SPAM DETECTION

• US 20080155693A1
• Filed: 12/22/2006
• Published: 06/26/2008
• Est. Priority Date: 12/22/2006
• Status: Active Grant

• Current Assignee: Cingular Wireless II LLC (AT&T, Inc.)
• Original Assignee: Cingular Wireless II LLC (AT&T, Inc.)
• Inventors: Cenciarelli, Fulvio, Mikan, Jeffrey, McNamara, Justin, Kefalas, Anastasios L., Lewis, John Ervin
• Granted Patent: US 8,458,262 B2
• Time in Patent Office: Days
• US Class Current: 726/23
• CPC Class Codes: H04L 51/212 using filtering or selective blocking
• CPC Class Codes: H04L 51/58 Message adaptation for wireless communication
• CPC Class Codes: H04W 88/184 Messaging devices, e.g. message centre

Abstract

Methods and systems of filtering spam messages for cellular network subscribers are provided that may include receiving a message from a decoy subscriber number. The method and systems may further be adapted to determine whether the message at the decoy subscriber number may be spam. If the message at the decoy number tends to be spam, the message may be output to a filtering service for further analysis. In the final analysis if a message is determined to be spam, then new rules may be created and distributed to front end spam and/or virus engines to restrict such traffic from reaching subscribers.

Claims

1. A method of filtering spam messages for cellular network subscribers, comprising:

receiving a message at a decoy subscriber number; and

determining that the message received at the decoy subscriber number is spam.

2. The method of claim 1, wherein the decoy subscriber number comprises a cellular phone number of an inactive account, wherein the inactive account comprises at least one of the following:

a transferred account, a cancelled account, and an unassigned account.

3. The method of claim 1, further comprising:

receiving a message from an active subscriber number; and

determining whether the message received from the active subscriber number is spam; and

if the determination is that the message is spam, outputting the message to a filtering service.

4. The method of claim 1, wherein determining whether the message received at the decoy subscriber number is spam comprises comparing information in the received message to one or more rules stored in a spam library.

5. The method of claim 1, wherein the message comprises at least one of the following:

an electronic message, an instant message, a video message, a text message, a multimedia message, a picture, or a graphic.

6. The method of claim 1, wherein the determination is that the message received at the decoy number is spam and further comprising flagging the message as spam.

7. A spam filter component for filtering spam messages on a cellular network, comprising:

a first decoy module, wherein the first decoy module receives one or more messages from a decoy subscriber number;

a spam library module adapted to store information for determining whether a message is spam, wherein the spam library module comprises one or more rules;

a spam processor component in operative communication with the first decoy module and the spam library module, wherein the spam processor component compares information in the message received by the first decoy module with the rules in the spam library module and, if the message includes information corresponding to the rules, outputs the message as spam.

8. The spam filter component of claim 7, wherein the decoy subscriber number comprises a cellular phone number of an inactive account, wherein the inactive account comprises at least one of the following:

a transferred account, a cancelled account, and an unassigned account.

9. The spam filter component of claim 7, wherein the first decoy module receives one or more messages from an active subscriber number, and

the spam processor component compares information in the message received by the first decoy module with the rules in the spam library module and, if the message includes information corresponding to the rules, outputs the message as spam.

10. The spam filter component of claim 7, wherein the message comprises at least one of the following:

an electronic message, an instant message, a video message, a text message, a multimedia message, a picture, or a graphic.

11. The spam filter component of claim 7, wherein the rules comprises at least one of the following:

a threshold limit of messages from a sender, prior use of a subscriber, one or more keywords indicating spam, sender identification, and information received from messages at other decoy subscriber numbers.

12. The spam filter component of claim 7, wherein the spam processor component compares the message received by the first decoy module with the rules in the spam library module, and if the message includes information corresponding to the rules, flags the message as spam.

13. A method of determining whether a message is spam, comprising:

receiving a message from a decoy subscriber number;

comparing information in the received message to one or more rules stored in a spam library;

flagging the received message as spam if information in the received message corresponds to the rules stored in the spam library; and

outputting the flagged message to a spam filtering service.

14. The method of claim 13, wherein the decoy subscriber number comprises a cellular phone number of an inactive account, wherein the inactive account comprises at least one of the following:

a transferred account, a cancelled account, and an unassigned account.

15. The method of claim 13, further comprising receiving a message from an active subscriber number;

comparing information in the received message to one or more rules stored in a spam library;

flagging the received message as spam if information in the received message corresponds to the rules stored in the spam library; and

outputting the flagged message to a spam filtering service.

16. The method of claim 13, wherein the message comprises at least one of the following:

an electronic message, an instant message, a video message, a text message, a multimedia message, a picture, or a graphic.

17. The method of claim 13, wherein the rules comprises at least one of the following:

a threshold limit of messages from a sender, prior use of a subscriber, one or more keywords indicating spam, sender identification, and information received from messages at other decoy subscriber numbers.