Using Dependency Tracking to Provide Explanations for Policy Management

Explanations for decisions made by a policy framework allow end users to understand how the results were obtained, increase trust in the policy decision and enforcement process, and enable policy administrators to ensure the correctness of the policy. In our framework, an explanation for any statement including a policy decision is a representation of the list of reasons (known as dependencies) associated with its derivation. Dependency tracking involves maintaining the list of reasons (statements and rules) for the derivation of a new statement. In this paper, we describe our policy approach that (i) provides explanations for policy decisions, (ii) provides more efficient and expressive reasoning through the use of nested sub-rules and goal direction, and (Hi) is grounded in semantic Web technologies. We discuss the characteristics of our approach and provide a brief overview of the AIR policy language that implements it. We also discuss how relevant explanation information is identified and presented to end users and describe our preliminary graphical user interface.