awesome-zkml

-

:

by (video)

( )

( , , , )

-

-

-

-

-

-

(Jul 2023)

-

-

-

zk-mnist

(2022)

zk-ml/demo

(2021)

circomlib-ml

(2022)

proto-neural-zkp

(2022)

RockyBot

(2022)

ezkl

by (2022+)

keras2circom

( ) (2023)

Zator

Verified inference of a 512-layer neural network using recursive SNARKs

Otti

(2022)

Linear A - tachikoma

(2022+)

Linear A - uchikoma

(2022+)

zk-dtp

Zero Knowledge Decision Tree Predict is designed to address this pressing issue by offering privacy-preserving predictions using decision tree models, built on top of RISC Zero's zkVM

zkp-gravity/0g

ZeroGravity - Zero Gravity is a system for proving an inference run (i.e. a classification) for a pre-trained, public Weightless NN and a private input. (2023)

ddkang/zkml

zkml is a framework for constructing proofs of ML model execution in ZK-SNARKs

ZKaggle

and - (2023)

(slides)

, , , (2022)

Axiom provides smart contracts trustless access to all on-chain data and arbitrary expressive compute over it. Like GPUs do for CPUs, Axiom augments blockchain consensus with zero-knowledge proofs

The 0xPARC Foundation promotes application-level innovation on Ethereum and other decentralized platforms

A Privacy-Preserving Proof-of-Personhood Protocol

Fully on-chain artificial intelligence on Starknet

Bringing powerful ML models on-chain

The General Purpose Zero-Knowledge VM

A product and service company developing hardware-accelerated cryptography for verifiable and confidential computing

(Hardware) - Zero Knowledge ASICs (ZPU)

(FHE ML / FHE-ZK ML) - FHE tooling for machine learning, blockchain and more. ZK-FHE is an interesting research area. is a very interesting community with a lot of potential for collaboration

ZKML tooling for Circom

Platform for building fully private and programmable Web applications

@ Ethereum Foundation - Some ZKML research initiatives

Lending protocol for staked & restaked assets. They partnered with Modulus to build a risk engine that analyzes validator credit risk. Read more

RockyBot

On-chain verifiable ML trading bot -

Enhancing the options protocol AMM with intelligent features

Creating a transparent AI-based reputation system for

Working on the technical breakthroughs needed for contract-level compliance tools using ML for (a zk-rollup with privacy features)

ML as a Service (MLaaS) transparency ( )

Verifying that a user has created a valid and unique locally by running the IrisCode model on self-hosted biometric data and is calling function on the WorldID Semaphore identity group with a valid identityCommitment. -> Makes protocol more permissionless

Creates the ability for creating a ZK proof of /fraud. Anomaly detection models could be trained on smart contract data and agreed upon by DAOs as interesting metrics to be able to automate security procedures such as preventively pausing contracts in a more proactive way. There are startups already looking at using ML models for security purposes in a smart contract context, so ZK anomaly detection proofs feel like the natural next step

Privacy-preserving inference: medical diagnostics on private patient data get fed into the model and the sensitive inference (i.e. cancer test result) gets sent to the patient. ( )