Access Control on Grid Resources Using Radial Basis Function Neural Network

Due to realization of the grid environment as commercial grid where diverse and unknown users can access the grid resources for job execution, resource access control becomes a major issue. Traditional methods of providing access control to grid resources fail because of lack of flexibility and scalability in them. Considering grid environment as cooperative model of the society, it is envisioned that as people like to give their valuable belongings to only trustworthy people to safeguard themselves from loss similarly if, somehow, the resource providers are able to classify the requesting users as trustworthy or not before giving them access of resources, then they will be able to protect their resources from malicious users. In this paper classification of the user requesting grid resources as trustworthy or not is done using Radial Basis Function Neural Network (RBFNN). They are good at approximation and are able to generalize well even for that data whose training is not given to the network.