Malicious JavaScript detection web service

• Main Author: Peng, Lunan
• Other Authors: Liu Yang
• Format: Final Year Project
• Language: English
• Published: 2016
• Subjects: DRNTU::Engineering::Computer science and engineering
• Online Access: http://hdl.handle.net/10356/66741
• Institution: Nanyang Technological University

Many malicious websites disguise their dangers. Once users access to them without the strong protection from anti-virus products, users’ computers might be harmed and their information might be stolen. One of the biggest threats in these websites is the Malicious JavaScript. Thus, the detection and prevention of Malicious JavaScript has always been an important research topics in cyber security. Many studies on malicious JavaScript detection were carried out and various detection tools were developed. One import technique applied is machine learning. Machine learning is a subfield of computer science that evolved from the study of pattern recognition and computational learning theory in artificial intelligence. It aims to develop algorithms that can learn from and make predictions on data. Such algorithms operate by building a model from example inputs to make data-driven predictions or decisions, rather than following strictly static program instructions[1]. To ensure a good accuracy of predictions, the amount of example inputs often needs to be large. In this project, about 160,000 JavaScript were collected from Internet for an existing machine learning-based malicious JavaScript detection tool. The model trained by this detection tool was used in a web application to provide online malicious JavaScript detection service.