Fraud detection mechanism

1. A computer-implemented method, comprising:

receiving, from a user device, a request to access a secure service, the request including access information, wherein the access information includes a received password;

receiving, from the user device, a requested action on the secure service;

correlating the access information and the requested action with stored information associated with the user device;

determining a fraud score based on a correlation between the received password and one of a most recently stored password and a previously stored password;

determining a security level associated with the requested action;

based on a determination that the fraud score is less than a threshold level, performing the requested action;

based on a determination that the fraud score is above the threshold level and that the security level is below a second threshold level, performing the requested action; and

based on a determination that the fraud is above the threshold level and that the security level is above a second threshold level, denying the requested action.

2. The method of claim 1 , wherein the fraud score is further based on:

a correlation between the requested action and a history of the user device's access to the secure service; and

a correlation between a user profile and the user device.

3. The method of claim 1 , wherein the correlation between one of the most recently stored password and the previously stored password and the received password is based on a Hamming distance between the one of the most recently stored password and the previously stored password and the received password.

4. The method of claim 2 , wherein the correlation between the requested action and the history of the user device's access to the secure service includes determining whether the requested action is a type of access frequently requested by the user device.

5. The method of claim 2 , wherein the correlation of the requested action to the history of the user device's access to the secure service includes determining whether a location of the requested action is frequently used by the user device to access secure service.

6. The method of claim 1 , further comprising determining a threshold level is received from the user device and storing the threshold level in a user profile associated with the user device.

7. The method of claim 2 , wherein a security level of the requested action is determined based on a type of action associated with the requested action.

8. The method of claim 7 , wherein the security level of the requested action is further based on a number of previous unsuccessful attempts to access the secure service during a time period.

9. A system for providing access to a secure service, the system comprising:

at least one processor

a memory, operably coupled to the at least one processor, the memory storing processor computer readable instructions;

the at least one processor, configured to execute computer readable instructions, which cause the processor to:

receive, from a user device, a request to access a secure service, the request including access information, wherein the access information includes a received password;

receive, from the user device, a requested action on the secure service;

correlate the access information and the requested action with stored information associated with the user device;

determine a fraud score based on a correlation between the received password and one of a most recently stored password and a previously stored password;

determine a security level associated with the requested action;

based on a determination that the fraud score is less than a threshold level, perform the requested action;

based on a determination that the fraud score is above the threshold level and that the security level is below a second threshold level, perform the requested action; and

based on a determination that the fraud is above the threshold level and that the security level is above a second threshold level, deny the requested action.

10. The system of claim 9 , wherein the fraud score is further based on:

a correlation between the requested action and a history of the user device's access to the secure service; and

a correlation between a user profile and the user device.

11. The system of claim 10 , wherein the correlation between one of the most recently stored password and the previously stored password and the received password is based on a Hamming distance between the one of the most recently stored password and the previously stored password and the received password.

12. The system of claim 11 , wherein the correlation between the requested action and the history of the user device's access to the secure service includes determining whether the requested action is a type of access frequently requested by the user device.

13. The system of claim 11 , wherein the correlation of the requested action to the history of the user device's access to the secure service includes determining whether a location of the requested action is frequently used by the user device to access secure service.

14. The system of claim 10 , further comprising determining a threshold level is received from the user device and storing the threshold level in a user profile associated with the user device.

15. The system of claim 11 , wherein a security level of the requested action is determined based on a type of action associated with the requested action.

16. The system of claim 15 , wherein the security level of the requested action is further based on a number of previous unsuccessful attempts to access the secure service during a time period.

17. A computer program product, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:

receive, from a user device, a request to access a secure service, the request including access information, wherein the access information includes a received password;

receive, from the user device, a requested action on the secure service;

correlate the access information and the requested action with stored information associated with the user device;

determine a fraud score based on a correlation between the received password and one of a most recently stored password and a previously stored password;

determine a security level associated with the requested action;

based on a determination that the fraud score is less than a threshold level, perform the requested action;

based on a determination that the fraud score is above the threshold level and that the security level is below a second threshold level, perform the requested action; and

based on a determination that the fraud is above the threshold level and that the security level is above a second threshold level, deny the requested action.

18. The computer program product of claim 17 , wherein the fraud score is further based on:

a correlation between the requested action and a history of the user device's access to the secure service; and

a correlation between a user profile and the user device.

19. The computer program product of claim 18 , wherein the correlation between one of the most recently stored password and the previously stored password and the received password is based on a Hamming distance between the one of the most recently stored password and the previously stored password and the received password.

20. The computer program product of claim 18 , wherein the correlation between the requested action and the history of the user device's access to the secure service includes determining whether the requested action is a type of access frequently requested by the user device.