Generalized Spot-Checking for Sabotage-Tolerance in Volunteer Computing Systems

While volunteer computing (VC) systems reach the most powerful computing platforms, they still have the problem of guaranteeing computational correctness, due to the inherent unreliability of volunteer participants. Spot-checking technique, which checks each participant by allocating spotter jobs, is a promising approach to the validation of computation results. The current spot-checking technique and associated sabotage-tolerance methods are based on the implicit assumption that participants never detect the allocation of spotter jobs, however generating such spotter jobs is still an open problem. Hence, in the real VC environment where the implicit assumption does not always hold, spot-checking-based sabotage-tolerance methods (such as well-known credibility-based voting) become almost impossible to guarantee the computational correctness. In this paper, we generalize the spot-checking technique by introducing the idea of imperfect checking. Using our new technique, it becomes possible to estimate the correct credibility for participant nodes even if they may detect spotter jobs. Moreover, by the idea of imperfect checking, we propose a new credibility-based voting which does not need to allocate spotter jobs. Simulation results show that the proposed method reduces the computation time compared to the original credibility-based voting, while guaranteeing the same level of computational correctness.