awesome-zkml

ZKML hub

A curated collection of resources and projects focused on ZKML (Zero-Knowledge Machine Learning) for its developers.

awesome-zkml repository

GitHub
821 stars
39 watching
129 forks
last commit: 4 months ago
Linked from 1 awesome list

managed-by-terraform

awesome-zkml / Learn ZK
Ingopedia 708 21 days ago
zkProof Standards - Resource
ZK Mesh - resource
Curated list of ZKP implementations
Awesome - Matter labs - ZK proofs 5,298 about 2 months ago
Awesome - Mikerah - Privacy on Blockchains 260 11 months ago
Resource: Awesome_Plonk 229 3 months ago
ZK research 0x
ZK canon
Proofs, Args and ZK - Justin Thaler

awesome-zkml / Learn ML
awesome-machine-learning 66,046 10 days ago

awesome-zkml / Learn ML / awesome-machine-learning
books 66,046 10 days ago
courses 66,046 10 days ago
content 66,046 10 days ago
events 66,046 10 days ago
meetups 66,046 10 days ago

awesome-zkml / Content / ZKML community calls
ZKML community call #0

awesome-zkml / Content / Articles and podcasts
Zero Knowledge Machine Learning -
Zero-Knowledge Proofs and Their Applications to Machine Learning (video)
ZK Machine Learning
ZK for ML
Zero Knowledge Podcast :
Zero-Knowledge Machine Learning by (video)
Modulus Labs ( )

awesome-zkml / Content / Articles and podcasts / Modulus Labs
Chapter 1: How to Put Your AI On-Chain
Chapter 2: Why Put Your AI On-Chain?
Chapter 3: The World’s First On-Chain AI Trading Bot
Chapter 4: Blockchains that Self-Improve
Chapter 5: The Cost of Intelligence

awesome-zkml / Content / Articles and podcasts
Trustless Verification of Machine Learning ( , , , )
ZK Podcast - episode 265: Where ZK and ML intersect with Yi Sun and Daniel Kang
Linear A Research 22 almost 2 years ago
An introduction to zero-knowledge machine learning - Worldcoin
Zero Gravity (The Weight is Over) - ZKHack Lisbon
Zero-Knowledge Decision Tree Prediction (ZK-DTP) - ZKHack Lisbon
Open-sourcing zkml: Trustless Machine Learning for All -
Checks and balances: Machine learning and zero-knowledge proofs -
ZKML: Bridging AI/ML and Web3 with Zero-Knowledge Proofs -
Do language models possess knowledge (soundness)? -
Balancing the Power of AI/ML: The Role of ZK and Blockchain - SevenX Ventures
The Ultimate Guide to the ZKML ecosystem (Twitter thread) -
Verified Execution of GPT, Bert, CLIP, and more -
zkML: Evolving the Intelligence of Smart Contracts Through Zero-Knowledge Cryptography - 1kx
Dcbuilder - Zero-Knowledge Machine Learning and its use cases (Jul 2023)
TensorPlonk: A “GPU” for ZKML, Delivering 1,000x Speedups -
ZK10: ZKML with EZKL: Where we are and the future -
ZK10: ZKML Endgame: Specialized ZK Proving with GKR -
ezkl blog
Modulus blog
Giza blog
The promise and challenges of crypto + AI applications - Vitalik Buterin

awesome-zkml / Codebases
zk-mnist 119 about 2 years ago (2022)
zk-ml/demo 213 over 2 years ago (2021)
circomlib-ml 166 5 months ago (2022)

awesome-zkml / Codebases / circomlib-ml
Gitcoin Grant Proposal

awesome-zkml / Codebases
proto-neural-zkp 169 4 months ago (2022)
RockyBot 131 11 months ago (2022)
ezkl 946 5 days ago by (2022+)
keras2circom 289 9 months ago ( ) (2023)
Zator 156 over 1 year ago Verified inference of a 512-layer neural network using recursive SNARKs
Otti 6 over 1 year ago (2022)
Linear A - tachikoma 33 about 1 year ago (2022+)
Linear A - uchikoma 29 about 2 years ago (2022+)
zk-dtp 24 about 1 year ago 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 40 over 1 year ago 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 345 6 months ago zkml is a framework for constructing proofs of ML model execution in ZK-SNARKs
ZKaggle 25 over 1 year ago and - (2023)

