Predicting attribute based user trustworthiness for access control of resources

The purpose of open, distributed systems, is to enable coordinated resource sharing to diverse users. In order to protect each participant's privilege and security, a secure and efficient access control is essential. Due to limited or lack of knowledge about user's identities in open systems, access control need to be specified in terms of the attributes and properties of the users. Moreover, the attribute based access control methods are known for their flexibility and dynamicity. This paper puts forward a novel attribute based trust model using Radial Basis Neural Network to define the access control. RBFNN is used because of its ability to generalize well even for unseen data and fast learning data. The trustworthiness of the requestors is computed using RBFNN, maintaining the continuity of access decisions. The framework is validated on the real data of EGEE grid, a distributed system and found to be performed better than feed forward neural network.