Blockchain-Based platform for Distribution AI

EasyChair Preprint 764

Abstract

In recent years, the current artificial intelligence exposed user data privacy during training and the high cost of training are getting more and more attention, which are becoming an obstacle to the development of AI. We identify the main issues as data privacy, ownership, and exchange and model privacy, which are difficult to be solved with the current centralized paradigm of machine learning training methodology or federating learning methodology. As a result, we propose a practical model training paradigm based on Blockchain, named Distributed AI, which aims to train a model with distributed data and to reserve the data ownership for their owners and the interest of trained model. In this new paradigm, we use Blockchain[3] as the base architecture in which we abstract different actors (i.e., model provider, data provider) taking different actions to archive own target, realize distributing encrypted model training by Federating Learning with different actors, set smart contract as model training infrastructure, set up notification server, pricing of training data is according to its contribution and therefore it is not about the exchange of data ownership.

Keyphrases: Actors, Blockchain, Distributed AI, Encrypted, smart contract

@booklet{EasyChair:764,
  author    = {Lifeng Liu and Chao Wu and Jun Xiao},
  title     = {Blockchain-Based platform for Distribution AI },
  doi       = {10.29007/4bz1},
  howpublished = {EasyChair Preprint 764},
  year      = {EasyChair, 2019}}