Data protection by means of fragmentation in distributed storage systems

This paper analyzes different dispersed storage systems that use data fragmentation as a way of protection. Existing solutions have been organized into two categories: those operating on unstructured data and in a uniform environment, and those having as input data with predefined confidentiality level and disposing of a heterogeneous environment in terms of machine trustworthiness. Furthermore, we outline requirements and desired architecture traits of an efficient dispersed storage, which will address the issues of performance (including latency), resilience and scalability.