Towards Learning and Verifying Invariants of Cyber-Physical Systems by Code Mutation

Abstract

Cyber-physical systems (CPS), which integrate algorithmic control with physical processes, often consist of physically distributed components communicating over a network. A malfunctioning or compromised component in such a CPS can lead to costly consequences, especially in the context of public infrastructure. In this short paper, we argue for the importance of constructing invariants (or models) of the physical behaviour exhibited by CPS, motivated by their applications to the control, monitoring, and attestation of components. To achieve this despite the inherent complexity of CPS, we propose a new technique for learning invariants that combines machine learning with ideas from mutation testing. We present a preliminary study on a water treatment system that suggests the efficacy of this approach, propose strategies for establishing confidence in the correctness of invariants, then summarise some research questions and the steps we are taking to investigate them.

arXiv commentShort paper accepted by the 21st International Symposium on Formal Methods (FM 2016)

Cited by in corpus (8)

• Anomaly Detection for a Water Treatment System Using Unsupervised Machine Learning
• Anomaly Detection for Water Treatment System based on Neural Network with Automatic Architecture Optimization
• Learning-Guided Network Fuzzing for Testing Cyber-Physical System Defences
• Log-based Anomaly Detection of CPS Using a Statistical Method
• Active Fuzzing for Testing and Securing Cyber-Physical Systems
• Code Integrity Attestation for PLCs using Black Box Neural Network Predictions
• Towards Systematically Deriving Defence Mechanisms from Functional Requirements of Cyber-Physical Systems
• Developing a Strong CPS Defender: An Evolutionary Approach