Cyber Physical Systems (CPS) integrate physical processes with electronic computing devices and digital communication channels. Their proper operation might be affected by two main sources of abnormality, security attacks and failures. The topics of fault diagnosis and security attack analysis in CPS have been studied extensively in a stand-alone manner. However, considering the co-existence of both sources of abnormality, faults and attacks, in a system and being able to differentiate among them, is an important and timely problem not yet addressed adequately. In this work, we study the internal communication environment of an Energy Aware Smart Home (EASH) system. More specifically, we formally define the problem of differentiating between component failures and network attacks in EASH, based on their effect on the communication behaviour. We formally show the correlation between such abnormality sources and provide a machine learning based framework for the differentiation problem. Our framework is evaluated using a simulation as well as a real-time testbed environment, demonstrating a promising accuracy in classification of over 85%. Based on the obtained experimental results, we also provide a detailed analysis on the considered classes and features used in the proposed approach, which can further improve the classification accuracy.

网络物理系统（CPS）将物理过程与电子计算设备和数字通信通道集成在一起。它们的正常运行可能受到异常的两个主要来源的影响，即安全攻击和故障。CPS中的故障诊断和安全攻击分析主题已经以独立的方式进行了广泛的研究。但是，考虑到系统中异常，故障和攻击这两种来源的共存并能够在其中进行区分是一个重要而及时的问题，尚未得到适当解决。在这项工作中，我们研究了能源感知智能家居（EASH）系统的内部通信环境。更具体地说，我们根据EASH中的组件故障和通信行为的影响，正式定义区分组件故障和网络攻击的问题。我们正式展示了此类异常源之间的相关性，并为基于机器学习的差异问题提供了框架。我们的框架是通过仿真和实时测试平台环境进行评估的，证明了超过85％的分类准确性。基于获得的实验结果，我们还对提议的方法中使用的考虑的类和特征进行了详细分析，这可以进一步提高分类的准确性。