by drCathieSo.eth
11/9/2023Zator: Verified inference of a 512-layer neural network using recursive SNARKs 🐊
5/16/2023ZK-friendly ML paradigms Background For ZK Hack Lisbon, I teamed up with a few ML and cryptography veterans to build Zero Gravity, where we proposed a novel approach to efficiently prove the correctness of machine learning model calculations using Weightless Neural Networks (WNNs), which are combinatorial and do not rely on floating point arithmetic. WNNs learn from input-output pairs using RAM cells as lookup tables, making them more amenable to Zero Knowledge Proofs. The project utilizes Bloom filters to make RAM cells scalable and introduces a new non-cryptographic hash function, the "MishMash", to improve performance. Research Directions/Tasks Implementing the Zero Gravity paradigm in Plonky2/Halo2 Identify and explore other high-accuracy weightless models In particular, evaluate their "ZK-friendliness" by their potential compatibility with ZKP, taking into consideration their computational complexity and performance on real-world datasets. e.g. boolean circuits, binarized neural networks, truth table net, ... Benchmarking (see below)
5/3/2023or
By clicking below, you agree to our terms of service.
New to HackMD? Sign up