Theses and Dissertations

ORCID

https://orcid.org/0000-0002-7766-568X

Advisor

Banicescu, Ioana

Committee Member

Iannucci, Stefano

Committee Member

Luke, Edward

Committee Member

Lim, Hyeona

Date of Degree

5-16-2025

Original embargo terms

Immediate Worldwide Access

Document Type

Dissertation - Open Access

Major

Computational Engineering

Degree Name

Doctor of Philosophy (Ph.D.)

College

James Worth Bagley College of Engineering

Department

Computational Engineering Program

Abstract

Autonomic Intrusion Detection Systems (AIDS) are sophisticated software systems designed to autonomously and adaptively identify and respond to security threats and intrusions in computer networks or systems. One of the fundamental challenges in intrusion detection research lies in the limited availability and scope of publicly available datasets. The proposed research aims to address data-related gaps with autonomic and traditional intrusion detection systems by describing a comprehensive approach to investigate the impact and potential of data augmentation. The goal is to explore various data augmentation techniques, assess their effectiveness in introducing variability, and evaluate their impact on the performance of neural-based intrusion detection models. The concept of Computational Knowledge Structures referred to as K-structures, is introduced. K-structures are foundational models representing the knowledge learned by extracting high-level features from related data; creating atomic blocks of knowledge that can be combined into a generalized machine learning model called an aggregate model. The resulting aggregate model is known as an ensemble model, where instead of aggregating "learners", data and knowledge are aggregated to create a generalized machine learning (ML) model that blends the characteristics of signature-based and anomaly-based intrusion detection systems. Resulting in IDSs that are more adaptable, robust, and capable of handling the complexities of real-world network environments. This study employs quantitative methods to assess the effectiveness, efficiency, and complexity of neural-based intrusion detection systems (IDSs). Through practical implementations of IDSs, empirical analysis was conducted to compare the proposed methods to ensure realistic, reliable, and widely applicable results. The significance of this research lies in its potential to substantially improve the effectiveness of the system by implementing end-to-end network intrusion detection to match the ever evolving tactics of intruders.

Download

Share

COinS