×

Classifying a message based on fraud indicators

  • US 8,661,545 B2
  • Filed: 05/03/2012
  • Issued: 02/25/2014
  • Est. Priority Date: 09/08/2003
  • Status: Expired due to Term
First Claim
Patent Images

1. A method for identifying fraudulent messages, the method comprising:

  • storing information in memory regarding a plurality of fraud indicators, each fraud indicator being a pattern previously identified as characteristic of fraudulent messages;

    receiving a message sent over a communication network; and

    executing instructions stored in memory, wherein execution of the instructions by a processor;

    parses the message and detects at least one pattern that is characteristic of fraudulent messages;

    matches the at least one pattern with at least one of the fraud indicators stored in memory;

    counts a number of fraud indicators identified in the message;

    computes a probability of the message being a fraudulent message based on the number of fraud indicators identified in the message;

    classifies the received message as a fraudulent message, andgenerates an alert that the received message has been classified as a fraudulent message.

View all claims
  • 14 Assignments
Timeline View
Assignment View
    ×
    ×