A Leak Detection Method Based on Semantic Knowledge Representation and Derivation Model

Abstract

Prevention from the leak of release information is a major challenge in public release information security issues. The derivation relation inherent in the information is the key to leak. To address the problem, a leak detection method based on semantic knowledge representation and derivation model is presented within two detections over the release information. Firstly, semantic knowledge of a sentence can be represented in the frame-based hierarchy through semantic and syntax analyses. Base on this, leaks in some ways can be detected, such as by enclosing information that need to be confidential (general secret information) directly, by using the substitution of synonym or restatement of secret information. Secondly, the derivation model is constructed through the hierarchy and derivation relations implicated in the information. This model is tailored to detect leaks caused by information derivation. Finally, we also report on the theory and experiment analysis. The result is satisfying.