Federated Learning (FL) is a method for training machine learning algorithms on decentralized data where sharing the raw data is not feasible due to privacy regulations. An instance of such data is Electronic Health Records (EHRs), which contain confidential patient information. In FL, the sensitive data is not shared, rather local models are trained and the model parameters are then aggregated on a central server. However, this method presents privacy challenges, necessitating the implementation of privacy protection strategies, such as data anonymization, before sharing the model parameters. Balancing the trade-off between privacy and utility is a crucial aspect in FL research, as integrating privacy algorithms can have an impact on the utility. The objective of this thesis is to improve the performance of FL while maintaining privacy, through techniques like data generalization, feature selection for dimension reduction, and minimizing noise in the anonymization process. This research also investigates separating data based on features instead of records and evaluates the performance of the proposed model using real healthcare data, with the aim of developing a predictive model for healthcare applications.
An important class of location-based services (LBSs) is information queries that provide users with location information of nearby point of interests such as a restaurant, a hospital or a gas station. To access an LBS, a user has to reveal her location to the locationbased service provider (LSP). From the revealed location, the LSP can infer private information about the user's health, habit and preferences. Thus, along with the benefits, LBSs also bring privacy concern to the users. Hence, protecting the privacy of LBSs users is a major challenge. Another major challenge is to ensure the reliability and correctness of the provided LBSs by the LSP, which is known as authentication. We develop a novel authentication technique that supports variants of privacy preserving LBSs with less storage and communication overhead. More importantly, we present a unified framework that can handle authentication for a wide range of privacy preserving location-based queries, range, nearest neighbor, and group nearest neighbor queries. We conduct experiments to show the efficiency and effectiveness of our approach in comparison with the state-of-art techniques.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.