IDENTIFICATION OF CONTENT BY METADATA

摘要

Systems and methods for identifying content in electronic messages are provided. An electronic message may include certain content. The content is detected and analyzed to identify any metadata. The metadata may include a numerical signature characterizing the content. A thumbprint is generated based on the numerical signature. The thumbprint may then be compared to thumbprints of previously received messages. The comparison allows for classification of the electronic message as spam or not spam.

主权项

1. A method for identifying content in electronic messages, the method comprising:
receiving a first electronic message over a communication network; extracting a plurality of numerical metadata values characterizing one or more images in the first electronic message; generating a first plurality of thumbprints based on the extracted plurality of numerical metadata values, wherein each thumbprint of the first plurality of thumbprints is based on at least a subset of the plurality of numerical metadata values; searching through one or more message thumbprints, each message thumbprint of the one or more message thumbprints corresponding to an electronic message other than the first electronic message; identifying one or more matching thumbprints of the one or more message thumbprints, the one or more matching thumbprints matching at least one of the first plurality of thumbprints; and classifying one or more matching electronic messages associated with the identified one or more matching thumbprints, the electronic messages classified into a first classification category.