NEUROLEDGER
Verifiable federated learning for medical AI — patient data never leaves the hospital, every computation is cryptographically proven on 0G Chain.
Videos
Description
NeuroLedger solves the core problem in medical AI: hospitals cannot legally share patient data, so AI models train in isolation and stay mediocre. We built a federated learning network where hospitals collaborate on AI training without sharing any patient data.
Each hospital agent uploads their patient CSV, trains a logistic regression model locally, and applies Rényi Differential Privacy noise (ε=1.0) to the gradient before it leaves the machine. The DP-noised gradient is uploaded to 0G Storage (turbo network) as a content-addressed file. Its Merkle root hash and CID are submitted to the NeuroLedger smart contract on 0G Chain as a GradientSubmitted event.
The aggregation runs inside an Intel TDX hardware enclave via 0G Compute's TeeML network. Multi-Krum and Trimmed Mean algorithms provide Byzantine robustness. The enclave produces a real hardware attestation (mr_enclave, mr_signer non-zero, inference_valid=True). This attestation JSON is stored on 0G Storage and its root hash is anchored on-chain in the AggregationComplete event.
The defining feature: anyone can download the gradient CIDs from 0G Storage and reproduce the exact aggregation hash on-chain using our verification script. The computation is deterministically verifiable by any third party — not just claimed.
Built and deployed during the hackathon:
- NeuroLedger.sol with 8-event lifecycle on 0G Galileo Testnet + 0G Aristotle Mainnet
- 21+ completed rounds with real UCI medical datasets
- 6 hospitals as on-chain agents with staked AOGI
- Real TeeML hardware attestation every round since round 18
- Hospital CSV upload with automatic data deletion after gradient computation
- Full Next.js frontend deployed on Vercel with live chain data
- 49+ on-chain events auditable on chainscan-galileo.0g.ai
0G components used: 0G Chain (smart contract), 0G Storage turbo (gradient and model files), 0G Compute TeeML (hardware-attested aggregation).
Progress During Hackathon
<p>Week 1 — Core Infrastructure:</p><p>Designed architecture around 0G's full stack. Built NeuroLedger.sol with</p><p>8-event lifecycle. Deployed to 0G Galileo. Completed first end-to-end round</p><p>with 3 hospitals submitting real gradients on-chain. Fixed gas limit issues,</p><p>startRound event parsing, and aggregator role management.</p><p>Week 2 — Real Integrations:</p><p>Switched 0G Storage from standard (down) to turbo network using the official</p><p>TypeScript SDK — real Merkle root CIDs replacing SHA256 fallbacks. Integrated</p><p>0G Compute TeeML via compute starter kit. Achieved first round with real Intel</p><p>TDX hardware attestation (inference_valid=True). Built SSE streaming for live</p><p>runner output. Implemented hospital CSV upload with DP privacy deletion.</p><p>Week 3 — Scale + Polish:</p><p>Built full Next.js frontend: Training Simulator with phase progress, TEE</p><p>Enclaves panel, Artifact Ledger with 49+ events, dynamic hospital selector</p><p>reading from chain, dataset upload with class distribution stats. Registered</p><p>6 hospitals on-chain. Ran 21+ rounds. Deployed to Vercel. Deployed contract</p><p>to 0G Aristotle Mainnet. Built reproducibility verification script.</p><p>Final numbers: 21+ rounds, 6 hospitals, 49+ events, real TeeML every round.</p>
Tech Stack
Fundraising Status
<p>Not currently fundraising.</p><p>NeuroLedger is a working prototype with real on-chain proof. The next step</p><p>is piloting with actual hospitals in APAC where health data regulations are</p><p>actively evolving (Singapore PDPA, India DPDP Act 2023). Open to conversations</p><p>with healthcare institutions, research hospitals, or infrastructure teams</p><p>interested in verifiable medical AI.</p>