User-specific data-driven network security
Detecting anomalous behavior of a device, including: generating, using information describing historical activity associated with a user device, a trained model for detecting normal activity for the user device; gathering information describing current activity associated with the user device; and determining, by using the information describing current activity associated with the user device as input to the trained model, whether the user device has deviated from normal activity.
1. A method of user-specific data-driven network security, the method comprising:
generating, based on historical activity associated with a user, a trained model for determining whether a network request deviates from normal activity for the user;
receiving, from a user device associated with the user, the network request;
determining, based on the historical activity for the user and the trained model, whether the network request deviates from normal activity for the user; and
initiating, in response to the network request deviating from normal activity for the user, an approval workflow for the network request, wherein the approval workflow comprises one or more user-completable steps that, if completed, cause the network request to he allowed.
2. The method of claim 1 further comprising periodically retraining the trained model.
3. The method of claim 2 wherein retraining the model is based at least in part on one or more workflow completions.
4. The method of claim 2 wherein retraining the model is based at least in part on additional historical activity for the user.
5. The method of claim 1 the approval workflow comprises a self-approval workflow.
6. The method of claim 1 the approval workflow comprises a third-party-approval workflow.
7. The method of claim 1 further comprising selecting the approval workflow from a plurality of workflows.
8. The method of claim 1 further comprising determining whether to allow the network request based on a completion of the approval workflow.
9. The method of claim 1 further comprising allowing the network request in response to determining that the network request does not deviate from normal activity for the user.
10. A computer program product for user-specific data-driven network security, the computer program product disposed on a non-transitory computer readable medium, the computer program product including computer program instructions configurable to carry out the steps of:
generating, based on historical activity associated with a user, a trained model for determining whether a network request deviates from normal activity for the user;
receiving, from a user device associated with the user, the network request;
determining, based on the historical activity for the user and the trained model, whether the network request deviates from normal activity for the user; and
initiating, in response to the network request deviating from normal activity for the user, an approval workflow for the network request, wherein the approval workflow comprises one or more user-completable steps that, if completed, cause the network request to be allowed.
11. The computer program product of claim 10 wherein the steps further comprise periodically retraining the trained model.
12. The computer program product of claim 11 wherein retraining the model is based at least in part on one or more workflow completions.
13. The computer program product of claim 11 wherein retraining the model is based at least in part on additional historical activity for the user.
14. The computer program product of claim 10 wherein the approval workflow comprises a self-approval workflow.
15. The computer program product of claim 10 wherein the approval workflow comprises a third-party-approval workflow.
16. The computer program product of claim 10 wherein the steps further comprise selecting the approval workflow from a plurality of workflows.
17. The computer program product of claim 10 wherein the steps further comprise determining whether to allow the network request based on a completion of the approval workflow.
18. The computer program product of claim 10 wherein the steps further comprise allowing the network request in response to determining that the network request does not deviate from normal activity for the user.