pizza Lecture : Establishing Secure Interactions Across Distributed Applications in Satellite Clusters

08/22/2014 12:00 pm
08/22/2014 1:00 pm

Title: Establishing Secure Interactions Across Distributed Applications in Satellite Clusters


Abstract:  Recent developments in small satellites have led to an increasing interest in building satellite clusters. When compared to traditional monolithic satellites, satellite clusters - (a) are easier and cheaper to launch and maintain since each satellite of a cluster could be launched over time by different organizations, and (b) results in a dynamic distributed system that provides flexibility with regards to resource provisioning, load balancing, and fault tolerance. An interesting use case for these satellite clusters is an open system that provides a distributed computing platform in space. This can be thought of as "cluster-as-a-service" in space. Being an open system, it can hosts different applications belonging to different organization and have different security classification levels. Therefore, the system must provide strict information partitioning such that only applications with compatible security classifications know about each other’s existence and therefore can interact with each other. Even though applications can interact using various interaction patterns, our work currently focuses on anonymous group publish/subscribe pattern of interaction since it has enjoyed great success in previous space software architectures, such as NASA's Cora Flight Executive. However, the difficulty is that existing solutions that support anonymous publish/subscribe interactions, such as the OMG's Data Distribution Service (DDS), do not support information partitioning based on security classification since they lack a well-defined security model. Our work makes two important contributions to address these limitations - (a) a kernel level transport mechanism that uses a lattice of labels to represent security classifications and enforces Multi-Level Security (MLS) policies to ensure strict information partitioning, and (b) a novel discovery service that allows us to use an existing DDS implementation with our custom transport mechanism to realize a publish/subscribe middleware that facilitates information partitioning based on security classification of applications. We include a use case scenario to verify our solution.


Presenter: Subhav Pradhan

 RSVP at