Skip to content

Mathematical formulations and circuit designs for zero-knowledge proofs.

License

Notifications You must be signed in to change notification settings

inference-labs-inc/zkml-blueprints

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

22 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

zkml-blueprints

A growing collection of custom circuit designs—with every constraint proven and every idea explained.
Built for clarity, rigor, and community collaboration—the reference we all wish we’d had!


zkml-blueprints is a collection of mathematical formulations and circuit designs supporting zero-knowledge (ZK) proofs for machine learning (ML) applications, focusing on efficiently implementing provable computations in ZK circuits. This repository provides formal descriptions, constraints, and structured blueprints for designing circuits that preserve privacy while ensuring verifiable correctness.

If you're new here, a good starting point is the matrix addition, Hadamard product, and matrix multiplication blueprint. It introduces the core ideas and verification paradigm used throughout the project, grounded in addition and multiplication over finite fields, before moving on to more technical constructions.

Features

  • 📖 Mathematical Formulations – Rigorous explanations of key principles underlying ZK circuit design.
  • 🛠 Circuit Constraints – Well-documented approaches to encoding computations in finite fields.
  • Implementation Guidelines – Blueprints for translating mathematical constructs into efficient circuit implementations.
  • 🔒 Use Cases – Applications in cryptographic protocols, zk-SNARKs, and privacy-preserving machine learning.

This repository aims to serve as a structured reference for researchers, developers, and practitioners working on ZK and zkML proof systems, offering both theoretical insights and practical implementations.

💡 Contributions and discussions are welcome!


📁 Repository Structure

Each subdirectory focuses on a specific class of operations:

Directory Contents
core_ops/ Range checks, max/min, and basic ReLU formulations
matmul/ Hadamard product, matrix addition, and matrix multiplication (standard and quantized)
pooling/ Max and min pooling circuits (⏳ coming soon)
conv_layers/ Convolutional layer blueprints (⏳ coming soon)
activation/ Activation functions like ReLU, LeakyReLU, etc. (only ReLU at this stage; others may follow in future work)
utils/ Internal links and shared references for documentation navigation

Each section contains:

  • 📄 PDF blueprints describing the circuit logic, constraints, and mathematical justification
  • 📓 (Planned) Jupyter notebooks for live examples and testing
  • 📘 A local README.md with context and links

About

Mathematical formulations and circuit designs for zero-knowledge proofs.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published