Credibility Evaluation Of Software Behavior Model Based On Scene Mining

Computer terminals and network security incidents take place with frequent in recent years. Viruses, trojans, worms and the vulnerability of software emerge in endlessly. Ensuring the security of software and information in the computer has become an urgent task. At present, trusted computer system can ensure the security of the computer systems' start-up phase.When the operating system and software application on run-time after start ,it is difficult to guarantee the security. If the dynamic credibility problems in the running process can not be solved, the TPM's (Trusted Platform Module) trusted mechanisms at the bottom of the credible computer is useless. By analyzing a variety of security threats, we can know that malicious operations or attacks achieve their aims by changing the normal behavior of the system or software running. So, the dynamic credibility detection technology base on software behavior becomes the focus of the research.Most of the current detection models for software behavior focus on the integrity detecting of its running path, but they rarely consider detecting the function realization integrity in each stage of the software running path. Therefore, credibility evaluation model of software behavior based on scene mining for called CEMBSM is proposed in this paper. First of all, this model describes the integrity of various stages'function implementation by introducing the concept of scene. Secondly, the model used association rules and sequence pattern algorithm in scene mining. Both of the algorithms can extract the hidden and valuable association information from the captured scene information set. And the mining result is used for credibility detection of software behavior. Finally, the results of simulation experiments indicate that CEMBSM model has a good detection performance.