Abstract: A system and method are disclosed for registering a email sender for the purpose of sending an email message to an email receiver including receiving a challenge message wherein the challenge message includes a machine answerable question; processing the challenge message to determine that it is a challenge message sent for the purpose of authorizing delivery of the email message; analyzing the question to determine a valid response to the challenge message; and sending the valid response that includes the answer wherein a nontrivial amount of resources are required to send the valid response.

Abstract: A system and method are disclosed for maintaining a whitelist, including: obtaining message data based on an email message sent by a user; extracting recipient information from message data; updating the whitelist using the recipient information.

Abstract: A system and method are disclosed for improving a statistical message classifier. A message may be tested with a machine classifier, wherein the machine classifier is capable of making a classification on the message. In the event the message is classifiable by the machine classifier, the statistical message classifier is updated according to the reliable classification made by the machine classifier. The message may also be tested with a first classifier. In the event that the message is not classifiable by the first classifier, it is tested with a second classifier, wherein the second classifier is capable of making a second classification. In the event that the message is classifiable by the second classifier, the statistical message classifier is updated according to the second classification.

Abstract: A technique for classifying a message is disclosed. In some embodiments, the technique comprises extracting a plurality of reference points, classifying the plurality of reference points, and detecting that the message is a phish message based on the classified reference points. In some embodiments, the technique comprises identifying a plurality of fraud indicators in the message, applying a statistical analysis on the plurality of fraud indicators; and determining whether the message is a fraudulent message based on the analysis.