Third International Symposium on Parallel and Distributed Computing/Third International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Networks (ISPDC/HeteroPar'04)
Designing Modular Services in the Scattered Byzantine Failure Model
Cork, Ireland
July 05-July 07
ISBN: 0-7695-2210-6
In this paper, we propose the scattered byzantine failure model. In this model processes alternate correct and faulty periods. Specifically, during its faulty periods, a process behaves arbitrarily (one cannot expect anything from it during these periods) whereas during its correct periods, it behaves according to its specification. In that sense, the scattered Byzantine failure model generalizes the classical Byzantine failure model. We characterize two reliable services guaranteeing timeliness properties in the presence of Byzantine failures, namely the Clock Synchronization and the Δ-Atomic Broadcast. We identify necessary and sufficient conditions to ensure the correctness of both services in the scattered byzantine failure model.
Citation:
E. Anceaume, C. Delporte-Gallet, H. Fauconnier, M. Hurfin, G. Le Lann, "Designing Modular Services in the Scattered Byzantine Failure Model," ispdc, pp.262-269, Third International Symposium on Parallel and Distributed Computing/Third International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Networks (ISPDC/HeteroPar'04), 2004