Privacy-aware and Resource-saving Collaborative Learning for Healthcare in Cloud Computing
Abstract
Electronic health records (EHR), generated in healthcare, contain extensive digital information, such as diagnoses, medications and complications. Recently, many studies have focused on constructing deep learning (DL) models with EHR data to improve the quality of healthcare services. However, in traditional centralized training, the collection of EHR causes serious privacy issues due to vulnerable transmission channels and untrusted DL service providers. An alternative that can mitigate the above privacy threat is federated learning (FL). It enables multiple healthcare institutions to learn a global predictive model by exchanging locally calculated updates without disclosing the private dataset. Unfortunately, the latest studies have shown that the local updates still expose sensitive information about the original training data. While several privacy-preserving FL protocols have been proposed, few prior works focused on energy consumption issues. Specifically, local training requires extensive computational resources, which is prohibitively expensive for resource-limited institutions. To overcome the above problems, we propose PRCL, a Privacy-aware and Resource-saving Collaborative Learning protocol. To reduce the local computational overhead, we design a novel model splitting method that partitions the neural network into three parts and outsources the computationally large middle part to cloud servers. By using the lightweight data perturbation and packed partially homomorphic encryption, PRCL protects the privacy of the original data and labels, as well as the parameters of the model. Moreover, we analyze the security of the proposed protocol, and demonstrate the superior performance of PRCL in terms of accuracy and efficiency.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
FL can enable flexible and privacy-preserving EHRs management in healthcare operations by building intelligent EHRs systems with the cooperation of multiple medical institutions and a powerful server such as the cloud.
“It can be learned from [110] that FL can enable flexible and privacy-preserving EHRs management in healthcare operations, by building intelligent EHRs systems with the cooperation of multiple medical institutions and a powerful server such as the cloud.”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [110]
Network resource management in industrial FL-IoT system design has been solved via resource allocation and stochastic training optimization.
“Network resource management is another critical issue in industrial FL-IoT system design that has been solved via resource allocation [178] and stochastic training optimization [180].”
From Federated Learning for Internet of Things: A Comprehensive Survey (2021) · cites this paper as [178]
An FL-based student-centered architecture is responsible for an EHR system with different clinics and a database server.
“An FL-based student-centered architecture is responsible for an EHR system with different clinics as well as a database server [66].”
From A comprehensive survey on federated learning techniques for healthcare informatics (2023) · cites this paper as [66]
A privacy-aware and resource-saving collaborative learning protocol provides privacy for electronic health records in resource-saving scenarios by outsourcing the major learning component to cloud servers and using lightweight data perturbation and packed partially homomorphic encryption.
“A privacy-aware and resource-saving collaborative learning protocol is proposed to provide privacy for EHRs when the FL system is engaged in resource-saving scenario [38].”
From A Review of Privacy Enhancement Methods for Federated Learning in Healthcare Systems (2023) · cites this paper as [38]
HE is very effective for FL privacy preservation because most operations required by FL systems, such as aggregation, model updates, and gradient calculations, can be performed without accessing raw data.
“This approach is very effective for FL privacy preservation as most of the operations required by the FL systems like aggregation, model updates, and gradient calculations can be performed without accessing the raw data [34,35,36,37,38].”
From A Review of Privacy Enhancement Methods for Federated Learning in Healthcare Systems (2023) · cites this paper as [38]
PRCL reduces local training overhead by outsourcing the middle part to the cloud server while providing similar accuracy to other state-of-the-art approaches.
“The simulation results show that PRCL reduces the local training overhead because outsourcing the middle part to the cloud server while providing similar accuracy to other state-of-the-art approaches.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [68]
In PRCL, confidentiality is preserved because the cloud cannot access the plaintext gradient and an attacker can only get the perturbed data due to the added noise.
“At the same time, confidentiality is preserved since the cloud cannot access the plaintext gradient and an attacker can only get the perturbed data due to the added noise.”
From Handling privacy-sensitive medical data with federated learning: Challenges and future directions (2023) · cites this paper as [68]
Although attackers can obtain perturbed information of EHRs, it is hard to obtain or recover the original data.
“Although attackers can obtain perturbed information of EHRs, it is hard to obtain or recover the original data.”
From Federated learning for smart healthcare: A survey (2023) · cites this paper as [65]
A lightweight data perturbation method in FL for EHRs analytic management perturbs training-related data and can defend against model memorization attacks.
“To ensure privacy for model parameters in the FL process, a lightweight data perturbation method is considered to perturb the training-related data, which thus can defend model memorization attack in the learning.”
From Federated learning for smart healthcare: A survey (2023) · cites this paper as [65]
FL can be useful to build privacy-aware and resource-saving collaborative learning protocols for EHRs analytic management systems with cooperation of multiple hospital institutions and a data centre.
“FL can be useful to build privacy-aware and resource-saving collaborative learning protocols for EHRs analytic management systems with the cooperation of multiple hospital institutions and a data centre [65].”
From Federated learning for smart healthcare: A survey (2023) · cites this paper as [65]
The citation lists haven’t been fetched yet
References 21 · Cited by 52
- Authors
- Hao, M., Li, H., Xu, G., Liu, Z., & Chen, Z.
- Affiliations
- University of Electronic Science and Technology of China (CN)
- Nanjing University of Aeronautics and Astronautics (CN)
- Venue
- ICC 2020 - 2020 IEEE International Conference on Communications (ICC)
- Publisher
- IEEE
- Published
- 2020-06
- Pages
- 1-6
- ISSN
- 1550-3607 (ISSN-L)
- OpenAlex
- W3046115333
- Cited by
- 52
- References
- 21
- Citations by year
- 2026: 1 · 2025: 7 · 2024: 13 · 2023: 17 · 2022: 6 · 2021: 8
- FWCI
- 2.96
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Conference on Communications (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Physical Sciences › Computer Science › Artificial Intelligence › Cryptography and Data Security
- Keywords
- federated learning, privacy-preserving machine learning, electronic health records, model splitting, partially homomorphic encryption, data perturbation, energy-efficient training, cloud computing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
