Recent Patents on Engineering, Vol 11, No 3 (2017)

Font Size:  Small  Medium  Large

A support subset algorithm and its application to information security risk assessment

Dr. Meng Wang, shiyuan Zhou, zhankui Dong

Abstract


Security information producing big data makes the risk assessment task very difficult at risk level evaluation because of high computational and communication overheads in collecting, storing and managing information. Under the background of the big data era today,facing vast amounts of the security information, information security risk assessment requires special technologies to efficiently process large numbers of data. This study proposes an evolutionary algorithm to address these problems, namely Clustering and Support Subset algorithm (CSS) based on the reviews of the traditional machine learning methods and the latest United States patents available on risk assessment of information security. The CSS discretizes the evaluated risk level and extracts the rules from the sample set for predicting. Numbers of experiments have been performed to compare CSS with the traditional classification algorithms with the datasets from the UCI machine learning repository. Experimental results indicate that CSS algorithm predicts the risk level efficiently with a higher accuracy rate. The applications of CSS algorithm used in the information security risk assessment results are shown in the experiments.

Refbacks

  • There are currently no refbacks.