A fundamental problem in the realm of cyber-physical security of smart water networks is attack detection, a key step towards designing adequate countermeasures. This task is typically carried out by algorithms that analyze time series of process data. However, the nature of the data available to develop these algorithms limits their capabilities: by relying on process data only, one cannot distinguish a cyber-attack from the failure of a system’s component or identify the root cause of an attack. Here, we show that these limitations can be addressed through the joint analysis of process and network data—with the latter representing the information exchanged between the components constituting the Industrial Control System, such as sensors and Programmable Logic Controllers (PLCs). For this purpose, we utilize a dataset generated by digital hydraulic simulator (DHALSIM)—a numerical modelling platform built on a two-way interaction between EPANET version 2.2 and a network emulation tool—which is extended here to include a framework for launching cyber-physical attacks. This paper presents a dataset with realistic network information of a smart water network under cyber-physical attacks and presents an analysis of how that information can enable the development of better intrusion detection systems that can localize and identify attacks. Through this analysis, the dataset provided here, and the open-source availability of DHALSIM, our work paves the way to a novel class of analytics for actionable detection.

Recently, reconstruction-based anomaly detection was proposed as an effective technique to detect attacks in dynamic industrial control networks. Unlike classical network anomaly detectors that observe the network traffic, reconstruction-based detectors operate on the measured sensor data, leveraging physical process models learned a priori. In this work, we investigate different approaches to evade prior-work reconstruction-based anomaly detectors by manipulating sensor data so that the attack is concealed. We find that replay attacks (commonly assumed to be very strong) show bad performance (i.e., increasing the number of alarms) if the attacker is constrained to manipulate less than 95% of all features in the system, as hidden correlations between the features are not replicated well. To address this, we propose two novel attacks that manipulate a subset of the sensor readings, leveraging learned physical constraints of the system. Our attacks feature two different attacker models: A white box attacker, which uses an optimization approach with a detection oracle, and a black box attacker, which uses an autoencoder to translate anomalous data into normal data. We evaluate our implementation on two different datasets from the water distribution domain, showing that the detector's Recall drops from 0.68 to 0.12 by manipulating 4 sensors out of 82 in WADI dataset. In addition, we show that our black box attacks are transferable to different detectors: They work against autoencoder-, LSTM-, and CNN-based detectors. Finally, we implement and demonstrate our attacks on a real industrial testbed to demonstrate their feasibility in real-time.