Malicious website detection

Ong, Vienna Lee (2019) Malicious website detection. Faculty of Computer System & Software Engineering, Universiti Malaysia Pahang.

[img]
Preview
Pdf
Malicious website.pdf - Accepted Version

Download (304kB) | Preview

Abstract

Malicious websites are among the major security threats on the Internet. This threat has been existing for years yet the best solution to overcome it has not been implemented by many people. Most of the existing methods for detecting malicious websites are focusing towards specific attacks. However, attacks are getting more complex and hackers have become more sophisticated with their blended techniques to evade existing countermeasures. In this thesis, a method will be introduced. With previous existing methods in consideration, the method to use for this project is by using heuristic-based detection with machine learning technique and the feature that will be used together with the technique is URL based feature. The purpose of this method is to classify benign and malicious website using machine learning and then will automatically detect malicious websites. By using this method is also to ensure the detection accuracy is high and all malicious websites can be detected even the latest one prompted by the hackers. In conclusion, the proposed method is the most effective way to detect malicious websites and easy to be implemented.

Item Type: Undergraduates Project Papers
Additional Information: Project Paper (Bachelors of Computer Science (Computer Systems & Networking)) -- Universiti Malaysia Pahang – 2019, SV: EN. MOHD FAIZAL AB RAZAK, e-Thesis
Uncontrolled Keywords: Malicious websites; heuristic-based; machine learning
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Faculty/Division: Faculty of Computer System And Software Engineering
Depositing User: Mrs. Sufarini Mohd Sudin
Date Deposited: 24 Dec 2019 04:59
Last Modified: 24 Dec 2019 04:59
URI: http://umpir.ump.edu.my/id/eprint/27110
Download Statistic: View Download Statistics

Actions (login required)

View Item View Item