Pamarthi, Srilakshmi (2024) An Artificial Intelligence aided simulation testing framework for network intrusion detection in different operating systems. Masters thesis, Dublin, National College of Ireland.
Preview |
PDF (Master of Science)
Download (1MB) | Preview |
Preview |
PDF (Configuration Manual)
Download (815kB) | Preview |
Abstract
This paper examines how to design and develop a machine learning-based Intrusion Detection System (IDS) for enhancing the level of security by timely s detection of the intrusions. Because of the rapid growth of the number of connected objects, the relied-on approaches to security are insufficient, thus exacerbating the vulnerabilities. The architecture that we want to develop adapts and implements AI technology in the process of simulation testing. under the guidance of which many features are complied with the regulation of the GDPR. For the assessment of various machine learning algorithms using the NSL-KDD dataset, it was discovered that both Random Forest and Decision Tree algorithms demonstrated better results in the detection of intrusions and vulnerabilities. The versatility in the framework is that it is capable of learning from new threats as they form thus making it dynamic in nature. This leads to minimizing the extent of use of manpower and consequently lowering of operating costs.
Actions (login required)
![]() |
View Item |