LinBFT: Linear-Communication Byzantine Fault Tolerance for Public Blockchains
This addresses scalability issues for public blockchain systems by reducing communication overhead, though it builds incrementally on known techniques like PBFT.
The paper tackles the problem of high communication complexity in Byzantine fault tolerance protocols for blockchains, presenting LinBFT which achieves amortized O(n) communication per block with deterministic safety and liveness guarantees, improving on previous quadratic or probabilistic methods.
This paper presents LinBFT, a novel Byzantine fault tolerance (BFT) protocol for blockchain systems that achieves amortized O(n) communication volume per block under reasonable conditions (where n is the number of participants), while satisfying determinist guarantees on safety and liveness. This significantly improves previous results, which either incurs quadratic communication complexity, or only satisfies safety in a probabilistic sense. LinBFT is based on the popular PBFT protocol, and cuts down its $O(n^4)$ complexity with three tricks, each by $O(n)$: linear view change, threshold signatures, and verifiable random functions. All three are known, i.e., the solutions are right in front of our eyes, and yet LinBFT is the first $O(n)$ solution with deterministic security guarantees. Further, LinBFT also addresses issues that are specific to permission-less, public blockchain systems, such as anonymous participants without a public-key infrastructure, proof-of-stake with slashing, rotating leader, and a dynamic participant set. In addition, LinBFT contains no proof-of-work module, reaches consensus for every block, and tolerates changing honesty of the participants for different blocks.