کنفرانس بین المللی فناوری اطلاعات و دانش

صفحه اصلی / پانزدهمین کنفرانس بین المللی فناوری اطلاعات و دانش

A Novel Decentralized Privacy Preserving Federated Learning Model for Healthcare Applications

نویسندگان :

Saba Ameri¹ Reza Ebrahimi Atani²

1- دانشگاه گیلان 2- دانشگاه گیلان

کلمات کلیدی :

Decentralized Learning،Edge AI،Federated Learning،Distributed Deep Learning،Privacy Preserving AI

چکیده :

With the increasing use of deep learning algorithms in various fields of science, particularly in healthcare and disease diagnosis, challenges related to data availability are often encountered. In the healthcare industry, due to the sensitivity around patient privacy, data collection is limited. To train a high-quality deep learning model capable of aiding in disease diagnosis, a large amount of data is required, which is difficult to obtain under these conditions. One solution for utilizing healthcare data to train an effective deep learning model is to implement distributed deep learning models, where data remains local but still participates in the training process of proposing a deep learning model. While some implementations of distributed deep learning, such as federated learning, exist, they suffer vulnerabilities in preserving data privacy. The goal of this research is to develop a distributed deep learning model that safeguards user’s privacy from both internal and external attacks while maintaining the quality of the deep learning model.