Vogel A, Berger C, Kapitza R (2026)
Publication Language: English
Publication Status: Published
Publication Type: Other publication type
Publication year: 2026
URI: https://arxiv.org/abs/2609.18512
DOI: 10.48550/arXiv.2609.18512
Open Access Link: https://arxiv.org/abs/2609.18512
Fault-tolerant agreement protocols fail if replicas share a common flaw that simultaneously affects more replicas than the tolerable threshold. Therefore replicas should ideally fail independently, which can be achieved through diversification. However, in practice, often the same protocol implementation is shared by all replicas which is not surprising given that the provision of multiple diverse implementations is difficult and highly laborious. This poses a major risk, as a shared protocol implementation is a prime candidate for common bugs due to its complexity. With PatchyBFT, we demonstrate how, given a reference implementation, Large Language Models (LLMs) can be utilised for the automated and scalable generation of code that compiles, passes tests, and crucially differs semantically/binary-wise, that can re- place code in the reference implementation, thereby significantly reducing diversification costs. We demonstrate the feasibility of diversification of replication protocol implementations using LLMs by diversifying three implementations: PBFT, HotStuff, and Raft, showing how up to 65% of the codebase can be diversified.
APA:
Vogel, A., Berger, C., & Kapitza, R. (2026). PatchyBFT: Automating Diversification of Fault-Tolerant Systems using LLMs.
MLA:
Vogel, Arne, Christian Berger, and Rüdiger Kapitza. PatchyBFT: Automating Diversification of Fault-Tolerant Systems using LLMs. 2026.
BibTeX: Download