Simulating cheated results acceptance rates for gossip-based volunteer computing

Abstract

In this article, we present two different methods to estimate the dissemination rates of cheated results for decentralised distribution algorithms designed for volunteer computing networks. First, we define gossip-based protocols and present a short taxonomy that is based on data sizes for categorisation of distribution algorithms. We show three different distribution algorithms that are suitable for volunteer computing based on gossip-based protocols. Here, we additionally present an attacker model showing different attack possibilities on such algorithms. To minimise the impact of cheaters on a volunteer computing job, we introduce cheat detection mechanisms based on positive and negative verification of computation results. Finally, to minimise the amount of needed cheat detection computations, we either use simulations with the help of cellular automatons and a mathematical model to estimate the dissemination rates of cheated results. With the help of our methods, the cheat detection rate can be adjusted in a way that the speed up is maximal and the computation overhead for the cheat detection is minimal.