GitHub Repository

Sovereign Map is a production-grade, Byzantine-tolerant Federated Learning framework. Utilizing the Mohawk Protocol for streaming aggregation, it achieves a 224x memory reduction, enabling secure orchestration of 100M+ nodes via TPM 2.0 hardware-rooted trust. Features full-stack observability with Prometheus & Grafana, built-in tokenomics telemetry

2 starsPython

I solo-validated Fed learning at 10M nodes with 50% Byzantine tolerance

Name: I solo-validated Fed learning at 10M nodes with 50% Byzantine tolerance
Availability: InStock
Author: rwilliamspbgops

by rwilliamspbgops·Feb 25, 2026·2 points·0 comments

Visit Project View on HN

AI Analysis

●MidBig BrainWizardry

10M-node Byzantine FL is impressive; but GitHub release lacks runnable code or verifiable benchmarks.

Strengths

•50% Byzantine tolerance at 10M nodes scales orders of magnitude beyond published research (Google maxes ~10K)
•O(n log n) streaming aggregation architecture prevents memory explosion at scale
•Comprehensive documentation (deployment, API, architecture) signals serious implementation intent

Weaknesses

•No working code in release—only badges, status dashboards, and promises; cannot independently verify claims
•'59 minute' single run proves nothing; missing statistical significance, hardware specs, and reproducible test scripts

Post Description

I just finished testing a federated learning system at 10 million nodes.

It maintains 82% accuracy even when 5 million nodes are malicious.

Here's what happened ↓

---

*The Test (Feb 24, 2026)*

10,000,000 nodes 4,000,000 - 5,000,000 malicious (Byzantine) nodes 59 minutes 41 seconds total runtime 100% success rate

Results: • 40% Byzantine (4M bad): 83.3% accuracy • 50% Byzantine (5M bad): 82.2% accuracy

---

*Why this matters*

Google's federated learning papers max out at ~10K nodes in production.

Academic Byzantine fault tolerance systems (HoneyBadgerBFT, etc.) are tested at 100-1K nodes.

I just validated 10M nodes with 50% malicious participation—solo, in under an hour.

---

*Scaling proven across 5 orders of magnitude*

100 nodes → 10M nodes O(n log n) holds perfectly Streaming aggregation prevents memory death Per-round time: 127-154 seconds at 10M scale

---

*The stack*

- Rust/Go core (MOHAWK protocol) - Python SDK - WebAssembly edge runtime - zk-SNARK verification (<1ms) - Hardware root of trust (TPM 2.0) - Hierarchical batching for extreme scale

---

*Solo dev context*

Built this alone. 5 hours of continuous testing today. 135KB documentation. 100% test pass rate.

No $10M venture funding. No PhD team. No Google infrastructure.

Just code that works at any scale.

---

*What this enables*

- Global sensor networks (climate, defense, agriculture) - Cross-hospital AI without patient data sharing - Multi-national intelligence collaboration - Autonomous vehicle fleets training together - Any scenario where you can't trust 50% of participants

---

Release: https://github.com/rwilliamspbg-ops/Sovereign_Map_Federated_...

Repo: https://github.com/rwilliamspbg-ops/Sovereign_Map_Federated_...

Looking for: defense pilots, enterprise users, academic collaboration, contributors.

Happy to answer questions.