Towards Learning Normality for Anomaly Detection in Industrial Control Networks - Emerging Management Mechanisms for the Future Internet Access content directly
Conference Papers Year : 2013

Towards Learning Normality for Anomaly Detection in Industrial Control Networks

Abstract

Recent trends in automation technology lead to a rising exposition of industrial control systems (ICS) to new vulnerabilities. This requires the introduction of proper security approaches in this field. Prevalent in ICS is the use of access control. Especially in critical infrastructures, however, preventive security measures should be complemented by reactive ones, such as intrusion detection. Beginning from the characteristics of automation networks we outline the implications for a suitable application of intrusion detection in this field. On this basis, an approach for creation of self-learning anomaly detection for ICS protocols is presented. In contrast to other approaches, it takes all network data into account: flow information, application data, and the packet order. We discuss the challenges that have to be solved in each step of the network data analysis to identify future aspects of research towards learning normality in industrial control networks.
Fichier principal
Vignette du fichier
978-3-642-38998-6_8_Chapter.pdf (397.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01489971 , version 1 (14-03-2017)

Licence

Attribution

Identifiers

Cite

Franka Schuster, Andreas Paul, Hartmut König. Towards Learning Normality for Anomaly Detection in Industrial Control Networks. 7th International Conference on Autonomous Infrastructure (AIMS), Jun 2013, Barcelona, Spain. pp.61-72, ⟨10.1007/978-3-642-38998-6_8⟩. ⟨hal-01489971⟩
79 View
615 Download

Altmetric

Share

Gmail Facebook X LinkedIn More