The deterministic and restricted nature of industrial control system networks sets them apart from more open networks, such as local area networks in office environments. This improves the usability of network security, monitoring approaches that would be less feasible in more open environments. One of such approaches is machine learning based anomaly detection. Without proper customization for the special requirements of the industrial control system network environment, many existing anomaly or misuse detection systems will perform sub-optimally. A machine learning based approach could reduce the amount of manual customization required for different industrial control system networks. In this paper we analyze a possible set of features to be used in a machine learning based anomaly detection system in the real world industrial control system network environment under investigation. The network under investigation is represented by architectural drawing and results derived from network trace analysis. The network trace is captured from a live running industrial process control network and includes both control data and the data flowing between the control network and the office network. We limit the investigation to the IP traffic in the traces.
In this paper we compare three static code analysis tools. The tools represent three different approaches in the field of static analysis: fortify SCA is a non-annotation based heuristic analyzer, Splint represents an annotation based heuristic analyzer, and Frama-C an annotation based correct analyzer. The tools are compared by analysing their performance when checking a demonstration code with intentionally implemented errors.
Detecting network intrusions and anomalies in industrial control systems is growing in urgency. Such systems used to be isolated but are now being connected to the outside world. Even in the case of isolated networks, privileged users may still present various threats to the system, either accidentally or intentionally. Also malfunctions in devices may cause anomalous traffic. Anomaly detection based network monitoring and intrusion detection systems could be capable of discerning normal and aberrant traffic in industrial control systems, detecting security incidents in an early phase. In this paper we discuss the challenges for such a monitoring system. One of the challenges is which features best differentiate between anomalous and normal behaviour. In the analysis, special focus is placed on this selection.
The nature of the traffic in industrial control system network is markedly different from more open networks. Industrial control system networks should be far more restricted in what types of traffic diversity is present. This enables the usage of approaches that are currently not as feasible in open environments, such as machine learning based anomaly detection. Without proper customization for the special requirements of industrial control system network environment many existing anomaly or misuse detection systems will perform sub-optimally. Machine learning based approach would reduce the amount of manual customization required for different restricted network environments of which an industrial control system network is an good example of. In this paper we present an initial analysis of data received from a ethernet network of a live running industrial site. This includes both control data and the data flowing between the control network and the office network. A set of possible features to be used for detecting anomalies is studied for this environment.