Malicious Website Identification Using Design Attribute Lerning

Via Zoom click here

Abstract:

Malicious websites pose a challenging cybersecurity threat. Traditional tools for detecting malicious websites rely heavily on industry-specific domain knowledge, are maintained by largescale research operations, and result in a never-ending attacker-defender dynamic. Malicious websites need to balance two opposing requirements to successfully function: escaping malware detection tools while attracting visitors. This fundamental conflict can be leveraged to create a robust and sustainable detection approach based on the extraction, analysis and learning of design attributes for malicious website identification. In this study, we propose a next-generation algorithm for extended design attribute learning that learns and analyzes web page structures, contents, appearances and reputations to detect malicious websites. Large-scale experiments that were conducted on more than 50,000 websites suggests that the proposed algorithm effectively detects more than 83% of all malicious websites while maintaining a low false-positive rate of 2%. In addition, the proposed method can incorporate user feedback and flag new suspicious websites and thus can be effective against zero-day attacks

Bio:

Or Naim is an MSc student in Lambda, the laboratory of AI, Machine Learning, Business & Data Analytics in the faculty of engineering in Tel Aviv University. Or has 15 years of experience in the Israeli cyber security ecosystem, including positions in the National Military Intelligence, IBM-Security, and top-notch Cybersecurity startups.

Contact:

• E-Mail: ornaim@mail.tau.ac.il

• Linkedin: https://www.linkedin.com/in/on19on19