A System for Improving Data Leakage Detection based on Association Relationship between Data Leakage Patterns

초록

This paper proposes a system that can detect the data leakage pattern using a convolutional neural networkbased on defining the behaviors of leaking data. In this case, the leakage detection scenario of data leakage iscomposed of the patterns of occurrence of security logs by administration and related patterns between thesecurity logs that are analyzed by association relationship analysis. This proposed system then detects whetherthe data is leaked through the convolutional neural network using an insider malicious behavior graph. Sinceeach graph is drawn according to the leakage detection scenario of a data leakage, the system can identify thecriminal insider along with the source of malicious behavior according to the results of the convolutional neuralnetwork. The results of the performance experiment using a virtual scenario show that even if a new maliciouspattern that has not been previously defined is inputted into the data leakage detection system, it is possible todetermine whether the data has been leaked. In addition, as compared with other data leakage detectionsystems, it can be seen that the proposed system is able to detect data leakage more flexibly.

키워드