Federated Learning for Protecting Medical Data Privacy

Abstract

Deep learning is one of the most advanced machine learning techniques, and its prominence has increased in recent years. Language processing, predictions in medical research and pattern recognition are few of the numerous fields in which it is widely utilized. Numerous modern medical applications benefit greatly from the implementation of machine learning (ML) models and the disruptive innovations in the entire modern health care system. It is extensively used for constructing accurate and robust statistical models from large volumes of medical data collected from a variety of sources in contemporary healthcare systems [1]. Due to privacy concerns that restrict access to medical data, these Deep learning techniques have yet to completely exploit medical data despite their immense potential benefits. Many data proprietors are unable to benefit from large-scale deep learning due to privacy and confidentiality concerns associated with data sharing. However, without access to sufficient data, Deep Learning will not be able to realize its maximum potential when transitioning from the research phase to clinical practice [2]. This project addresses this problem by implementing Federated Learning and Encrypted Computations on text data, such as Multi Party Computation. SyferText, a Python library for privacy-protected Natural Language Processing that leverages PySyft to conduct Federated Learning, is used in this context.

Ähnliche Arbeiten