Application of artificial neural networks and related techniques to intrusion detection

摘要: The increasing complexity of today's information technology (IT) together with our dependency upon it, has led to a situation in which security breach not only effects for individuals but can also affect the availability critical services (power supply, communication) or result significant financial loss. Criminals and terrorists want exploit system vulnerabilities capitalise on modern society's interwovenness IT. To counter this, organisations try secure their IT assets enforce policies, be compliant legal regulatory requirements ultimately deter unauthorised intruders from gaining access them. At core, goal intrusion detection systems is identification suspicious traffic flowing within, leaving entering an organisation. identify such traffic, may focus data within single host integrated various network segments. Identified then reported responsible authorities take appropriate course action. This report concerned state-of-the-art systems. Systems leveraging gathered host, i.e. host-based systems, are presented as well approaches observing analysing across networks, network-based Specific placed that make use artificial neural networks variations thereof separate potentially malicious ordinary traffic.