Blockchain-orchestrated machine learning for privacy preserving federated learning in electronic health data
End-to-end privacy preserving deep learning on multi-institutional medical imaging
A Taxonomy of Attacks on Federated Learning
Federated learning is a privacy-by-design framework that enables training deep neural networks from decentralized sources of data, but it is fraught with innumerable attack surfaces. We provide a taxonomy of recent attacks on federated learning systems and detail the need for more robust threat modeling in federated learning environments.
2CP: Decentralized Protocols to Transparently Evaluate Contributivity in Blockchain Federated Learning Environments
Federated Learning harnesses data from multiple sources to build a single model. While the initial model might belong solely to the actor bringing it to the network for training, determining the ownership of the trained model resulting from Federated Learning remains an open question. In this paper we explore how Blockchains (in particular Ethereum) can be used to determine the evolving ownership of a model trained with Federated Learning.
A Systematic Comparison of Encrypted Machine Learning Solutions for Image Classification
This work provides a comprehensive review of existing frameworks based on secure computing techniques in the context of private image classification. The in-depth analysis of these approaches is followed by careful examination of their performance costs, in particular runtime and communication overhead.