A Proposal for Information Systems Security Monitoring Based on Large Datasets

This article describes how the objective of recent advances in soft computing and machine learning models is the resolution of issues related to security monitoring for information systems. Most current techniques and models face significant limitations, in the monitoring of information systems. To address these limitations, the authors propose a new model designed to detect potential security breaches at an early stage using logging data. The proposed model uses unsupervised training techniques with a rule-based system to analyse data file logs. The proposed approach has been evaluated using a case study based on the learning of data file logs to determine the effectiveness of the proposed approach. Experimental results show that the proposed approach performs well, the results demonstrate that the proposed approach performs better than other conventional security methods in the identification of the correct decisions related to potential security in information systems.