Blockchain-Enabled Federated Learning for Secure and Decentralised Learning

该项目旨在开发新的支持区块链的联邦学习技术，以实现安全和分散的学习。它解决了一个重要而紧迫的机器学习问题，即用于训练机器学习模型的数据通常由不同的所有者持有，这些所有者由于隐私问题而不愿意共享他们的数据，从而导致孤立的数据孤岛。该项目将产生一组创新算法，为区块链支持的联合学习中的关键挑战提供解决方案。该项目的预期成果将大大推进机器学习和区块链研究的前沿，并为澳大利亚和国际社会带来巨大的社会和经济效益。

This project aims to develop novel blockchain-enabled federated learning techniques for secure and decentralised learning. It addresses an important and urgent machine learning problem, that is, the data useful for training machine learning models are often held by different owners who are not willing to share their data due to privacy concerns, resulting in isolated data islands. The project will result in a set of innovative algorithms that provide solutions to the key challenges in blockchain-enabled federated learning. The expected outcomes of the project will dramatically advance the frontier of machine learning and blockchain research, and have massive social and economic benefits for Australia and international communities.