Project Fact File

Title: An Intelligent Technique for Intrusion Detection in Computer Networks
Category: IT
Area:
No. of units: 2 or 4
Supervisor: Yan Li (Staff Profile)
Description:

Computer security is now becoming a major concern of modern society as a large fraction of information flows through computer networks. Standard protection mechanisms such as user authentication, service control, and traffic filtering cannot guarantee from the risk of computer attacks. The main reason of the weakness of computer networks lies in the great variability of network traffic, and in the so-called "bugs" always contained in system and application software, and complex unforeseen interactions between software components and/or network protocols. The objective of computer attacks is to obtain unauthorized access to the information stored in computer systems and/or to cause a temporary unavailability of its service. Intrusion Detection Systems (IDSs) are the fine grain filter placed inside the protected network, that look for known or potential threats in network traffic and/or in audit data recorded by hosts. Recently neural networks have also been used for the improvement of network intrusion detection systems based on searching for attack-specific keywords in network traffic. Neural networks provide a solution to the problems of modelling the users behaviour in anomaly detection because they do not require any explicit user model. In addition they can automatically learn attack signatures from attack samples. In this project, we will develop a neural approach for intrusion detection in computer networks.

Student: