Systems and methods for data correlation and artifact matching in identity management artificial intelligence systems
Systems and methods for embodiments of artificial intelligence systems for identity management are disclosed. Embodiments of the identity management systems disclosed herein may support the correlation of identities determined authoritative source systems with uncorrelated accounts within an enterprise using artificial intelligence techniques.
1. An identity management system, comprising:
a processor;
a non-transitory, computer-readable storage medium, including computer instructions for:
obtaining identity management data associated with a plurality of source systems in a distributed enterprise computing environment, the identity management data comprising data on a set of identity management artifacts utilized in identity management in the distributed enterprise computing environment, wherein the plurality of source systems include a non-authoritative source system and an authoritative source system and the identity management data comprises account data on accounts from the non-authoritative source system and identity data on identities from the authoritative source system;
determining a set of uncorrelated accounts of the accounts from the non-authoritative source system and a set of correlated accounts from the account from the non-authoritative source system, wherein each of the set of correlated accounts is associated with an identity of the identities from the authoritative source system;
determining a similarity measure between each uncorrelated account and each of the set of correlated accounts;
clustering the accounts to determine a set of account clusters, the clustering based on the similarity measure between each uncorrelated account and each of the set of correlated accounts, wherein each account cluster comprising uncorrelated accounts and correlated accounts from the non-authoritative source system;
managing network security of the distributed enterprise computing environment by:
for an uncorrelated account of the set of uncorrelated accounts, determining an account cluster including the uncorrelated account;
determining peer correlated accounts in the account cluster, wherein each peer correlated account is one of the set of uncorrelated accounts included in the account cluster;
determining a crowdsourcing target based on the peer correlated accounts, wherein the crowdsourcing target is a first identity of the set of identities;
sending a crowdsourcing communication associated with the uncorrelated account to the crowdsourcing target;
determining a response to the crowdsourcing communication associated with the uncorrelated account; and
managing network security of the distributed enterprise computing environment by managing access of the uncorrelated account within the distributed enterprise computing environment based on the response.
2. The system of claim 1 , wherein determining a crowdsourcing target comprises:
determining a second identity that is correlated with the peer correlated accounts and determining that the first identity that is a manager of the second identity.
3. The system of claim 1 , wherein the instructions are further for: performing an initial correlation between the accounts from the non-authoritative source system with the identities to determine the set of uncorrelated accounts and the set of correlated accounts.
4. The system of claim 3 , wherein the initial correlation is a performed by a machine learning model specific to the non-authoritative source system.
5. The system of claim 1 , wherein managing network security of the distributed enterprise computing environment further comprises determining a subset of uncorrelated accounts for deletion from their respective non-authoritative source system within the distributed enterprise computing environment to manage.
6. The system of claim 1 , wherein managing access of the uncorrelated account based on the received response further comprises provisioning one or more defined access rights for the uncorrelated account.
7. The system of claim 1 , wherein the similarity measure is a Jaccard similarity and the clustering is hierarchical clustering.
8. A method, comprising:
obtaining identity management data associated with a plurality of source systems in a distributed enterprise computing environment, the identity management data comprising data on a set of identity management artifacts utilized in identity management in the distributed enterprise computing environment, wherein the plurality of source systems include a non-authoritative source system and an authoritative source system and the identity management data comprises account data on accounts from the non-authoritative source system and identity data on identities from the authoritative source system;
determining a set of uncorrelated accounts of the accounts from the non-authoritative source system and a set of correlated accounts from the account from the non-authoritative source system, wherein each of the set of correlated accounts is associated with an identity of the identities from the authoritative source system;
managing network security of the distributed enterprise computing environment by:
determining a similarity measure between each uncorrelated account and each of the set of correlated accounts;
clustering the accounts to determine a set of account clusters, the clustering based on the similarity measure between each uncorrelated account and each of the set of correlated accounts, wherein each account cluster comprising uncorrelated accounts and correlated accounts from the non-authoritative source system;
for an uncorrelated account of the set of uncorrelated accounts, determining an account cluster including the uncorrelated account;
determining peer correlated accounts in the account cluster, wherein each peer correlated account is one of the set of uncorrelated accounts included in the account cluster;
determining a crowdsourcing target based on the peer correlated accounts, wherein the crowdsourcing target is a first identity of the set of identities;
sending a crowdsourcing communication associated with the uncorrelated account to the crowdsourcing target;
determining a response to the crowdsourcing communication associated with the uncorrelated account; and
managing network security of the distributed enterprise computing environment by managing access of the uncorrelated account within the distributed enterprise computing environment based on the response.
