article · Computers
Existing leaderless Byzantine Fault Tolerance blockchain protocols such as Redbelly achieve high scalability and low energy consumption, but cannot assess transaction fraud or node misbehaviour. ML-Redbelly addresses this by adding four machine learning components directly to the consensus pipeline without compromising protocol safety or liveness. These additions include a LightGBM fraud classifier, an Isolation Forest anomaly detector, a Q-learning agent for adaptive committee selection, and a Paillier-based privacy-preserving federated learning aggregator. In discrete-event simulations evaluated on a standard fraud detection benchmark, the machine learning layer adds minimal overhead, reducing throughput by only about 4 percent. The integrated framework sustains 48,844 transactions per second across 32 validators, outperforming traditional leader-based protocols while maintaining energy consumption orders of magnitude lower than proof-of-work systems.
Blockchain networks frequently face trade-offs between transaction speed, energy use, and security against fraudulent activity. By introducing automated fraud detection and node monitoring directly into the consensus process with minimal processing delay, networks can block economic fraud and malicious participants proactively. This provides a path toward scalable, secure distributed ledgers that avoid the heavy environmental costs associated with traditional proof-of-work mining.
The framework could enable secure, high-throughput transaction processing for enterprise blockchain networks, financial technology providers, and distributed systems requiring native fraud prevention. Evaluated through discrete-event simulations against a 400,000-transaction fraud benchmark rather than on a live network, the technology is currently at the applied research stage, with real-cluster deployment noted as the next necessary milestone.
AI-generated from the published abstract. Always read the original work before citing.
Blockchain consensus still forces a hard choice among scalability, security, and energy use. Redbelly, a leaderless Byzantine Fault Tolerance protocol, largely settles the scalability-versus-energy side of that tension, yet it accepts any cryptographically valid transaction without judging whether it is economically fraudulent or whether the node behind it is misbehaving. That blind spot is what we target. We present ML-Redbelly, a formally specified extension that attaches four learning components to the Redbelly pipeline: a LightGBM gradient-boosted fraud classifier, an Isolation Forest behavioural anomaly detector, a tabular Q-Learning agent for adaptive committee selection, and a Paillier-based federated learning aggregator that keeps model updates private. We prove that this layer leaves Redbelly’s safety and liveness intact, give pseudocode and complexity bounds for every component, and measure the system on the IEEE-CIS Fraud Detection benchmark (400,000 transactions) paired with a faithful discrete-event Redbelly simulator parameterised from measured inputs and validated against the published Redbelly deployment. LightGBM reaches an F1 of 0.783 (precision 0.858, recall 0.719, AUROC 0.963), a 34 percent relative F1 gain over the conference-baseline Random Forest at five times the inference speed. The Isolation Forest detector attains recall 0.885 at a false-positive rate of 0.047, and the Q-Learning agent settles into a stable policy within about 200 rounds across normal, bursty, and Byzantine-attack conditions. End to end, the framework sustains 48,844 TPS on 32 validators (mean over 30 seeds), and because the leaderless superblock commits every proposer’s block in parallel, this throughput advantage over leader-based BFT grows with the validator count (5.0 times PBFT and 2.9 times HotStuff at 32 validators). The learning layer costs only about 4 percent in throughput, since the measured ML inference is small next to the geo-distributed consensus round. Per-transaction energy is comparable across BFT protocols, being dominated by signature verification, and is orders of magnitude below proof-of-work chains, which expend energy on mining. One federated update epoch takes 36 s across 10 nodes with 2048-bit Paillier keys and reconstructs gradients with negligible error. All performance figures are emergent outputs of the discrete-event simulation, which reproduces the published Redbelly benchmark to within a conservative factor of about 1.7. Taken together, these results outline a simulation-validated design for making consensus intelligent as well as fast and identify the steps needed toward real-cluster deployment.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.3390/computers15090579
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
