Neural Chain Architecture

Three-layer blockchain architecture powering decentralized AI inference

Three-Layer Architecture

3

AI Inference Layer

PyTorch + ONNX Runtime

  • Model registry and version control
  • TieredModelLoader (TorchScript, ONNX, llama.cpp)
  • Performance prediction and routing
  • KV-cache reuse and batching
2

Privacy & Consensus Layer

TEE + Zero-Knowledge Proofs

  • RSA 2048-bit + AES-256 encryption
  • Zero-knowledge proof verification
  • BFT consensus (80% threshold)
  • Node tier system (Gold/Silver/Bronze)
1

Universal Mining Layer

Dynamic Proof-of-Inference

  • Dynamic reward calculation
  • Performance-based multipliers
  • VRF-based random selection
  • Three-tier mining architecture

Core Components

Storage Network

IPFS content-addressed storage with caching, manifest support, and checksum management

Consensus Protocol

Byzantine fault-tolerant consensus requiring 80% agreement (8/10 miners, 40/50 verifiers)

Secure Enclaves

TEE attestation and threshold key management for protecting model secrets

Query Lifecycle

Client SDK → Network selection → Miner inference → Proof verification → Reward distribution

Query Data Flow

01

Query Submission

Client uploads encrypted payload off-chain and submits query hash on-chain

02

Miner Selection

Network selects eligible miner based on staking and infrastructure score

03

Inference Execution

Miner runs inference in TEE or secure software environment

04

Proof Generation

Miner generates zero-knowledge proof and posts it on-chain

05

Verification

Verifier validates proof and attestation deterministically

06

Finalization

On-chain module finalizes query, mints rewards, or initiates slashing

Performance Targets

<3s
P95 Latency
80%
Consensus Threshold
100%
Proof Verification