Summary of Ml2sc: Deploying Machine Learning Models As Smart Contracts on the Blockchain, by Zhikai Li et al.
ML2SC: Deploying Machine Learning Models as Smart Contracts on the Blockchain
by Zhikai Li, Steve Vott, Bhaskar Krishnamachar
First submitted to arxiv on: 28 Mar 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Cryptography and Security (cs.CR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This research paper introduces Machine Learning to Smart Contract (ML2SC), a translator that converts multi-layer perceptron (MLP) models written in PyTorch to Solidity smart contract versions. The ML2SC uses a fixed-point math library to approximate floating-point computation, enabling the deployment of PyTorch-trained models on EVM-compatible blockchains like Ethereum. The paper shows that the gas costs associated with deploying and running these models on-chain increase linearly with various parameters, providing mathematical modeling and empirical results to support this claim. Additionally, the classification accuracy is evaluated, demonstrating that the outputs obtained by the transparent on-chain implementation are identical to those achieved using PyTorch off-chain. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper creates a way to use artificial intelligence models on blockchains, which helps keep computations safe and trustworthy. To do this, they made a program called ML2SC that can take models written in Python and turn them into code that can be used on blockchains like Ethereum. This program uses special math to make sure the calculations are done correctly, even though the computer is doing it differently than usual. The researchers tested their idea and showed that it works, with costs increasing as the size of the model grows. They also checked the accuracy of the models and found they were just as good when used on the blockchain. |
Keywords
» Artificial intelligence » Classification » Machine learning
