Deep Learning Based Multi Agent Intrusion Detection Approach for Cloud Security

Pokharkar, Aishwarya Ashok (2024) Deep Learning Based Multi Agent Intrusion Detection Approach for Cloud Security. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (900kB) | Preview
Preview	PDF (Configuration Manual) Download (596kB) | Preview

Abstract

Intrusion Detection Systems (IDS) are crucial in today's cloud environment due to the increased complexity and scale of network infrastructures, which are often distributed across multiple locations and accessed globally. Effective IDS are vital for identifying and mitigating network attacks and threats. Deep learning excels at processing complex, high-dimensional, and large-scale traffic data, offering superior detection capability. Current IDS solutions face challenges such as low detection accuracy, sub-optimal structures, and high false positive rates. To address these issues, this paper presents a sophisticated hierarchical intrusion detection model that compared multiple deep learning models and introduces a novel attention mechanism, aiming to enhance detection accuracy and reliability. The major objective achieved by this research is to reduce false positive rates using an attention-based mechanism and to increase the accuracy of detection. After evaluating the comparative analysis between different deep learning models, it has been found that Bi-LSTM with attention mechanism has the highest accuracy score over the test data.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Sahni, Vikas UNSPECIFIED
Uncontrolled Keywords:	Cloud Security; Network Security; Attention mechanism; Deep Learning; Feature selection
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Cloud computing 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 Cloud Computing
Depositing User:	Ciara O'Brien
Date Deposited:	04 Jul 2025 10:20
Last Modified:	04 Jul 2025 10:20
URI:	https://norma.ncirl.ie/id/eprint/8048

Actions (login required)

View Item