Detecting fraudulent activity on a network
Described are computer-based methods and apparatuses, including computer program products, for detecting fraudulent activity on a network. A user utilizes a transmitting device to transmit user requests that are split between a plurality of data centers for processing. The user requests are captured at the data centers. The user requests are unified into a user session. The user session can be analyzed for fraud detection, marketing analysis, network intrusion detection, customer service analysis, and/or performance analysis. If fraudulent activity is detected, then the user can be interdicted to prevent further fraudulent activity.
1. A method of detecting fraudulent activity, the method comprising:
receiving, by a fraud detection device in a first network, at least a portion of a user session comprising a plurality of interactions between a plurality of data centers and one or more devices, remote from the data centers, of a user, from a data reconstruction device, wherein each interaction of the plurality of interactions includes (i) envelope information and (ii) at least one request for information, a data center request for information, a user response, or a data center response;
comparing, at the fraud detection device, the at least a portion of the user session to one or more application contexts to determine whether the at least a portion of the user session includes fraudulent activity, wherein each of the one or more application contexts includes a set of fraudulent behavior indicators;
generating, at the fraud detection device, a session confidence value based on the comparison of the at least a portion of the user session to one or more application contexts; and
redirecting, by the fraud detection device, subsequent interactions received from the one or more devices to a second network isolated from the plurality of data centers if the activity pattern is found to deviate from the baseline of normal activity; and
monitoring, by the fraud detection device, the subsequent interactions to determine additional deviations from the baseline of normal activity.
2. The method of claim 1 , wherein the fraud detection device includes a geolocational profiling engine.
3. The method of claim 2 wherein the geolocational profiling engine uses global address lookup, network address, network information, routing information, time, date, device cookies, fraudulent activity history, fraud patterns, device fingerprint, or combinations thereof.
4. The method of claim 1 , wherein the fraud detection device includes a behavior profiling engine.
5. The method of claim 4 wherein the behavior profiling engine uses global address lookup, network address, network information, routing information, time, date, device cookies, fraudulent activity history, user behavior history, user preferences, user account information, fraud patterns, device fingerprint, or combinations thereof.
6. The method of claim 1 , wherein the fraud detection device includes an application rules engine.
7. The method of claim 6 wherein the application rules engine uses global address lookup, network address, network information, routing information, time, date, device cookies, fraudulent activity history, user behavior history, user preferences, user account information, user profile changes, account activity, or combinations thereof.
8. The method of claim 1 , wherein the fraud detection device includes a transactional rules engine.
9. The method of claim 8 wherein the transactional rules engine uses global address lookup, network address, network information, routing information, time, date, device cookies, fraudulent activity history, user behavior history, user preferences, user account information, user profile changes, account activity, transaction history, transaction, or combinations thereof.
10. The method of claim 1 , wherein the set of fraudulent behavior indicators includes geolocational profiling indicators.
11. The method of claim 1 , wherein the set of fraudulent behavior indicators includes behavioral profiling indicators.
12. The method of claim 1 , wherein the set of fraudulent behavior indicators includes application rules indicators.
13. The method of claim 1 , wherein the set of fraudulent behavior indicators includes transactional rules indicators.
14. The method of claim 1 , wherein the one or more application contexts include a human resources context, a financial services context, a customer service context, a consumer transaction context, or any combination thereof.
15. The method of claim 1 , wherein the at least a portion of a user session includes live user session data, historical user session data, or both.
16. The method of claim 1 , wherein the at least a portion of a user session includes data associated with a plurality of users.
17. A system for detecting fraudulent activity, the system comprising:
a fraud detection device in a first network configured to:
receive at least a portion of a user session comprising a plurality of interactions between a plurality of data centers and one or more devices, remote from the data centers, of a user, from a data reconstruction device, wherein each interaction of the plurality of interactions includes (i) envelope information and (ii) a user request for information, a data center request for information, a user response, or a data center response;
compare the at least a portion of the user session to one or more application contexts to determine whether the at least a portion of the user session includes fraudulent activity, wherein each of the one or more application contexts includes a set of fraudulent behavior indicators;
generate a session confidence value based on the comparison of the at least a portion of the user session to one or more application contexts; and
redirect subsequent interactions received from the one or more devices to a second network isolated from the plurality of data centers if the activity pattern is found to deviate from the baseline of normal activity; and
monitor the subsequent interactions to determine additional deviations from the baseline of normal activity.
18. A system for detecting fraudulent activity, the system comprising:
means for receiving, at a fraud detection device in a first network, at least a portion of a user session comprising a plurality of interactions between a plurality of data centers and one or more devices, remote from the data centers, of a user, from a data reconstruction device, wherein each interaction of the plurality of interactions includes (i) envelope information and (ii) a user request for information, a data center request for information, a user response, or a data center response;
means for comparing, at the fraud detection device, compare the at least a portion of the user session to one or more application contexts to determine whether the at least a portion of the user session includes fraudulent activity, wherein each of the one or more application contexts includes a set of fraudulent behavior indicators;
means for generating, at the fraud detection device, a session confidence value based on the comparison of the at least a portion of the user session to one or more application contexts; and
means for redirecting, by the fraud detection device, subsequent interactions received from the one or more devices to a second network isolated from the plurality of data centers if the session confidence value falls below a predetermined threshold;
means for monitoring, by the fraud detection device, the subsequent interactions to determine additional deviations from the baseline of normal activity.
19. A computer program product, tangibly embodied in a computer readable storage medium, for detecting fraudulent activity, the computer program product including instructions operable to cause a data processing apparatus in a first network to:
receive at least a portion of a user session comprising a plurality of interactions between a plurality of data centers and one or more devices, remote from the data centers, of a user, from a data reconstruction device, wherein each interaction of the plurality of interactions includes (i) envelope information and (ii) a user request for information, a data center request for information, a user response, or a data center response;
compare the at least a portion of the user session to one or more application contexts to determine whether the at least a portion of the user session includes fraudulent activity, wherein each of the one or more application contexts includes a set of fraudulent behavior indicators;
generate a session confidence value based on the comparison of the at least a portion of the user session to one or more application contexts; and
redirect subsequent interactions received from the one or more devices to a second network isolated from the plurality of data centers if the activity pattern is found to deviate from the baseline of normal activity; and
monitor the subsequent interactions to determine additional deviations from the baseline of normal activity.