Home // ICAS 2016, The Twelfth International Conference on Autonomic and Autonomous Systems // View article

Threat Evaluation Based on Automatic Sensor Signal Characterisation and Anomaly Detection

Authors:
Anatolij Bezemskij
Richard John Anthony
Diane Gan
George Loukas

Keywords: Anomaly detection; Autonomous behaviour; Threat; Cyber-Security; Signature.

Abstract:
Autonomous cyber physical systems are increasingly common in a wide variety of application domains, with a correspondingly wide range of functionalities and types of sensing and actuation. At the same time, the variety and frequency of cyber attacks is increasing in correspondence with the increasing popularity and functionality of these systems, from in-vehicle driver assistance to smart city infrastructure and robotics. These technologies rely on a variety of sensors, actuating nodes and control communications. Each sensor adds context by which the autonomous system can better understand its environment, but each sensor also provides opportunities for attack, as has been observed in a variety of attacks on different systems. It would therefore be extremely useful to develop mechanisms by which these systems can detect cyber and cyber-physical attacks, including previously unknown attacks, and preferably in an autonomous manner. For this to be feasible, they need to be able themselves to learn their own "normal" operational conditions and accordingly autonomously detect abnormal conditions. In this paper, we introduce a model to observe signal characteristics, including noise level patterns, on sensor data streams and incorporate this information to differentiate between normal or abnormal behaviour of a robotic vehicle. This model forms the basis of an automated threat detection scheme, which we test using a purpose-built testbed. Experiments are conducted in a controlled environment using stochastic elements to introduce certain levels of randomness during the experiment. The results indicate that the system is able to distinguish the behaviour of a robotic vehicle under different levels of environmental volatility and is able to identify a sensory channel attack against it.

Pages: 25 to 31

Copyright: Copyright (c) IARIA, 2016

Publication date: June 26, 2016

Published in: conference

ISSN: 2308-3913

ISBN: 978-1-61208-483-1

Location: Lisbon, Portugal

Dates: from June 26, 2016 to June 30, 2016