arXiv subjects

Lefteris Kokoris-Kogias

Publications and source records attributed to Lefteris Kokoris-Kogias.

23 records · Page 2Linked to original sources

arXiv2023

HammerHead: Leader Reputation for Dynamic Scheduling

The need for high throughput and censorship resistance in blockchain technology has led to research on DAG-based consensus. The Sui blockchain protocol uses a variant of the Bullshark consensus algorithm due to its lower latency, but this leader-based protocol causes performance issues when candidate leaders crash. In this paper, we explore the ideas pioneered by Carousel on providing Leader-Utilization and present HammerHead. Unlike Carousel, which is built with a chained and pipelined consensus protocol in mind, HammerHead does not need to worry about chain quality as it is directly provided by the DAG, but needs to make sure that even though validators might commit blocks in different views the safety and liveness is preserved. Our implementation of HammerHead shows a slight performance increase in a faultless setting, and a drastic 2x latency reduction and up to 40% throughput increase when suffering faults (100 validators, 33 faults).

cs.CR↗

arXiv2023

Cuttlefish: Expressive Fast Path Blockchains with FastUnlock

Cuttlefish addresses several limitations of existing consensus-less and consensus-minimized decentralized ledgers, including restricted programmability and the risk of deadlocked assets. The key insight of Cuttlefish is that consensus in blockchains is necessary due to contention, rather than multiple owners of an asset as suggested by prior work. Previous proposals proactively use consensus to prevent contention from blocking assets, taking a pessimistic approach. In contrast, Cuttlefish introduces collective objects and multi-owner transactions that can offer most of the functionality of classic blockchains when objects transacted on are not under contention. Additionally, in case of contention, Cuttlefish proposes a novel `Unlock' protocol that significantly reduces the latency of unblocking contented objects. By leveraging these features, Cuttlefish implements consensus-less protocols for a broader range of transactions, including asset swaps and multi-signature transactions, which were previously believed to require consensus.

cs.CR↗

arXiv2022

Bullshark: The Partially Synchronous Version

The purpose of this manuscript is to describe the deterministic partially synchronous version of Bullshark in a simple and clean way. This result is published in CCS 2022, however, the description there is less clear because it uses the terminology of the full asynchronous Bullshark. The CCS version ties the description of the asynchronous and partially synchronous versions of Bullshark since it targets an academic audience. Due to the recent interest in DAG-based BFT protocols, we provide a separate and simple description of the partially synchronous version that targets a more general audience. We focus here on the DAG ordering logic. For more details about the asynchronous version, garbage collection, fairness, proofs, related work, evaluation, and efficient DAG implementation please refer to the fullpaper. An intuitive extended summary can be found in the "DAG meets BFT" blogpost.

cs.DC↗

arXiv2022

Bullshark: DAG BFT Protocols Made Practical

We present Bullshark, the first directed acyclic graph (DAG) based asynchronous Byzantine Atomic Broadcast protocol that is optimized for the common synchronous case. Like previous DAG-based BFT protocols, Bullshark requires no extra communication to achieve consensus on top of building the DAG. That is, parties can totally order the vertices of the DAG by interpreting their local view of the DAG edges. Unlike other asynchronous DAG-based protocols, Bullshark provides a practical low latency fast-path that exploits synchronous periods and deprecates the need for notoriously complex view-change mechanisms. Bullshark achieves this while maintaining all the desired properties of its predecessor DAG-Rider. Namely, it has optimal amortized communication complexity, it provides fairness and asynchronous liveness, and safety is guaranteed even under a quantum adversary. In order to show the practicality and simplicity of our approach, we also introduce a standalone partially synchronous version of Bullshark which we evaluate against the state of the art. The implemented protocol is embarrassingly simple (200 LOC on top of an existing DAG-based mempool implementation (Narwhal & Tusk). It is highly efficient, achieving for example, 125,000 transaction per second with a 2 seconds latency for a deployment of 50 parties. In the same setting the state of the art pays a steep 50% latency increase as it optimizes for asynchrony.

cs.CR↗

arXiv2021

Be Prepared When Network Goes Bad: An Asynchronous View-Change Protocol

The popularity of permissioned blockchain systems demands BFT SMR protocols that are efficient under good network conditions (synchrony) and robust under bad network conditions (asynchrony). The state-of-the-art partially synchronous BFT SMR protocols provide optimal linear communication cost per decision under synchrony and good leaders, but lose liveness under asynchrony. On the other hand, the state-of-the-art asynchronous BFT SMR protocols are live even under asynchrony, but always pay quadratic cost even under synchrony. In this paper, we propose a BFT SMR protocol that achieves the best of both worlds -- optimal linear cost per decision under good networks and leaders, optimal quadratic cost per decision under bad networks, and remains always live.

cs.DC↗