FullReview: Practical Accountability in Presence of Selfish Nodes

Accountability is becoming increasingly required in today's distributed systems. Indeed, accountability allows not only to detect faults but also to build provable evidence about the misbehaving participants of a distributed system. There exists a number of solutions to enforce accountability in distributed systems, among which PeerReview is the only solution that is not specific to a given application and that does not rely on any special hardware. However, this protocol is not resilient to selfish nodes, i.e. nodes that aim at maximising their benefit without contributing their fair share to the system. Our objective in this paper is to provide a software solution to enforce accountability on any underlying application in presence of selfish nodes. To tackle this problem, we propose the FullReview protocol. FullReview relies on game theory by embedding incentives that force nodes to stick to the protocol. We theoretically prove that our protocol is a Nash equilibrium, i.e. that nodes do not have any interest in deviating from it. Furthermore, we practically evaluate FullReview by deploying it for enforcing accountability in two applications: (1) SplitStream, an efficient multicast protocol, and (2) Onion routing, the most widely used anonymous communication protocol. Performance evaluation shows that FullReview effectively detects faults in presence of selfish nodes while incurring a small overhead compared to PeerReview and scaling as PeerReview.