Automatic crawler for phishing sites
keywords CYBERSECURITY, MACHINE LEARNING, ARTIFICIAL NEURAL NETWORKS, PHISHING
Reference persons MARCO MELLIA
External reference persons Idilio Drago
Research Groups SmartData@PoliTO, Telecommunication Networks Group
Thesis type EXPERIMENTAL
Description The thesis focuses on the design, engineering and testing of an automatic crawler that identifies possible phishing sites. Given a URL, the crawler will be able to quantify the probability that that page is i) phishing, ii) parking, iii) legitimate, iv) corrupted or other possible classes.
The system will be based on functionalities extracted from the page (number of links, number of images, etc.) integrated with external information (TLS certificate, hosting site, website country, use of content management systems, etc.).
The student will use some already available data, like https://phishtank.org, or solutions like https://conferences.sigcomm.org/imc/2022/program/#p54 to design and implement a system that automatically visits a page and returns any classification of that page.
Required skills - Interest in cyber-security
- Interest in machine learning and AI algorithms
- Good programming skill (Python)
- Good knowledge on machine learning classifiers
Deadline 13/12/2023 PROPONI LA TUA CANDIDATURA