ISC-MTI: An IPFS and smart contract-based framework for machine learning model training and invocation

Abstract

Due to centralized storage, centralization problems are common in machine learning model training and invocation, which makes train data and trained models extremely vulnerable to tampering and stealing. A safe framework for training and invoking models called ISC-MTI (IPFS (InterPlanetary File System) and Smart Contract-Based Method for Storage and Invocation of Machine Learning Mobel) is proposed in this paper. The framework uses IPFS as the storage solution, EOS (Enterprise Operation System) blockchain as the smart contract platform, RSA and AES as the implementation of encrypted communication. The Action responsible for invoking the training data and trained models in the smart contract and the model training, uploading, and invoking methods are designed. The experimental results demonstrate that ISC-MTI can improve the safety of model training and invocation with losing a little efficiency. Simultaneously, ISC-MTI can provide anti-theft model capabilities, traceability, tamper resistance, reliability, and privacy for the process.