Document Type


Date of Award

Fall 1-31-2005

Degree Name

Doctor of Philosophy in Electrical Engineering - (Ph.D.)


Electrical and Computer Engineering

First Advisor

Symeon Papavassiliou

Second Advisor

Nirwan Ansari

Third Advisor

Teunis J. Ott

Fourth Advisor

Lev A. Zakrevski

Fifth Advisor

Roberto Rojas-Cessa


With the advent and the explosive growth of the global Internet and the electronic commerce environment, adaptive/automatic network and service anomaly detection is fast gaining critical research and practical importance. If the next generation of network technology is to operate beyond the levels of current networks, it will require a set of well-designed tools for its management that will provide the capability of dynamically and reliably identifying network anomalies. Early detection of network anomalies and performance degradations is a key to rapid fault recovery and robust networking, and has been receiving increasing attention lately.

In this dissertation we present a network anomaly detection methodology, which relies on the analysis of network traffic and the characterization of the dynamic statistical properties of traffic normality, in order to accurately and timely detect network anomalies. Anomaly detection is based on the concept that perturbations of normal behavior suggest the presence of anomalies, faults, attacks etc. This methodology can be uniformly applied in order to detect network attacks, especially in cases where novel attacks are present and the nature of the intrusion is unknown.

Specifically, in order to provide an accurate identification of the normal network traffic behavior, we first develop an anomaly-tolerant non-stationary traffic prediction technique, which is capable of removing both pulse and continuous anomalies. Furthermore we introduce and design dynamic thresholds, and based on them we define adaptive anomaly violation conditions, as a combined function of both the magnitude and duration of the traffic deviations. Numerical results are presented that demonstrate the operational effectiveness and efficiency of the proposed approach, under different anomaly traffic scenarios and attacks, such as mail-bombing and UDP flooding attacks.

In order to improve the prediction accuracy of the statistical network traffic normality, especially in cases where high burstiness is present, we propose, study and analyze a new network traffic prediction methodology, based on the "frequency domain" traffic analysis and filtering, with the objective_of enhancing the network anomaly detection capabilities. Our approach is based on the observation that the various network traffic components, are better identified, represented and isolated in the frequency domain. As a result, the traffic can be effectively separated into a baseline component, that includes most of the low frequency traffic and presents low burstiness, and the short-term traffic that includes the most dynamic part. The baseline traffic is a mean non-stationary periodic time series, and the Extended Resource-Allocating Network (BRAN) methodology is used for its accurate prediction. The short-term traffic is shown to be a time-dependent series, and the Autoregressive Moving Average (ARMA) model is proposed to be used for the accurate prediction of this component. Furthermore, it is demonstrated that the proposed enhanced traffic prediction strategy can be combined with the use of dynamic thresholds and adaptive anomaly violation conditions, in order to improve the network anomaly detection effectiveness. The performance evaluation of the proposed overall strategy, in terms of the achievable network traffic prediction accuracy and anomaly detection capability, and the corresponding numerical results demonstrate and quantify the significant improvements that can be achieved.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.