Tools
Tools
Osei, Maame Yaa (2023) An Application of Explainable AI on Dynamic Convolutional Neural Networks for Transparent Malicious URL Detection. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (1MB) | Preview |
Abstract
Artificial Intelligence (AI) and machine learning models, particularly in cybersecurity, are experiencing rapid growth and widespread adoption. This surge, often involving expanding parameters to improve efficiency, gives rise to a deeper understanding of such complex models. The rapid advancement of Artificial Intelligence (AI) and machine learning in cybersecurity births the need for a deeper understanding of these technologies. This research focuses on Dynamic Convolutional Neural Networks (DCNNs), using Explainable AI (XAI) to clarify their complexities. DCNNs, known for their exceptional feature extraction abilities, dynamically adjust during convolution to detect intricate data patterns.
Understanding the complex inner workings of DCNNs is challenging. The research introduces tools like Local Interpretable Model-agnostic Explanations (LIME) within XAI to provide insights into the models’ decision processes, including feature importance. This approach also integrates word and character embedding to capture linguistic and morphological subtleties.
Incorporating XAI into DCNN models transforms cybersecurity practices, enabling security professionals to make more informed decisions in building and refining machine learning models and enhancing threat detection and response. As machine learning models increase in complexity, the significance of XAI in ensuring their reliability, transparency, and effectiveness becomes paramount. This study emphasizes XAI’s critical role in making cybersecurity AI models more understandable, efficient, and transparent, contributing to better handling of evolving cybersecurity threats.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Spellman, Ross UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QH Natural history > QH301 Biology > Methods of research. Technique. Experimental biology > Data processing. Bioinformatics > Artificial intelligence Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Artificial intelligence Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning |
| Divisions: | School of Computing > Master of Science in Cyber Security |
| Depositing User: | Ciara O'Brien |
| Date Deposited: | 21 Apr 2025 13:17 |
| Last Modified: | 21 Apr 2025 13:17 |
| URI: | https://norma.ncirl.ie/id/eprint/7452 |
Actions (login required)
 |
View Item |