zkCNN
CNN snark
An implementation of a GKR-based snark for CNN model inference, providing a zero-knowledge proof protocol for neural network computations.
A GKR-based zero-knowledge proof protocol for CNN model inference.
73 stars
3 watching
13 forks
Language: C++
last commit: over 3 years agoRelated projects:
| Repository | Description | Stars |
|---|---|---|
 lyronctk/zator | This project verifies the inference of a deep neural network using recursive SNARKs and leverages a folding scheme to reduce computation complexity. | 160 |
 zk-ml/tachikoma | Defines a standard for serializing neural network inference processes into a graph of operator computational traces. | 33 |
 luozhuzhang/zkps-circuit-snark | A zk-SNARK implementation using circom and snarkjs for secure multi-party computation and decentralized applications. | 61 |
 meilof/geppetri | An implementation of a Pinocchio-based adaptive zk-SNARK system for distributed computation | 16 |
 matter-labs-archive/snarkygpu | A GPU-based zkSNARK prover that aims to improve the performance of distributed verification processes for blockchain applications. | 23 |
 szagoruyko/binary-wide-resnet | An implementation of a 1-bit weight neural network architecture using PyTorch | 124 |
 jeshraghian/snntorch | A Python package for training spiking neural networks with gradient-based learning | 1,383 |
 iden3/snarkjs | A JavaScript and WebAssembly implementation of a zero-knowledge proof protocol for secure multi-party computations | 1,801 |
 benedekrozemberczki/capsgnn | A PyTorch implementation of a graph neural network architecture | 1,246 |
| benedekrozemberczki/mixhop-and-n-gcn | A deep learning framework implementation of higher-order graph convolutional architectures and their applications | 403 |
 ebfull/powersoftau | A multi-party computation protocol for generating secure parameters using zk-SNARKs | 141 |
 zokrates/zokrates | Toolbox for implementing and deploying zkSNARKs on the Ethereum blockchain | 1,836 |
 consensys/gnark | A fast zk-SNARK library with a high-level API to design circuits. | 1,459 |
| benedekrozemberczki/sgcn | An implementation of a deep learning algorithm for graph data | 270 |