Fully-Distributed Construction of Byzantine-Resilient Dynamic Peer-to-Peer Networks

TL;DR

This paper presents a fully-distributed, randomized protocol for constructing and maintaining a resilient, sparse expander topology in dynamic P2P networks with high churn and Byzantine nodes, enabling efficient distributed algorithms.

Contribution

It introduces a novel scalable protocol that maintains high-expansion, low-degree networks resilient to Byzantine faults under continuous churn, with minimal overhead.

Findings

Maintains constant degree expander topology with high probability.

Tolerates up to o(n/polylog(n)) Byzantine nodes.

Operates with polylogarithmic communication and computation overhead.

Abstract

We address a fundamental problem in Peer-to-Peer (P2P) networks, namely, constructing and maintaining dynamic P2P overlay network topologies with essential properties such as connectivity, low diameter, and high expansion, that are resilient to continuous high churn and the presence of a large number of malicious (Byzantine) nodes. Our main goal is to construct and maintain a sparse (bounded degree) expander topology despite high churn and a large number of Byzantine nodes. Such an expander topology has logarithmic diameter, high expansion, and is robust to churn and the presence of a large number of bad nodes, and facilitates efficient and robust algorithms for fundamental problems in distributed computing, such as agreement, broadcasting, routing, etc. Our main contribution is a randomized, fully-distributed dynamic P2P protocol that works with only local initial knowledge and guarantees, with a high probability, the maintenance of a constant degree graph with high expansion even under continuous churn and in the presence of a large number of Byzantine nodes. Our protocol can tolerate up to $o(n/poly\log(n))$ Byzantine nodes (where $n$ is the stable network size). Our protocol is efficient, lightweight, and scalable, and it incurs only $O(poly\log(n))$ overhead for topology maintenance: only polylogarithmic (in $n$) bits need to be processed and sent by each honest node per round, and any honest node's computation cost per round is also polylogarithmic. Our protocol can be used as a building block for solving fundamental distributed computing problems in highly dynamic networks, such as Byzantine agreement and Byzantine leader election, and enables fast and scalable algorithms for these problems.