Deep Learning Algorithm using Transfer-Entropy measures for Anomaly Detection in Cyber-Physical Systems

  • Authors

    • Dr. Valliammal. N Assistant Professor(SS), Department of Computer Science, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore,Tamil Nadu, India
    • Dr. Padmavathi. G Professor,Department of Computer Science, Avinashilingam Institute for Home Science and Higher Education for Women, Coimbatore, Tamilnadu, India
  • Cyber-Physical Systems, Cyber Attacks, Transfer-Entropy, ANN, DNN, Causality Countermeasures.
  • Generally, in cyber-physical systems, there are various attacks detected such as internet-based load altering attacks, False-Data Injection Attack (FDIA), stealthy deception attacks, covert attacks, time synchronization attacks, etc. Over the past decades, attack detection and secure control system design has a high interest due to the rapid growth of cyber security challenges by sophisticated attacks in cyber-physical system like Internet-of-Things (IoT). Among various techniques, Transfer Entropy Measure (TEM) was introduced to detect four types of attacks like Denial-of-Service (DoS), replay, innovation-based deception attack and data injection attacks. Since, it discovers the interaction behavior among pairs of entities generating by each cyber-physical systems. As well, conventional machine-learning based attack detection mechanisms have been successfully employed in IoT i.e., wireless sensors to detect cyber-attacks. However, such mechanisms have less accuracy and scalability with high computational complexity. Hence in this article, a novel distributed deep learning algorithm is proposed for cyber attack detection in IoT since deep learning algorithms try to learn high-level features from data in an incremental manner and solve the problem end to end. Here, the transfer-entropy is measured with different parameters like node, network and channel for sensor measurements. Then, the obtained values are gathered as training dataset. Subsequently, Artificial Neural Network (ANN) and Deep Neural Network (DNN) are trained with training dataset to detect the existence of the attacks in cyber-physical system. Finally, the average detection accuracy values of ANN and DNN are evaluated through the simulation results as 98.9% and 99.6% respectively.



  • References

    1. [1] Liu Y, Ning P, & Reiter MK (2011), “False data injection attacks against state estimation in electric power gridsâ€, ACM Transactions on Information and System Security (TISSEC), 14(1), 13.

      [2] Mo Y, Chabukswar R, & Sinopoli B (2014), “Detecting integrity attacks on SCADA systemsâ€, IEEE Transactions on Control Systems Technology, 22(4), 1396-1407.

      [3] Shi D, Guo Z, Johansson KH, & Shi L (2018), “Causality countermeasures for anomaly detection in cyber-physical systemsâ€, IEEE Transactions on Automatic Control, 63(2), 386-401.

      [4] Mohsenian-Rad AH, & Leon-Garcia A (2011), “Distributed internet-based load altering attacks against smart power gridsâ€, IEEE Transactions on Smart Grid, 2(4), 667-674.

      [5] Beg OA, Johnson TT, & Davoudi A (2017), “Detection of false-data injection attacks in cyber-physical dc microgridsâ€, IEEE Transactions on Industrial Informatics, 13(5), 2693-2703.

      [6] Pasqualetti F, Dörfler F, & Bullo F (2013), “Attack detection and identification in cyber-physical systemsâ€, IEEE Transactions on Automatic Control, 58(11), 2715-2729.

      [7] Fawzi H, Tabuada P, & Diggavi S (2014), “Secure estimation and control for cyber-physical systems under adversarial attacksâ€, IEEE Transactions on Automatic Control, 59(6), 1454-1467.

      [8] Shi D, Elliott RJ, & Chen T (2017), “On Finite-State Stochastic Modeling and Secure Estimation of Cyber-Physical Systemsâ€, IEEE Trans. Automat. Contr., 62(1), 65-80.

      [9] Yu W, & Yang F (2015), “Detection of causality between process variables based on industrial alarm data using transfer entropyâ€, Entropy, 17(8), 5868-5887.

      [10] Duan P, Yang F, Chen T, & Shah SL (2013), “Direct causality detection via the transfer entropy approachâ€, IEEE transactions on control systems technology, 21(6), 2052-2066.

      [11] Duan P, Yang F, Shah SL, & Chen T (2015), “Transfer zero-entropy and its application for capturing cause and effect relationship between variablesâ€, IEEE Transactions on Control Systems Technology, 23(3), 855-867.

      [12] Marques VM, Munaro CJ, & Shah SL (2015), “Detection of causal relationships based on residual analysisâ€, IEEE Transactions on Automation Science and Engineering, 12(4), 1525-1534.

      [13] Tavallaee M, Bagheri E, Lu W, & Ghorbani, AA (2009), “A detailed analysis of the KDD CUP 99 data setâ€, In Computational Intelligence for Security and Defense Applications, 2009. CISDA 2009. IEEE Symposium on (pp. 1-6). IEEE.

      [14] KDD’99 Competition Dataset. Available on:, 1999.

  • Downloads

  • How to Cite

    Valliammal. N, D., & Padmavathi. G, D. (2019). Deep Learning Algorithm using Transfer-Entropy measures for Anomaly Detection in Cyber-Physical Systems. International Journal of Engineering & Technology, 7(4), 5084-5089.