Abstract
In the modern age of content, web browsers serve as an important bridge between content and users. On the other hand, web browsers are also a link to malicious codes, and new types of malicious codes that are secretly mining through browsers are being created. In recent years, a web browser investigation is essential to find the path of malicious code infection when a security incident occurs. However, the content became vast, and as network performance is getting better, websites are getting bigger, and the number of web pages included in a single website has increased exponentially. It is almost impossible to manually analyze all of the thousands of sites due to time limitations. In this paper, we propose a method to apply machine learning to web browser forensics to solve these problems. Also, we propose AIBFT: Artificial Intelligence Browser Forensic Toolkit, a Proof-of-Concept (POC) tool that provides automatic detection of malicious webpages using AI models, analysis of malicious probability, and timeline visualization. We collected 52,500 benign and malicious web pages for AI models and learning. As a result of applying the randomforest algorithm among AI algorithms, we could achieve 99.8% accuracy.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Forensic Science International: Digital Investigation
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
