The Use of Statistic Complexity for Security and Performance Analysis in Autonomic Component Ensembles

The paper proposes a new technique for detecting malware threats in autonomic component ensembles. The technique is based on the statistic complexity metrics, which relate objects to random variables and (unlike other complexity measures considering objects as individual symbol strings) are ensemble based. This transforms the classic problem of assessing the complexity of an object into the realm of statistics. The proposed technique requires implementation of the process X (which generates ‘healthy’ flows containing no malware threats) and objects generated by the actual (possible infected) process Y. The component flows files are used as objects of the processes X and Y. The result of the proposed procedure gives us the distribution of probabilities of malware infection among autonomic components. The possibility to use the results obtained to perform quantitative probabilistic verification and analysis of ASEs using the probabilistic model checking tool PRISM is demonstrated.