Yoriyuki Yamagata

Takumi Akazaki, Shuang Liu, Yoriyuki Yamagata et al.

With the rapid development of software and distributed computing, Cyber-Physical Systems (CPS) are widely adopted in many application areas, e.g., smart grid, autonomous automobile. It is difficult to detect defects in CPS models due to the complexities involved in the software and physical systems. To find defects in CPS models efficiently, robustness guided falsification of CPS is introduced. Existing methods use several optimization techniques to generate counterexamples, which falsify the given properties of a CPS. However those methods may require a large number of simulation runs to find the counterexample and is far from practical. In this work, we explore state-of-the-art Deep Reinforcement Learning (DRL) techniques to reduce the number of simulation runs required to find such counterexamples. We report our method and the preliminary evaluation results.

Jun Inoue, Yoriyuki Yamagata, Yuqi Chen et al.

In this paper, we propose and evaluate the application of unsupervised machine learning to anomaly detection for a Cyber-Physical System (CPS). We compare two methods: Deep Neural Networks (DNN) adapted to time series data generated by a CPS, and one-class Support Vector Machines (SVM). These methods are evaluated against data from the Secure Water Treatment (SWaT) testbed, a scaled-down but fully operational raw water purification plant. For both methods, we first train detectors using a log generated by SWaT operating under normal conditions. Then, we evaluate the performance of both methods using a log generated by SWaT operating under 36 different attack scenarios. We find that our DNN generates fewer false positives than our one-class SVM while our SVM detects slightly more anomalies. Overall, our DNN has a slightly better F measure than our SVM. We discuss the characteristics of the DNN and one-class SVM used in this experiment, and compare the advantages and disadvantages of the two methods.

Yoshiyuki Harada, Yoriyuki Yamagata, Osamu Mizuno et al.

Detecting anomalies of a cyber physical system (CPS), which is a complex system consisting of both physical and software parts, is important because a CPS often operates autonomously in an unpredictable environment. However, because of the ever-changing nature and lack of a precise model for a CPS, detecting anomalies is still a challenging task. To address this problem, we propose applying an outlier detection method to a CPS log. By using a log obtained from an actual aquarium management system, we evaluated the effectiveness of our proposed method by analyzing outliers that it detected. By investigating the outliers with the developer of the system, we confirmed that some outliers indicate actual faults in the system. For example, our method detected failures of mutual exclusion in the control system that were unknown to the developer. Our method also detected transient losses of functionalities and unexpected reboots. On the other hand, our method did not detect anomalies that were too many and similar. In addition, our method reported rare but unproblematic concurrent combinations of operations as anomalies. Thus, our approach is effective at finding anomalies, but there is still room for improvement.

Ling Fang, Yoriyuki Yamagata, Yutaka Oiwa

If a Micro Processor Unit (MPU) receives an external electric signal as noise, the system function will freeze or malfunction easily. A new resilience strategy is implemented in order to reset the MPU automatically and stop the MPU from freezing or malfunctioning. The technique is useful for embedded systems which work in non-human environments. However, evaluating resilience strategies is difficult because their effectiveness depends on numerous, complex, interacting factors. In this paper, we use probabilistic model checking to evaluate the embedded systems installed with the above mentioned new resilience strategy. Qualitative evaluations are implemented with 6 PCTL formulas, and quantitative evaluations use two kinds of evaluation. One is system failure reduction, and the other is ADT (Average Down Time), the industry standard. Our work demonstrates the benefits brought by the resilience strategy. Experimental results indicate that our evaluation is cost-effective and reliable.