Abstract: Extracting semantic meaning of local access control policies is an effective method to avoid conceptual and logical conflicts in multi domain policies integration. In view of domain ontology, a secure policy integration method based on ontology similarity was proposed.Using a machine learning algorithm of Baycsian, it can self-adaptively construct a secure multi-domain interoperation model to satisfy the autonomy and cooperation of all domains.

Key words: Multi-domain, Ontology similarity, Policy integration