Detection of Insider Threats Based on Deep Learning Using LSTM – CNN Model

Tamanna, Tahaseen (2020) Detection of Insider Threats Based on Deep Learning Using LSTM – CNN Model. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (862kB) | Preview
Preview	PDF (Configuration manual) Download (389kB) | Preview

Abstract

Insider threats are threats that originate within the organization and these insiders are the trusted employees in an organization. Detection of such internal attacks is challenging as the insiders have insight on sensitive information and vulnerabilities in the system. However, user actions and behaviours can help to determine the malicious activities at an early stage. Previous work mainly focused on traditional non-machine learning and machine learning techniques. Detailed research and study on deep learning techniques is achieved. One of the advantages of using deep learning approach is to have the advantage of learning features automatically. Therefore, a model is proposed with Deep Neural Network to detect insider threats based on user behaviour. Combination of LSTM and CNN (Long Short Term Memory and Convolutional Neural Network) is used to detect the anomalous behaviour of the users. In this paper, the proposed model for detecting insider threats is to apply the combination of LSTM with CNN to the user behaviour activity data. The proposed method is applied to public dataset CMU CERT version r4.2 of size 12GB. Result of the experiments shows the proposed model can detect insider threats successfully with the ROC 0.914 and comparison with machine learning approach justifies the proposed model can successfully detect insider threats.

Item Type:	Thesis (Masters)
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science Q Science > QA Mathematics > Computer software > Computer Security T Technology > T Technology (General) > Information Technology > Computer software > Computer Security
Divisions:	School of Computing > Master of Science in Cyber Security
Depositing User:	Dan English
Date Deposited:	27 Jan 2021 18:52
Last Modified:	27 Jan 2021 18:52
URI:	https://norma.ncirl.ie/id/eprint/4520

Actions (login required)

View Item