Fraudulent message detection
AssigneeSonicWALL, Inc.
InventorsJonathan Oliver, Scott D. Eikenberry, Gleb Budman, Bryan Kim
Life of this patent
Estimating the term…
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.
Claims15
A method for classifying a message, comprising:
- extracting a plurality of reference points from a body of the message, each reference point being information used to contact a referenced entity;
- classifying each of the plurality of reference points based on a source associated with each reference point;
- determining whether the message is a fraudulent message appearing to be from a legitimate source based on the classified reference points;
- and
- processing the message based on the determination of whether the message is a fraudulent message appearing to be from a legitimate source.
A computer readable storage medium having embodied thereon a program, the program being executable by a processor to perform a method for classifying a message, the method comprising:
- extracting a plurality of reference points from a body of the message;
- classifying the plurality of reference points;
- determining whether the message is a fraudulent message appearing to be from a legitimate source based on the classified reference points;
- and
- processing the message based on the determination of whether the message is a fraudulent message appearing to be from a legitimate source.
Dependencies are inferred from the claim text.