zkml zkml 是用于在 ZK-SNARK 中构建 ML 模型执行证明的框架。请阅读我们的博客文章和论文,了解实现细节…
zkml is a framework for constructing proofs of ML model execution in ZK-SNARKs. Read our blog post and paper for implementation details.
zkml requires the nightly build of Rust:
rustup override set nightlyRun the following commands:
# Installs rust, skip if you already have rust installed
curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh
git clone https://github.com/ddkang/zkml.git
cd zkml
rustup override set nightly
cargo build --release
mkdir params_kzg
mkdir params_ipa
# This should take ~16s to run the first time
# and ~8s to run the second time
./target/release/time_circuit examples/mnist/model.msgpack examples/mnist/inp.msgpack kzgThis will prove an MNIST circuit! It will require around 2GB of memory and take around 8 seconds to run.
To convert your own model and data, you will need to convert the model and data to the format zkml expects. Currently, we accept TFLite models. We show an example below.
First cd examples/mnist
We've already created a model that achieves high accuracy on MNIST (model.tflite). You will
need to create your own TFLite model. One way is to convert a model from Keras.
You will need to convert the model:
python ../../python/converter.py --model model.tflite --model_output converted_model.msgpack --config_output config.msgpack --scale_factor 512 --k 17 --num_cols 10 --num_randoms 1024There are several parameters that need to be changed depending on the model (scale_factor, k,
num_cols, and num_randoms).
npy. We've
written a small script to do this for the first test data point in MNIST:python data_to_npy.pypython ../../python/input_converter.py --model_config converted_model.msgpack --inputs 7.npy --output example_inp.msgpackcd ../../
./target/release/test_circuit examples/mnist/converted_model.msgpack examples/mnist/example_inp.msgpackIf you're interested in extending or using zkml, please contact us at ddkang [at] g.illinois.edu.
暂无开放 Issues,或尚未同步最近议题。