Full metadata record
| DC Field | Value | Language |
|---|---|---|
| dc.contributor | Department of Electronic and Information Engineering | en_US |
| dc.contributor.advisor | Hu, Haibo (EIE) | en_US |
| dc.creator | Yao, Ruiqi | - |
| dc.identifier.uri | https://theses.lib.polyu.edu.hk/handle/200/10748 | - |
| dc.language | English | en_US |
| dc.publisher | Hong Kong Polytechnic University | en_US |
| dc.rights | All rights reserved | en_US |
| dc.title | Deep learning on malicious DNS queries in real world | en_US |
| dcterms.abstract | Domain name system (DNS) is a service of the Internet. As a distributed database that resolves a domain name to an IP address, it can make people access the Internet more easily. If DNS suffers from attacks, Internet services will be paralyzed. However, with the popularity of the Internet, network security problems are becoming increasingly severe. Various types of DNS attacks, such as malware, phishing, botnet, Distributed Denial of Service (DDoS), etc, occur in an endless stream. It has caused huge economic losses in the worldwide, and the entire cyberworld is trying their best to deal with the problem of network security. Fortunately, the development of artificial intelligence provides us with more advanced technology to deal with DNS attacks detection and protection. Machine learning, deep learning and reinforcement learning make DNS detection methods change from the original static detection to the dynamic automatic detection. The research of DNS attack detection based on deep learning has become a world-class research topic, which is of great significance. In this dissertation, I combine both theoretical research and scientific experiment to study the problem of malicious DNS query detection. Several types of supervised learning (CNN, DNN, RNN, the combination of CNN and RNN) are reproduced in practice. The theoretical model is designed and tested by experiment, and the actual effect is measured and analyzed. This paper also makes a comprehensive theoretical research on semi-supervised learning (GAN), designs a theoretical model, and makes experimental tests. The research results of GAN to sovle malicious DNS attack detection are rare at present. At the same time, it also explains the existing problems and paves way to future research along this direction. | en_US |
| dcterms.extent | 7, 67 pages : color illustrations | en_US |
| dcterms.isPartOf | PolyU Electronic Theses | en_US |
| dcterms.issued | 2020 | en_US |
| dcterms.educationalLevel | M.Sc. | en_US |
| dcterms.educationalLevel | All Master | en_US |
| dcterms.LCSH | Internet domain names -- Security measures | en_US |
| dcterms.LCSH | Computer security | en_US |
| dcterms.LCSH | Internet addresses | en_US |
| dcterms.LCSH | Hong Kong Polytechnic University -- Dissertations | en_US |
| dcterms.accessRights | restricted access | en_US |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 5174.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 3.07 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/10748