Document Type


Date of Award

Spring 5-31-2005

Degree Name

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


Electrical and Computer Engineering

First Advisor

Edwin Hou

Second Advisor

Nirwan Ansari

Third Advisor

Roberto Rojas-Cessa

Fourth Advisor

Swades K. De

Fifth Advisor

Daochuan Hung


Internet has grown by several orders of magnitude in recent years, and this growth has escalated the importance of computer security. Intrusion Detection System (IDS) is used to protect computer networks. However, the overwhelming flow of log data generated by IDS hamper security administrators from uncovering new insights and hidden attack scenarios. Security Information Management (SIM) is a new growing area of interest for intrusion detection. The research work in this dissertation explores the semantics of attack behaviors and designs Frame-based Attack Representation and First-order logic Automatic Reasoning (FAR-FAR) using linguistics and First-order Logic (FOL) based approaches. Techniques based on linguistics can provide efficient solutions to acquire semantic information from alert contexts, while FOL can tackle a wide variety of problems in attack scenario reasoning and querying. In FAR-FAR, the modified case grammar PCTCG is used to convert raw alerts into frame-structured alert streams and the alert semantic network 2-AASN is used to generate the attack scenarios, which can then inform the security administrator. Based on the alert contexts and attack ontology, Space Vector Model (SVM) is applied to categorize the intrusion stages. Furthermore, a robust Variant Packet Sending-interval Link Padding algorithm (VPSLP) is proposed to prevent links between the IDS sensors and the FAR-FAR agents from traffic analysis attacks. Recent measurements and studies demonstrated that real network traffic exhibits statistical self-similarity over several time scales. The bursty traffic anomaly detection method, Multi-Time scaling Detection (MTD), is proposed to statistically analyze network traffic's Histogram Feature Vector to detect traffic anomalies.



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.