A formal model for masquerade detection software based upon natural mimicry

摘要

This paper is about the development of a framework for the formal certification of software for masquerade detection based upon natural mimicry. A masquerade is when an intruder mimics a genuine user in order to compromise the security of a computer system. The framework consists of looking at mimicry in the natural world. Based on this, a model for mimicry is developed based on the principle of indiscernibility. This is followed by a look into the requirements for masquerade detection software. A formal model for an agent for masquerade detection is then derived which discerns the static attributes of the user as well as detects anomalies in the dynamic user behavior via a statistical classifier. This agent is then used for masquerade detection in the Human Machine Interface (HMI) of an industrial automation network.