Finding phishing sites

US8839418B2 · kind B2 · utility

Assignee

• Microsoft Corporation · US

Inventors

• Geoffrey J. Hulten · Bainbridge Island, US
• Paul Rehfuss · Seattle, US
• Robert L. Rounthwaite · Fall City, US
• Joshua T. Goodman · Redmond, US
• Gopalakrishnan Seshadrinathan · Redmond, US
• Anthony Penta · Bellevue, US
• Manav Mishra · Kirkland, US
• Roderic C. Deyo · Redmond, US
• Elliott Jeb Haber · Fall City, US
• David Snelling · Everett, US

Key dates

• Filing date: Jan 18, 2006
• Grant date: Sep 16, 2014
• Expiry date: Apr 8, 2031

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04L63/08
• WIPO field: Digital communication
• WIPO sector: Electrical engineering

Abstract

Described is a technology by which phishing-related data sources are processed into aggregated data and a given site evaluated the aggregated data using a predictive model to automatically determine whether the given site is likely to be a phishing site. The predictive model may be built using machine learning based on training data, e.g., including known phishing sites and/or known non-phishing sites. To determine whether an object corresponding to a site is likely a phishing-related object are described, various criteria are evaluated, including one or more features of the object when evaluated. The determination is output in some way, e.g., made available to a reputation service, used to block access to a site or warn a user before allowing access, and/or used to assist a hand grader in being more efficient in evaluating sites.