jagannathan, and F. Lewis, " Stochastic optimal design for unknown linear discrete-time system zero-sum games in input-output form under communication constraints,” Asian J. Control, vol. 16, no. 5, pp. 1263–1276, 2014. doi: 10.1002/asjc.804
    • Related Articles
    • Supplements(0)

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索

    Figures(7)

    Get Citation
    PDF
    XML

    Article Metrics

    Article views (1689) PDF downloads(82) Cited by()

    Highlights

    • Attack detection and estimation scheme is proposed for an uncertain lin ear networked control system (NCS) using learning methodology where adversarial attacks are considered on both the network channels and the physical system. Due to random packet drops and delays, the dynamics of the NCS become unknown. In addition, the attacks induce changes in network traffic due to additional random packet dropouts and delays affecting the physical system dynamics and controller performance. An adaptive observer is introduced for attack detection.
    • By using a state-space network flow representation, a Q-learning based optimal flow controller is designed to stabilize the flow. The adaptive observer detects the attacks on the communication network. Upon de tection, estimation scheme is proposed to determine the injected attack signal. Attack detectability condition is derived for network attacks.
    • The physical system dynamics take into account the network imperfections which make the dynamics uncertain. A game-theory based event-triggered controller is designed that optimizes the triggering instants and control input simultaneously.
    • The magnitude of the physical system state vector serves as the detection signal for both network and physical system component attacks. Max imum tolerable delay due to attacks is derived for the physical system. Overall stability of the NCS is demonstrated.

    /

    DownLoad:  Full-Size Img  PowerPoint
    Return
    Return