Facial reconstruction

Search LJMU Research Online

Browse Repository | Browse E-Theses

Using Deep Learning Model for Network Scanning Detection

Nguyen Viet, H, Nguyen Van, Q, Thi Trang, LL and Shone, N (2018) Using Deep Learning Model for Network Scanning Detection. In: Proceedings of the 4th International Conference on Frontiers of Educational Technologies (18). pp. 117-121. (ICFET '18 Proceedings of the 4th International Conference on Frontiers of Educational Technologies, 25 June 2018 - 27 June 2018, Moscow, Russian Federation).

[img]
Preview
Text
p117-Viet.pdf - Accepted Version

Download (583kB) | Preview

Abstract

In recent years, new and devastating cyber attacks amplify the need for robust cybersecurity practices. Preventing novel cyber attacks requires the invention of Intrusion Detection Systems (IDSs), which can identify previously unseen attacks. Many researchers have attempted to produce anomaly - based IDSs, however they are not yet able to detect malicious network traffic consistently enough to warrant implementation in real networks. Obviously, it remains a challenge for the security community to produce IDSs that are suitable for implementation in the real world. In this paper, we propose a new approach using a Deep Belief Network with a combination of supervised and unsupervised machine learning methods for port scanning attacks detection - the task of probing enterprise networks or Internet wide services, searching for vulnerabilities or ways to infiltrate IT assets. Our proposed approach will be tested with network security datasets and compared with previously existing methods.

Item Type: Conference or Workshop Item (Paper)
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions: Computer Science
Publisher: ACM
Date Deposited: 07 Jun 2019 09:57
Last Modified: 07 Jun 2019 09:57
DOI or Identification number: 10.1145/3233347.3233379
URI: http://researchonline.ljmu.ac.uk/id/eprint/9525

Actions (login required)

View Item View Item