Systems and methods of detecting communications fraud
A telephone fraud prevention system is provided. A fraud application server is in communication with a fraud database and a switch that determines which calls are sent to the fraud application server. A policy function may be integrated with existing fraud detection and correlation systems. When a call is originated and authentication fails, whether that's through a PIN, voice recognition, etc., the fraud application server sends a message indicating that this customer has failed to authenticate. After a number of authentication failures, evidence of high-risk calling is determined. Instead of reactively dealing with the fraud, the risk has been captured at the fraud application server and the switch blocks potential damage from that call and from that user.
1. A system comprising:
a fraud application server (FAS) configured to test calls for compliance with a fraud policy;
a database comprising known and assumed fraudulent numbers;
a routing engine configured to determine a trust level of at least one of trusted, probation, and suspended with each of trusted, probation, and suspended applied to at least one number of the database, and to determine whether a call is to or from a fraudulent number and is to be passed to the FAS, wherein if the routing engine determines that the call is to or from the fraudulent number, the FAS queries for subscriber specific information; and
a router configured to route the call based on the test by the FAS.
2. The system of claim 1 , wherein the trust level is determined by the numbers and type of policy violations.
3. The system of claim 1 , wherein the database is updated in real time for every call.
4. The system of claim 1 , wherein the subscriber specific information comprising at least one of: unique personal identification number (PIN), biometric information, and answer to a preset personal question.
5. The system of claim 4 , wherein, if the call is determined to be to or from a fraudulent number, an alternative form of payment is requested.
6. A method comprising:
saving known and assumed fraudulent numbers in a database;
determining a trust level for each source number in the database, the trust level comprising at least one of trusted, probation, and suspended with each of trusted, probation, and suspended applied to at least one number of the database;
determining whether a call is to or from a fraudulent number; passing the call to or from the fraudulent number to a fraud application server; testing the call for compliance with a fraud policy, wherein if the call is determined to be to or from the fraudulent number, further comprising querying for subscriber specific information; and
routing the call based on the testing.
7. The method of claim 6 , wherein determining the trust level further comprises determining the trust level by the number and type of policy violations.
8. The method of claim 6 , further comprising updating the database in real time for every call.
9. The method of claim 6 , wherein the subscriber specific information comprising at least one of: unique personal identification number, biometric information, and answer to a preset personal question.
10. The method of claim 9 , wherein further comprising requesting an alternative form of payment if the call is determined to be to or from a fraudulent number.
11. A non-transitory computer readable medium comprising instructions for performing a method, the method comprising:
saving known and assumed fraudulent numbers in a database;
determining a trust level for each source number in the database, the trust level comprising at least one of trusted, probation, and suspended with each of trusted, probation, and suspended applied to at least one number of the database;
determining whether a call is to or from a fraudulent number; passing the call to or from the fraudulent number to a fraud application server; testing the call for compliance with a fraud policy, wherein if the call is determined to be to or from the fraudulent number, further comprising instructions for querying for subscriber specific information; and
routing the call based on the testing.
12. The computer readable medium of claim 11 , wherein instructions for determining the trust level further comprises instructions for determining the trust level by the number and type of policy violations.
13. The computer readable medium of claim 11 , further comprising instructions for updating the database in real time for every call.
14. The computer readable medium of claim 11 , wherein the subscriber specific information comprising at least one of: unique personal identification number, biometric information, and answer to a preset personal question.