Back to search

Carleton University

Augmenting Vulnerability Assessment and Attack Modeling with New Factors

Abstract

dc:description.abstract

Security modeling and quantification play a central role in enabling risk assessment. Among existing techniques, attack graphs have emerged as a powerful model for representing an attacker's actions. However, the effectiveness of security models is heavily influenced by the quality of information they rely on. Incomplete or inaccurate input data can result in misleading analyses. To this end, this thesis proposes a multi-source vulnerability analysis framework to improve the accuracy and reliability of automated vulnerability classification to facilitate the automated generation of attack graphs. By leveraging Multi-Instance Learning and Large Language Models, we achieved a flexible approach that can aggregate information from multiple vulnerability data sources to perform context-aware classification. Furthermore, we propose a two-dimensional attack graph model that incorporates shared infrastructure components and supports the cloud-specific attack paths. This approach addresses a critical limitation of traditional attack graphs and models the threats introduced by virtualization layers in cloud environments.

Degree

thesis:*
Name thesis:degree_name
Master of Computer Science (M.C.S.)
Level thesis:degree_level
Master's
Discipline thesis:degree_discipline
Computer Science
Grantor dc:publisher
Carleton University
Year dc:date.issued
2025

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Kootzari, Parsa

Subjects

dc:subject × 1

Rights

dc:rights
Statement dc:rights
  • Copyright © 2025 the author(s). Theses may be used for non-commercial research, educational, or related academic purposes only. Such uses include personal study, distribution to students, research and scholarship. Theses may only be shared by linking to the Carleton University Institutional Repository and no part may be copied without proper attribution to the author; no part may be used for commercial purposes directly or indirectly via a for-profit platform; no adaptation or derivative works are permitted without consent from the copyright owner.
Language dc:language.iso
en

Identifiers

dc:identifier.*

Chain of custody

source
Harvested from
Carleton University
Base URL
carleton.scholaris.ca/server/oai/request
Last updated
2026-11-19
Source record
OAI-PMH GetRecord
citation

Kootzari, Parsa. Augmenting Vulnerability Assessment and Attack Modeling with New Factors. Master's thesis, Carleton University, 2025. https://hdl.handle.net/20.500.14718/44882