Official websites use .gov
A .gov website belongs to an official government organization in the United States.

Secure .gov websites use HTTPS
A lock ( ) or https:// means you’ve safely connected to the .gov website. Share sensitive information only on official, secure websites.

NIST IR 8360 (Initial Public Draft)

Machine Learning for Access Control Policy Verification

Date Published: March 2021
Comments Due: May 7, 2021 (public comment period is CLOSED)
Email Questions to:


Vincent Hu (NIST)


Access control policy verification ensures that there are no faults within the policy that leak or block access privileges. To answer the challenges of traditional verification methods, this report proposes an efficient and straightforward method for access control policy verification by applying a classification algorithm of machine learning. This method does not require comprehensive test cases, oracle, or system translation but rather checks the logic of policy rules directly, making it more efficient and feasible compared to traditional methods. This report also demonstrates an experiment for the proposed method with an example that uses current available machine learning tools to facilitate the random forest classification algorithm. The result illustrates its capabilities as well as parameter settings for performing the verification steps. 

NOTE: A call for patent claims is included on page iv of this draft. For additional information, see the Information Technology Laboratory (ITL) Patent Policy--Inclusion of Patents in ITL Publications



ABAC; access control; access control test; access control verification; AI; authorization; machine learning; policy
Control Families

None selected


Download URL

Supplemental Material:
None available

Document History:
03/23/21: IR 8360 (Draft)
09/16/21: IR 8360 (Final)


Security and Privacy

access authorization, access control


artificial intelligence