Papers › Twins: BFT Systems Made Robust
Twins: BFT Systems Made Robust
Shehar Bano, Alberto Sonnino, Andrey Chursin, Dmitri Perelman, Zekun Li, Avery Ching, Dahlia Malkhi
The archive published only this paper's code-link row. Authors, date and abstract are from arXiv's metadata (CC0), read from the Kaggle arXiv metadata snapshot of 2026-09-12 where its title matched the archive's; the title is the archive's.
This paper presents Twins, an automated unit test generator of Byzantine attacks. Twins implements three types of Byzantine behaviors: (i) leader equivocation, (ii) double voting, and (iii) losing internal state such as forgetting 'locks' guarding voted values. To emulate interesting attacks by a Byzantine node, it instantiates twin copies of the node instead of one, giving both twins the same identities and network credentials. To the rest of the system, the twins appear indistinguishable from a single node behaving in a 'questionable' manner. Twins can systematically generate Byzantine attack scenarios at scale, execute them in a controlled manner, and examine their behavior. Twins scenarios iterate over protocol rounds and vary the communication patterns among nodes. Twins runs in a production setting within DiemBFT where it can execute 44M Twins-generated scenarios daily. Whereas the system at hand did not manifest errors, subtle safety bugs that were deliberately injected for the purpose of validating the implementation of Twins itself were exposed within minutes. Twins can prevent developers from regressing correctness when updating the codebase, introducing new features, or performing routine maintenance tasks. Twins only requires a thin wrapper over DiemBFT, we thus envision other systems using it. Building on this idea, one new attack and several known attacks against other BFT protocols were materialized as Twins scenarios. In all cases, the target protocols break within fewer than a dozen protocol rounds, hence it is realistic for the Twins approach to expose the problems.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Results from the paper archive 2025-07-28
No leaderboard rows for this paper in the archive.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections