System and method for predictive modeling for entitlement diffusion and role evolution in identity management artificial intelligence systems using network identity graphs
Systems and methods for embodiments of a graph based artificial intelligence systems for identity management are disclosed. Embodiments of the identity management systems disclosed herein may utilize a network graph approach to analyzing identities, roles, entitlements or other identity management artifacts of a distributed networked enterprise computing environment. Specifically, embodiments of an artificial intelligence based identity management systems may perform predictive modeling for entitlement diffusion or role evolution or other aspects of identity management artifact using network identity graphs.
1. An identity management system, comprising:
a data store;
a processor;
a non-transitory, computer-readable storage medium, including computer instructions for:
obtaining identity management data from one or more identity management systems in a distributed enterprise computing environment, the identity management data comprising data on a set of identities and a set of entitlements associated with the set of identities utilized in identity management in the distributed enterprise computing environment;
evaluating the identity management data to determine the set of identities and a set of entitlements associated with the set of identities;
generating a first identity graph from the identity management data by:
creating a node of a first type in the first identity graph for each of the determined set of identities,
creating a node of a second type in the first identity graph for each of the set of entitlements;
for each first identity that has an entitlement of the set of entitlements, creating an edge in the first identity graph representing a first relationship between a first node representing the first identity and a second node representing the entitlement;
for each first identity and a second identity that share at least one entitlement of the set of entitlements, creating an edge in the first identity graph representing a second relationship between the first node representing the first identity and a third node of the identity graph representing the second identity, and
generating a weight for each edge of the first identity graph representing the second relationship between each first node and third node based on the at least one entitlement shared between the first identity represented by the first node and the second identity represented by the third node; and
storing the first identity graph in the data store;
applying a predictive model to a portion of the first identity graph to generate a predictive graph, wherein the predictive graph is an evolution of the first identity graph to a future point in time relative to a first point in time represented in the portion of the first identity graph; and
determining predictive data to present to a user utilizing the predictive graph based on an identity management artifact of interest.
2. The system of claim 1 , wherein each node of the first type for each of the determined set of identities of the first identity graph is an identity state node representing a state of a corresponding identity of the determined set of identities at the point in time.
3. The system of claim 2 , wherein each edge of the first identity graph between each first node representing the first identity and each second node representing the entitlement represents that the first identity of the first node has that entitlement at the point in time.
4. The system of claim 1 , wherein the predictive model is one of a Susceptible-Infectious (SI), Susceptible-Infectious-Susceptible (SIS) or Susceptible-Infectious-Recovered/Immune (SIR) model.
5. The system of claim 1 , wherein the first portion of the first identity graph is determined by scoping the first identity graph based on the identity management artifact of interest or the point in time.
6. The system of claim 5 , wherein the instructions are further for scoping the first portion of the first identity graph or the first identity graph to a second point in time to generate a testing graph, and testing the second identity graph using the testing graph.
7. The system of claim 1 , wherein the predictive data comprises a rate of spread of the identity management artifact of interest or a cost associated with the identity management artifact of interest at the future point in time.
8. An method for predictive identity management, comprising:
obtaining identity management data from one or more identity management systems in a distributed enterprise computing environment, the identity management data comprising data on a set of identities and a set of entitlements associated with the set of identities utilized in identity management in the distributed enterprise computing environment;
evaluating the identity management data to determine the set of identities and a set of entitlements associated with the set of identities;
generating a first identity graph from the identity management data by:
creating a node of a first type in the first identity graph for each of the determined set of identities,
creating a node of a second type in the first identity graph for each of the set of entitlements;
for each first identity and a second identity that share at least one entitlement of the set of entitlements, creating an edge in the first identity graph representing a second relationship between the first node representing the first identity and a third node of the identity graph representing the second identity, and
generating a weight for each edge of the first identity graph representing the second relationship between each first node and third node based on the at least one entitlement shared between the first identity represented by the first node and the second identity represented by the third node; and
storing the first identity graph in the data store;
applying a predictive model to a portion of the first identity graph to generate a predictive graph, wherein the predictive graph is an evolution of the first identity graph to a future point in time relative to a first point in time represented in the portion of the first identity graph; and
determining predictive data to present to a user utilizing the predictive graph based on an identity management artifact of interest.
9. The method of claim 8 , wherein each node of the first type for each of the determined set of identities of the first identity graph is an identity state node representing a state of a corresponding identity of the determined set of identities at the point in time.
10. The method of claim 9 , wherein each edge of the first identity graph between each first node representing the first identity and each second node representing the entitlement represents that the first identity of the first node has that entitlement at the point in time.
11. The method of claim 8 , wherein the predictive model is one of a Susceptible-Infectious (SI), Susceptible-Infectious-Susceptible (SIS) or Susceptible-Infectious-Recovered/Immune (SIR) model.
12. The method of claim 8 , wherein the first portion of the first identity graph is determined by scoping the first identity graph based on the identity management artifact of interest or the point in time.
13. The method of claim 12 , further comprising scoping the first portion of the first identity graph or the first identity graph to a second point in time to generate a testing graph, and testing the second identity graph using the testing graph.
14. The method of claim 8 , wherein the predictive data comprises a rate of spread of the identity management artifact of interest or a cost associated with the identity management artifact of interest at the future point in time.
15. A non-transitory computer readable medium, comprising instructions for:
obtaining identity management data from one or more identity management systems in a distributed enterprise computing environment, the identity management data comprising data on a set of identities and a set of entitlements associated with the set of identities utilized in identity management in the distributed enterprise computing environment;
evaluating the identity management data to determine the set of identities and a set of entitlements associated with the set of identities;
generating a first identity graph from the identity management data by:
creating a node of a first type in the first identity graph for each of the determined set of identities,
creating a node of a second type in the first identity graph for each of the set of entitlements;
for each first identity and a second identity that share at least one entitlement of the set of entitlements, creating an edge in the first identity graph representing a second relationship between the first node representing the first identity and a third node of the identity graph representing the second identity, and
generating a weight for each edge of the first identity graph representing the second relationship between each first node and third node based on the at least one entitlement shared between the first identity represented by the first node and the second identity represented by the third node; and
storing the first identity graph in the data store;
applying a predictive model to a portion of the first identity graph to generate a predictive graph, wherein the predictive graph is an evolution of the first identity graph to a future point in time relative to a first point in time represented in the portion of the first identity graph; and
determining predictive data to present to a user utilizing the predictive graph based on an identity management artifact of interest.
16. The non-transitory computer readable medium of claim 15 , wherein each node of the first type for each of the determined set of identities of the first identity graph is an identity state node representing a state of a corresponding identity of the determined set of identities at the point in time.
17. The non-transitory computer readable medium of claim 16 , wherein each edge of the first identity graph between each first node representing the first identity and each second node representing the entitlement represents that the first identity of the first node has that entitlement at the point in time.
18. The non-transitory computer readable medium of claim 15 , wherein the predictive model is one of a Susceptible-Infectious (SI), Susceptible-Infectious-Susceptible (SIS) or Susceptible-Infectious-Recovered/Immune (SIR) model.
19. The non-transitory computer readable medium of claim 15 , wherein the first portion of the first identity graph is determined by scoping the first identity graph based on the identity management artifact of interest or the point in time.
20. The non-transitory computer readable medium of claim 19 , further comprising instructions for scoping the first portion of the first identity graph or the first identity graph to a second point in time to generate a testing graph, and testing the second identity graph using the testing graph.
21. The non-transitory computer readable medium of claim 15 , wherein the predictive data comprises a rate of spread of the identity management artifact of interest or a cost associated with the identity management artifact of interest at the future point in time.