In distributed, heterogeneous and network-connected collaborative environments where resources are provided to diverse unknown users for their applications, it is necessary to define access control for resources. Access control for such systems is defined as the ability to authorise
or repudiate access to resources by a particular user. Traditional access control solutions are inherently inadequate for collaborative systems because they are effective only in situations where the system knows in advance which users are going to access the resources and what are their access
rights so that they can be predefined by the developers or security administrators, but in collaborative systems the number of users as well as their usage on resources is not static. Targeting collaborative systems, a fine grained, flexible, persistent trust-based model for protecting the
access and usage of digital resources is defined in this paper using radial basis function neural network (RBFNN). RBFNN classifies the users requesting the resources as trustworthy and non-trustworthy based on their attributes. RBFNN is used for classification because of its ability to generalise
well for even unseen data and non-iterative method employed in its training. A proof of concept implementation backed by extensive set of tests on the real data collected for one such collaborative systems, i.e. Enabling Grids for E-Science grid demonstrated that the design is sound for collaborative
systems where access of resources are provided to large and unknown users with their variant set of requirements.
No Reference information available - sign in for access.
No Citation information available - sign in for access.