System and method for outlier and anomaly detection in identity management artificial intelligence systems using cluster based analysis of network identity graphs
Systems and methods for artificial intelligence systems for identity management systems are disclosed. Embodiments may perform outlier detection and risk assessment based on identity management data, including one or more property graphs or peer groups determined from those property graphs, to determine identity management artifacts with ‘abnormal’ patterns when compared to other related identity management artifacts.
1. An identity management system for risk assessment using graphs, comprising:
a memory;
a processor;
a non-transitory, computer-readable storage medium including instructions executable by the processor for:
accessing identity management data obtained from one or more source systems of an enterprise;
evaluating the accessed identity management data to determine a set of identity management artifacts associated with a set of identities and at least one entitlement, utilized in identity management in association with the enterprise;
generating an identity management graph from the identity management data by:
creating nodes of the identity management graph by creating a node of the identity management graph for each of the determined identity management artifacts associated with the determined set of identities,
creating edges of the identity management graph between nodes of the identity management graph representing the determined identity management artifacts, the creating including pruning one or more edges, and
generating weights for created edges of the identity management graph, based on the created nodes associated with the created edges in accordance with the associated set of identities or at least one entitlement;
storing the identity management graph in a data store;
analyzing the identity management graph or the identity management data to identify an anomaly; and
identifying an identity management artifact associated with the identified anomaly as a high risk identity management artifact.
2. The system of claim 1 , wherein the analysis of the identity management graph comprises dynamic analysis.
3. The system of claim 2 , wherein the dynamic analysis comprises comparing the identity management graph or identity management data with a predicted identity management graph or predicted identity management data.
4. The system of 1 , wherein the instructions are further for presenting an interface depicting a representation of the identity management graph, identity management data or anomaly to a user.
5. The system of claim 4 , wherein the instructions are further for presenting a recommendation associated with the identity management artifact to a user.
6. The system of claim 1 , wherein the instructions are further for generating an alert to a user based on the identified anomaly.
7. The system of claim 6 , wherein the alert is generated based on a threshold for an assessment metric utilized in identifying the anomaly.
8. A method for risk detection using an identity management graph comprising:
accessing identity management data obtained from one or more source systems of an enterprise;
evaluating the accessed identity management data to determine a set of identity management artifacts associated with a set of identities and at least one entitlement, utilized in identity management in association with the enterprise;
generating an identity management graph from the identity management data by:
creating nodes of the identity management graph by creating a node of the identity management graph for each of the determined identity management artifacts associated with the determined set of identities,
creating edges identity management graph between nodes of the identity management graph representing the determined identity management artifacts, the creating including pruning one or more edges, and
generating weights for created edges of the identity management graph, based on the created nodes associated with the created edges in accordance with the associated set of identities or at least one entitlement;
storing the identity management graph in a data store;
analyzing the identity management graph or the identity management data to identify an anomaly; and
identifying an identity management artifact associated with the identified anomaly as a high risk identity management artifact.
9. The method of claim 8 , wherein the analysis of the identity management graph comprises dynamic analysis.
10. The method of claim 9 , wherein the dynamic analysis comprises comparing the identity management graph or identity management data with a predicted identity management graph or predicted identity management data.
11. The method of 8 , further comprising presenting an interface depicting a representation of the identity management graph, identity management data or anomaly to a user.
12. The method of claim 11 , further comprising presenting a recommendation associated with the identity management artifact to a user.
13. The method of claim 8 , further comprising generating an alert to a user based on the identified anomaly.
14. The method of claim 13 , wherein the alert is generated based on a threshold for an assessment metric utilized in identifying the anomaly.
15. A non-transitory computer readable storage medium, comprising instructions for risk detection using an identity management graph executable by a processor for:
accessing identity management data obtained from one or more source systems of an enterprise;
evaluating the accessed identity management data to determine a set of identity management artifacts associated with a set of identities and at least one entitlement, utilized in identity management in association with the enterprise;
generating an identity management graph from the identity management data by:
creating nodes of the identity management graph by creating a node of the identity management graph for each of the determined identity management artifacts associated with the determined set of identities,
creating edges of the identity management graph between nodes of the identity management graph representing the determined identity management artifacts, the creating including pruning one or more edges, and
generating weights for created edges of the identity management graph, based on the created nodes associated with the created edges in accordance with the associated set of identities or at least one entitlement;
storing the identity management graph in a data store;
analyzing the identity management graph or the identity management data to identify an anomaly; and
identifying an identity management artifact associated with the identified anomaly as a high risk identity management artifact.
16. The non-transitory computer readable storage medium of claim 15 , wherein the analysis of the identity management graph comprises dynamic analysis.
17. The non-transitory computer readable storage medium of claim 16 , wherein the dynamic analysis comprises comparing the identity management graph or identity management data with a predicted identity management graph or predicted identity management data.
18. The non-transitory computer readable storage medium of 15 , wherein the instructions are further for presenting an interface depicting a representation of the identity management graph, identity management data or anomaly to a user.
19. The non-transitory computer readable storage medium of claim 18 , wherein the instructions are further for presenting a recommendation associated with the identity management artifact to a user.
20. The non-transitory computer readable storage medium of claim 15 , wherein the instructions are further for generating an alert to a user based on the identified anomaly.
21. The non-transitory computer readable storage medium of claim 20 , wherein the alert is generated based on a threshold for an assessment metric utilized in identifying the anomaly.