Efficient Access Control Permission Decision Engine Based on Machine Learning

Access control technology is critical to the safe and reliable operation of information systems. However, owing massive policy scale number access entities in open distributed systems, such as big data, Internet Things, cloud computing, existing permission decision methods suffer from a performance bottleneck. Consequently, large time overhead affects normal business services. To overcome above-mentioned problem, this paper proposes an efficient engine scheme based on machine learning (EPDE-ML). The proposed converts attribute-based request into vector, problem transformed binary classification that allows or denies access. random forest algorithm used construct vector classifier order establish engine. Experimental results show method can achieve accuracy around 92.6% test dataset, its efficiency significantly higher than benchmark method. In addition, improvement becomes more obvious increases.