@MASTERSTHESIS\{IMM2007-05193,
    author       = "A. Oksuz",
    title        = "Unsupervised Intrusion Detection System",
    year         = "2007",
    keywords     = "Intrusion Detection System, Neural Network, Unsupervised Learning Algorithm, Pcap, Network Features",
    school       = "Informatics and Mathematical Modelling, Technical University of Denmark, {DTU}",
    address      = "Richard Petersens Plads, Building 321, {DK-}2800 Kgs. Lyngby",
    type         = "",
    note         = "Supervised by Prof. Robin Sharp, {IMM,} {DTU}.",
    url          = "http://www2.compute.dtu.dk/pubdb/pubs/5193-full.html",
    abstract     = "This thesis evolves around Intrusion Detection System (IDS) and Neural Network (NN). Intrusion detection systems are gaining more and more territory in the field of secure networks and new ideas and concepts regarding the intrusion detection  process keep surfacing.

One idea is to use a neural network algorithm for detecting intrusions. The neural network algorithms have the ability to be trained and ’learn’ socalled patterns in a given environment. This feature can be used in connection with an intrusion detection system, where the neural network algorithm can be trained to detect intrusions by recognizing patterns of an intrusion.

This thesis outlines an investigation on the unsupervised neural network models and choice of one of them for evaluation and implementation. The thesis also includes works on computer networks, providing a description and analysis of the structure of the computer network in order to generate network features. A design proposal for such a system is documented in this thesis together with an implementation of an unsupervised intrusion detection system."
}