Publications

Publications

Blockchain-orchestrated machine learning for privacy preserving federated learning in electronic health data

Abstract:
Machine learning and blockchain technology have been explored for potential applications in medicine with only modest success to date. Focus has shifted to exploring the intersection of these technologies along with other privacy preserving encryption techniques for better utility.

End-to-end privacy preserving deep learning on multi-institutional medical imaging

Abstract:
Using large, multi-national datasets for high-performance medical imaging AI systems requires innovation in privacy-preserving machine learning so models can train on sensitive data without requiring data transfer. Here we present PriMIA (Privacy-preserving Medical Image Analysis), a free, open-source software framework for differentially private, securely aggregated federated learning and encrypted inference on medical imaging data.

A Taxonomy of Attacks on Federated Learning

Abstract:
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

Abstract:
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

Abstract:
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.

Pragmatic, Interdisciplinary Perspectives on Blockchain and Distributed Ledger Technology: Paving the Future for Healthcare

Abstract:
Background: Blockchain and distributed ledger technology is a disruptive force in healthcare. Methods: This article provides a globally relevant, interdisciplinary perspective intended to aid disparate group of actors, participants, and users that represent the diverse stakeholders of an increasingly complex and technologically reliant healthcare system. Domain expertise reinforced by literature published via industry, technical, and academic venues was used to inform these perspectives.

Blockchain in healthcare, research, and scientific publishing

Abstract:
Data are being transmitted and stored on cloud-based networks, including clinical, research, and publishing data. These cloudbased systems often lack comprehensiveness, accessibility, interoperability, confidentiality, accountability, and flexibility, which can cause delays for medical treatments, slowed research projects, and general inefficiencies. The advent of blockchain-based technologies provides a reliable solution to ensure that data storage and access are standardised and transparent, independent of a trusted third party.

Blockchain Compliance by Design: Regulatory Considerations for Blockchain in Clinical Research

As clinical research moves toward real-world data capture with increased data sharing, there is a growing need for patient-centered technologies that ensure data authenticity and promote researcher and patient access. Blockchain is one of an emerging set of distributed ledger technologies with the potential to offer both research data transparency and trust, while offering robust security measures. As blockchain-based systems are being developed for clinical research applications, these systems may be required to follow state and federal research regulations, such as ethical protections for human participants and data privacy.

Blockchain in healthcare, research, and scientific publishing

Abstract:
Data are being transmitted and stored on cloud-based networks, including clinical, research, and publishing data. These cloudbased systems often lack comprehensiveness, accessibility, interoperability, confidentiality, accountability, and flexibility, which can cause delays for medical treatments, slowed research projects, and general inefficiencies. The advent of blockchain-based technologies provides a reliable solution to ensure that data storage and access are standardised and transparent, independent of a trusted third party.

The case for establishing a blockchain research and development program at an academic medical center

To develop a research and development program to study factors that will support research, education and innovation using blockchain technology for health in an effective and sustainable manner. We proposed to conduct qualitative research to generate insights for developing a market strategy to build a research lab for the promotion of blockchain technologies in health in academic environments. The team aimed to identify the key barriers and opportunities for developing a sustainable research lab that generates research, education, and application of blockchain in healthcare at an academic medical institution and test those strategies in a real-world scenario.

Shopping Cart