Date of Award

4-2012

Document Type

Thesis

Degree Name

Master of Science (MS)

Department

Computer Science

First Advisor

Qiuming Zhu

Second Advisor

William Mahoney

Third Advisor

Robin A. Gandhi

Fourth Advisor

Stanley Wileman

Abstract

Cyber-attacks have become a huge threat to the information age. In a previous study, cyber-attacks associated with events in Social, Political, Economic and Cultural (SPEC) dimensions were analyzed [6]. The task of this research is to construct an automated classifier that can classify media reports related to past and current cyber-attack events according to the SPEC taxonomy. The classifier was built on a machine learning principle incorporated with approaches focused on 1) document indexing; 2) calculation of classification thresholds; 3) definition of classification effectiveness; and 4) calculation of precision and recall. The classifier is expected to perform with acceptable effectiveness so that it helps analysts to deal with large number of media reports that are predictive of possible cyber-attacks.

Comments

A Thesis Presented to the Department of Computer Science and the Faculty of the Graduate College University of Nebraska. In Partial Fulfillment of the Requirements for the Degree Master of Science. Copyright 2012 Jinhua Zhang.

Files over 3MB may be slow to open. For best results, right-click and select "save as..."

COinS