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.
The increasing degree of connectivity in factory of the future (FoF) environments, with systems that were never designed for a networked environment in terms of their technical security nature, is accompanied by a number of security risks that must be considered. This leads to the necessity of relying on risk assessment-based approaches to reach a sufficiently mature cyber security management level. However, the lack of common definitions of cyber threat actors (CTA) poses challenges in untested environments such as the FoF. This paper analyses policy papers and reports from expert organizations to identify common definitions of CTAs. A significant consensus exists only on two common CTAs, while other CTAs are often either ignored or overestimated in their importance. The identified motivations of CTAs are contrasted with the specific characteristics of FoF environments to determine the most likely CTAs targeting FoF environments. Special emphasis is given to corporate competitors, as FoF environments probably provide better opportunities than ever for industrial espionage if they are not sufficiently secured. In this context, the study aims to draw attention to the research gaps in this area.