Back to search

National Technical University of Athens (NTUA)

Ανίχνευση ανωμαλιών σε δίκτυα μεγάλης κλίμακας με χρήση ανάλυσης κυρίων συνιστωσών

Abstract

dc:description

One of the main challenges in security management of large scale networks is the detection of suspicious anomalies in network traffic patterns due to threats such as Distributed Denial of Service (DDoS) attacks or worm propagation. Usually network anomaly detection methodologies rely on the analysis of network traffic and the characterization of the dynamic statistical properties of traffic normality. Anomaly detection is based on the concept that perturbations of normal behavior suggest the presence of anomalies such as faults and attacks and can be uniformly applied in order to detect network attacks, even in cases where novel attacks are present and the nature of the intrusion is unknown. In this context, we envisage a variety of distributed monitors that exchange information through a common automated platform and assist the anomaly detection algorithms by sharing their views. The proposed approach is based on the application of Principal Component Analysis on multi-metric-multi-link data, and provides an efficient and unified way of taking into account the combined effect of the correlated observed data, for anomaly detection purposes. It actually introduces a generalized anomaly detection methodology, capable of detecting not only volume based anomalies, but a much wider range of classes of anomalies, such as the ones that may result in alterations in traffic composition or traffic paths. The proposed methodology effectively combines correlated data in order to reveal anomalies that span through a number of neighboring elements in the network graph and allows for the identification of the corresponding paths that contain the anomaly. Throughout this thesis, the proposed anomaly detection methodology is applied in different kinds of large scale networks that present different characteristics and application environments, and are quite representative of the networks that will compose the Internet of the Future, such as high speed networks, wireless sensor networks and hybrid vehicular networks. In each case, the application of the proposed methodology within the specific environment is discussed, and its effectiveness is evaluated via simulation or/and emulation. Throughout this thesis it is demonstrated that such an approach can be used in principle for several anomaly detection applications and scenarios, including: identify an abnormal situation in a series of measurements (e.g. cases where the values of the measured or monitored parameters may deviate significantly from the norm), discover the existence of faulty sensors in a sensor network, detect potential network attacks, and/or filter suspicious reports throughout the overall decision making process.

Degree

thesis:*
Grantor dc:publisher
National Technical University of Athens (NTUA)
Year dc:date
2009

Author and committee

dc:creator, dc:contributor.*
Authors dc:creator
  • Chatzigiannakis, Vassilis
  • Χατζηγιαννάκης, Βασίλειος

Subjects

dc:subject × 16

Rights

Language dc:language
gre

Identifiers

dc:identifier.*
Identifier
10.12681/eadd/17967

Chain of custody

source
Harvested from
Greek National Archive of PhD Theses
Base URL
phdtheses.ekt.gr/eadd_oai/request
Last updated
2026-11-18
Source record
OAI-PMH GetRecord
citation

Chatzigiannakis, Vassilis; Χατζηγιαννάκης, Βασίλειος. Ανίχνευση ανωμαλιών σε δίκτυα μεγάλης κλίμακας με χρήση ανάλυσης κυρίων συνιστωσών. National Technical University of Athens (NTUA), 2009. http://hdl.handle.net/10442/hedi/17967