Privacy Preserving Federated Big Data Analysis

Dai, Wenrui; Wang, Shuang; Xiong, Hongkai; Jiang, Xiaoqian

doi:10.1007/978-3-319-53817-4_3

Cited by 19 publications

(14 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another major difficulty in data sharing is related to privacy concerns as inappropriate access to sensitive patient data might lead to patients' identity disclosure. While there are machine learning techniques that preserve data privacy [101][102][103][104][105], it is often impossible to share patient data due to privacy issues. Thus, providing workflow and computer code associated with publications is becoming increasingly common to enable the reproducibility of the method, if not the full work.…”

Section: Computational Resources and Reproducibilitymentioning

confidence: 99%

Deep representation learning of patient data from Electronic Health Records (EHR): A systematic review

Zhao

et al. 2021

Journal of Biomedical Informatics

Self Cite

122

View full text Add to dashboard Cite

Section: Computational Resources and Reproducibilitymentioning

confidence: 99%

Deep representation learning of patient data from Electronic Health Records (EHR): A systematic review

Zhao

et al. 2021

Journal of Biomedical Informatics

Self Cite

122

View full text Add to dashboard Cite

“…Motivated by privacy concerns of distributed learning in the cloud, the federated learning [14], [15], [16], [17] has been proposed as an efficient method to train a federated model by aggregating outsourced local models trained on multiple DIs in a privacy-preserving way. Since local models contain sensitive information of DIs, each DI encrypts individual local model under his/her key before outsourcing it to the cloud [18].…”

Section: Introductionmentioning

confidence: 99%

Pocket Diagnosis: Secure Federated Learning against Poisoning Attack in the Cloud

Miao

et al. 2020

Preprint

View full text Add to dashboard Cite

Federated learning has become prevalent in medical diagnosis due to its effectiveness in training a federated model among multiple health institutions (i.e., Data Islands (DIs)). However, increasingly massive DI-level poisoning attacks have shed light on a vulnerability in federated learning, which inject poisoned data into certain DIs to corrupt the availability of the federated model. Previous works on federated learning have been inadequate in ensuring the privacy of DIs and the availability of the final federated model. In this paper, we design a secure federated learning mechanism with multiple keys to prevent DI-level poisoning attacks for medical diagnosis, called SFPA. Concretely, SFPA provides privacy-preserving random forest-based federated learning by using the multi-key secure computation, which guarantees the confidentiality of DI-related information. Meanwhile, a secure defense strategy over encrypted locally-submitted models is proposed to defense DI-level poisoning attacks. Finally, our formal security analysis and empirical tests on a public cloud platform demonstrate the security and efficiency of SFPA as well as its capability of resisting DI-level poisoning attacks.

show abstract

“…The motivation of gleaning insights from vertically partitioned data dates back to association rule mining Clifton (2002, 2003). A few very recent studies Kenthapadi et al (2013); Ying et al (2018); Hu et al (2019); Heinze-Deml et al (2018); Dai et al (2018); Stolpe et al (2016) have reinvestigated vertically partitioned features under the setting of distributed machine learning, which is motivated by the ever-increasing data dimensionality as well as the opportunity and chal-lenge of cooperation between multiple parties that may hold different aspects of information about the same samples.…”

Section: Introductionmentioning

confidence: 99%

Learning Privately over Distributed Features: An ADMM Sharing Approach

Hu,

Liu,

Kong

et al. 2019

Preprint

View full text Add to dashboard Cite

Distributed machine learning has been widely studied in order to handle exploding amount of data. In this paper, we study an important yet less visited distributed learning problem where features are inherently distributed or vertically partitioned among multiple parties, and sharing of raw data or model parameters among parties is prohibited due to privacy concerns. We propose an ADMM sharing framework to approach risk minimization over distributed features, where each party only needs to share a single value for each sample in the training process, thus minimizing the data leakage risk. We establish convergence and iteration complexity results for the proposed parallel ADMM algorithm under non-convex loss. We further introduce a novel differentially private ADMM sharing algorithm and bound the privacy guarantee with carefully designed noise perturbation. The experiments based on a prototype system shows that the proposed ADMM algorithms converge efficiently in a robust fashion, demonstrating advantage over gradient based methods especially for data set with high dimensional feature spaces.

show abstract

Privacy Preserving Federated Big Data Analysis

Cited by 19 publications

References 52 publications

Deep representation learning of patient data from Electronic Health Records (EHR): A systematic review

Deep representation learning of patient data from Electronic Health Records (EHR): A systematic review

Pocket Diagnosis: Secure Federated Learning against Poisoning Attack in the Cloud

Learning Privately over Distributed Features: An ADMM Sharing Approach

Contact Info

Product

Resources

About