Spam classification system based on network flow data

US10397256B2 · kind B2 · utility

Assignee

• MICROSOFT TECHNOLOGY LICENSING, LLC · US

Inventors

• Ori Kashi · Seattle, US
• Philip Newman · Seattle, US
• Daniel Alon · Even Yehuda, IL
• Elad Yom-Tov · Shfaram, IL
• Hani Hana Neuvirth · Redmond, US
• Royi Ronen · Nes Ziona, IL

Key dates

• Filing date: Nov 30, 2016
• Grant date: Aug 27, 2019
• Expiry date: Mar 29, 2037

Classification

• Technology area (CPC H): Electricity
• CPC primary: H04L51/216
• WIPO field: Digital communication
• WIPO sector: Electrical engineering

Abstract

In an example embodiment, a computer-implemented method comprises obtaining labels from messages associated with an email service provider, wherein the labels indicate for each message IP how many spam and non-spam messages have been received; obtaining network data features from a cloud service provider; providing the labels and network data features to a machine learning application; generating a prediction model representing an algorithm for determining whether a particular set of network data features are spam or not; applying the prediction model to network data features for an unlabeled message; and generating an output of the prediction model indicating a likelihood that the unlabeled message is spam.