Tools
Tools
O'Brien, Michael (2023) Evaluate the use of Supervised Machine Learning Algorithms in the detection of phishing attacks. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration manual)
Download (968kB) | Preview |
Abstract
The weakest elements in any cybersecurity framework are the end users, people. Hackers have been taking advantage of the end users since the birth of the modern Technology age. Social Engineering, in particular phishing is seen as an easy method attack. The Nigerian prince, one of the earliest global phishing attacks, which is still doing the rounds today, is still estimated to be making over $700,000 a year. And it is not because there isn’t email Security systems or not because people are aware of these attacks, it’s just a human condition, we have a lot on our minds, we are not paying full attention and we make mistakes, it is as simple as that.
In today’s world, Artificial Intelligence (AI) and Machine Learning (ML) have been intergraded to millions of systems and within the IT security sector, because of the lack of security professional available to manage an ever-growing sector, AI and ML are one of the, if not the, largest growing technologies being utilized. And when we speak about AI and ML, we are not talking about the T1000 (Terminator 2) or the singularity (Vernor Vinge, 1993) intelligence, we are talking about intelligence demonstrated by machines based on making predictions from Data by using Algorithms.
This research paper is going to examine the threat of phishing in today world. The paper will examine existing techniques used to identifying phishing attacks and phishing URL’s. The goal of this research is to evaluate the use of these AI/ML algorithms and their accuracy in the detection of phishing attacks compared to existing detection methods currently being used.
The research will examine three Machine Learning Algorithms (Decision Tree, Random Forest, & Naive Bayes) and evaluate their accuracy in detecting phishing attackers from a known dataset, using supervised learning. The goal from this research paper is going to be data, calculated data that can be used and compared to existing methods of phishing detection. Data that is measurable, tested and can be used for further research. Aiming to identify which Machine Learning algorithm, with supervised learning approach can be used to achieve the most accuracy in the detection of phishing attacks.
| Item Type: | Thesis (Masters) |
|---|---|
| Supervisors: | Name Email Spelman, Ross UNSPECIFIED |
| Subjects: | Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Algebra > Algorithms > Computer algorithms 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: | Tamara Malone |
| Date Deposited: | 04 May 2023 14:33 |
| Last Modified: | 04 May 2023 14:33 |
| URI: | https://norma.ncirl.ie/id/eprint/6532 |
Actions (login required)
 |
View Item |