9. The method of claim 8 , wherein determining a crowdsourcing target comprises:
determining a second identity that is correlated with the peer correlated accounts and determining that the first identity that is a manager of the second identity.
10. The method of claim 8 , wherein the instructions are further for: performing an initial correlation between the accounts from the non-authoritative source system with the identities to determine the set of uncorrelated accounts and the set of correlated accounts.
11. The method of claim 10 , wherein the initial correlation is a performed by a machine learning model specific to the non-authoritative source system.
12. The method of claim 8 , wherein managing network security of the distributed enterprise computing environment further comprises determining a subset of uncorrelated accounts for deletion from their respective non-authoritative source system within the distributed enterprise computing environment to manage.
13. The method of claim 8 , wherein managing access of the uncorrelated account based on the received response further comprises provisioning one or more defined access rights for the uncorrelated account.
14. The method of claim 8 , wherein the similarity measure is a Jaccard similarity and the clustering is hierarchical clustering.
15. A non-transitory computer readable medium, comprising instructions for:
obtaining identity management data associated with a plurality of source systems in a distributed enterprise computing environment, the identity management data comprising data on a set of identity management artifacts utilized in identity management in the distributed enterprise computing environment, wherein the plurality of source systems include a non-authoritative source system and an authoritative source system and the identity management data comprises account data on accounts from the non-authoritative source system and identity data on identities from the authoritative source system;
determining a set of uncorrelated accounts of the accounts from the non-authoritative source system and a set of correlated accounts from the account from the non-authoritative source system, wherein each of the set of correlated accounts is associated with an identity of the identities from the authoritative source system;
managing network security of the distributed enterprise computing environment by:
determining a similarity measure between each uncorrelated account and each of the set of correlated accounts;
clustering the accounts to determine a set of account clusters, the clustering based on the similarity measure between each uncorrelated account and each of the set of correlated accounts, wherein each account cluster comprising uncorrelated accounts and correlated accounts from the non-authoritative source system;
for an uncorrelated account of the set of uncorrelated accounts, determining an account cluster including the uncorrelated account;
determining peer correlated accounts in the account cluster, wherein each peer correlated account is one of the set of uncorrelated accounts included in the account cluster;
determining a crowdsourcing target based on the peer correlated accounts, wherein the crowdsourcing target is a first identity of the set of identities;
sending a crowdsourcing communication associated with the uncorrelated account to the crowdsourcing target;
determining a response to the crowdsourcing communication associated with the uncorrelated account; and
managing network security of the distributed enterprise computing environment by managing access of the uncorrelated account within the distributed enterprise computing environment based on the response.
16. The non-transitory computer readable medium of claim 15 , wherein determining a crowdsourcing target comprises: determining a second identity that is correlated with the peer correlated accounts and determining that the first identity that is a manager of the second identity.
17. The non-transitory computer readable medium of claim 15 , wherein the instructions are further for: performing an initial correlation between the accounts from the non-authoritative source system with the identities to determine the set of uncorrelated accounts and the set of correlated accounts.
18. The non-transitory computer readable medium of claim 17 , wherein the initial correlation is a performed by a machine learning model specific to the non-authoritative source system.
19. The non-transitory computer readable medium of claim 15 , wherein managing network security of the distributed enterprise computing environment further comprises determining a subset of uncorrelated accounts for deletion from their respective non-authoritative source system within the distributed enterprise computing environment to manage.
20. The non-transitory computer readable medium of claim 15 , wherein managing access of the uncorrelated account based on the received response further comprises provisioning one or more defined access rights for the uncorrelated account.
21. The non-transitory computer readable medium of claim 15 , wherein the similarity measure is a Jaccard similarity and the clustering is hierarchical clustering.