Probabilistic Method for Anomalies Detection Based on the Analysis of Cyber Parameters in a Group of Mobile Robots

Abstract

This article is devoted to the issues of ensuring the security of a group of mobile robots in the implementation of attacks aimed at the property of accessibility of information and the availability of network nodes. The article presents a method for detecting an abnormal behavior of a network node based on the analysis by the group members of the parameters: residual energy and network load. Analysis of the behavior of individual robots relative to general behavior using probabilistic methods avoids the problem of creating a reference distribution for describing the behavior of a node, as well as creating a signature database for detecting anomalies. The developed method demonstrates high detection rate of denial of service attack and distributed denial of service attack with the number of malicious nodes not exceeding or slightly exceeding the number of trusted nodes. It also provides detection of the Sybil attack.