| Title | Learning-Based Time Delay Attack Characterization for Cyber-Physical Systems |
| Publication Type | Conference Paper |
| Year of Publication | 2019 |
| Authors | Lou, Xin, Tran, Cuong, Yau, David K.Y., Tan, Rui, Ng, Hongwei, Fu, Tom Zhengjia, Winslett, Marianne |
| Conference Name | 2019 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) |
| Date Published | Oct. 2019 |
| Publisher | IEEE |
| ISBN Number | 978-1-5386-8099-5 |
| Keywords | Air gaps, bidirectional long short-term memory units, built-in attack characterization scheme, composability, control engineering computing, control systems, cyber-attacks, Cyber-physical systems, Data models, deep learning model, Delay effects, delay systems, delays, Human Behavior, human factors, learning (artificial intelligence), learning-based time delay attack characterization, Logic gates, long time-sequence data, LSTM-based deep learning approach, Metrics, power engineering computing, power generation, power generation control, power plant control system, power plants, pubcrawl, recurrent neural nets, resilience, Resiliency, security of data, Smart grids, system control commands |
| Abstract | The cyber-physical systems (CPSes) rely on computing and control techniques to achieve system safety and reliability. However, recent attacks show that these techniques are vulnerable once the cyber-attackers have bypassed air gaps. The attacks may cause service disruptions or even physical damages. This paper designs the built-in attack characterization scheme for one general type of cyber-attacks in CPS, which we call time delay attack, that delays the transmission of the system control commands. We use the recurrent neural networks in deep learning to estimate the delay values from the input trace. Specifically, to deal with the long time-sequence data, we design the deep learning model using stacked bidirectional long short-term memory (LSTM) units. The proposed approach is tested by using the data generated from a power plant control system. The results show that the LSTM-based deep learning approach can work well based on data traces from three sensor measurements, i.e., temperature, pressure, and power generation, in the power plant control system. Moreover, we show that the proposed approach outperforms the base approach based on k-nearest neighbors. |
| URL | https://ieeexplore.ieee.org/document/8909732 |
| DOI | 10.1109/SmartGridComm.2019.8909732 |
| Citation Key | lou_learning-based_2019 |
Learning-Based Time Delay Attack Characterization for Cyber-Physical Systems