awesome-zkml / Papers
Justin Thaler (2013). "Time-Optimal Interactive Proofs for Circuit Evaluation"
Pengtao Xie, Misha Bilenko, Tom Finley, Ran Gilad-Bachrach, Kristin Lauter, Michael Naehrig (2014). "Crypto-Nets: Neural Networks over Encrypted Data"
Nathan Dowlin, Ran Gilad-Bachrach, Kim Laine, Kristin Lauter, Michael Naehrig, John Wernsing (2016). "CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy"
Zahra Ghodsi, Tianyu Gu, Siddharth Garg (2017). "SafetyNets: Verifiable Execution of Deep Neural Networks on an Untrusted Cloud"
Payman Mohassel and Yupeng Zhang (2017). "SecureML: A System for Scalable Privacy-Preserving Machine Learning"
Jian Liu, Mika Juuti, Yao Lu, and N. Asokan (2017). "Oblivious Neural Network Predictions via MiniONN transformations"
Seunghwa Lee, Hankyung Ko, Jihye Kim, and Hyunok Oh (2020). "vCNN: Verifiable Convolutional Neural Network based on zk-SNARKs"
Ramy E. Ali, Jinhyun So, A. Salman Avestimehr (2020). "On Polynomial Approximations for Privacy-Preserving and Verifiable ReLU Networks"
Boyuan Feng, Lianke Qin, Zhenfei Zhang, Yufei Ding, and Shumo Chu (2021). "ZEN: An Optimizing Compiler for Verifiable, Zero-Knowledge Neural Network Inferences"
Tianyi Liu, Xiang Xie, and Yupeng Zhang (2021). "zkCNN: Zero Knowledge Proofs for Convolutional Neural Network Predictions and Accuracy"
Chenkai Weng, Kang Yang, Xiang Xie, Jonathan Katz, and Xiao Wang (2021). "Mystique: Efficient Conversions for Zero-Knowledge Proofs with Applications to Machine Learning" (slides)
Jiasi Weng, Jian Weng, Member, IEEE, Gui Tang, Anjia Yang, Ming Li, Jia-Nan Liu (2022). pvCNN: Privacy-Preserving and Verifiable Convolutional Neural Network Testing
Sebastian Angel, Andrew J. Blumberg, Eleftherios Ioannidis, Jess woods (2022). Efficient Representation of Numerical Optimization Problems for SNARKs
Daniel Kang , , , (2022)
Haodi Wang, Thang Hoang (2022). ezDPS: An Efficient and Zero-Knowledge Machine Learning Inference Pipeline
Modulus Labs - The Cost of Intelligence: Proving Machine Learning Inference with Zero-Knowledge

awesome-zkml / Projects interested in ZKML
Axiom 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
0xPARC The 0xPARC Foundation promotes application-level innovation on Ethereum and other decentralized platforms

awesome-zkml / Projects interested in ZKML / 0xPARC
zkMnist

awesome-zkml / Projects interested in ZKML
Worldcoin A Privacy-Preserving Proof-of-Personhood Protocol

awesome-zkml / Projects interested in ZKML / Worldcoin
proto-neural-zkp 169 4 months ago

awesome-zkml / Projects interested in ZKML
Gizatech Fully on-chain artificial intelligence on Starknet
Modulus Labs Bringing powerful ML models on-chain
Risc Zero The General Purpose Zero-Knowledge VM
Supranational A product and service company developing hardware-accelerated cryptography for verifiable and confidential computing
Ingonyama (Hardware) - Zero Knowledge ASICs (ZPU)
Zama.ai (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
zkMachineLearning ZKML tooling for Circom
Aleo Platform for building fully private and programmable Web applications
PSE team @ Ethereum Foundation - Some ZKML research initiatives
Ion Protocol Lending protocol for staked & restaked assets. They partnered with Modulus to build a risk engine that analyzes validator credit risk. Read more

awesome-zkml / Use cases / Computational integrity
Modulus Labs

awesome-zkml / Use cases / Computational integrity / Modulus Labs
RockyBot 131 11 months ago On-chain verifiable ML trading bot -

awesome-zkml / Use cases / Computational integrity / Modulus Labs / Blockchains that self-improve vision (examples):
Lyra finance Enhancing the options protocol AMM with intelligent features
Astraly Creating a transparent AI-based reputation system for
Aztec Protocol Working on the technical breakthroughs needed for contract-level compliance tools using ML for (a zk-rollup with privacy features)

awesome-zkml / Use cases / Computational integrity
link ML as a Service (MLaaS) transparency ( )
Worldcoin

awesome-zkml / Use cases / Computational integrity / Worldcoin
WorldID 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

awesome-zkml / Use cases / Computational integrity / ZK anomaly/fraud detection
exploitability 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

awesome-zkml / Use cases / Privacy
vCNN paper, page 2/16 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. ( )

Backlinks from these awesome lists:

More related projects: