Accuracy and Privacy Evaluations of Collaborative Data Analysis
Distributed data analysis without revealing the individual data has recently attracted significant attention in several applications. A collaborative data analysis through sharing dimensionality reduced representations of data has been proposed as a non-model sharing-type federated learning. This paper analyzes the accuracy and privacy evaluations of this novel framework. In the accuracy analysis, we provided sufficient conditions for the equivalence of the collaborative data analysis and the centralized analysis with dimensionality reduction. In the privacy analysis, we proved that collaborative users' private datasets are protected with a double privacy layer against insider and external attacking scenarios.
Code (0)
등록된 구현이 없습니다.
Tasks
Dimensionality ReductionFederated LearningSimilar Papers 제목 키워드 기반
Efficient Privacy Preserving Logistic Regression for Horizontally Distributed Data
Internet of Things devices are expanding rapidly and generating huge amount of data. There is an increasing need to explore data collected from these devices. Collaborative learning provides a strategic solution for the …
Privacy PreservingregressionPrivacy-Preserving Multi-Center Differential Protein Abundance Analysis with FedProt
Quantitative mass spectrometry has revolutionized proteomics by enabling simultaneous quantification of thousands of proteins. Pooling patient-derived data from multiple institutions enhances statistical power but raises…
Federated LearningPrivacy PreservingRoulette: A Semantic Privacy-Preserving Device-Edge Collaborative Inference Framework for Deep Learning Classification Tasks
Deep learning classifiers are crucial in the age of artificial intelligence. The device-edge-based collaborative inference has been widely adopted as an efficient framework for promoting its applications in IoT and 5G/6G…
Collaborative InferencePrivacy PreservingTransfer LearningPrivacy Assessment of Federated Learning using Private Personalized Layers
Federated Learning (FL) is a collaborative scheme to train a learning model across multiple participants without sharing data. While FL is a clear step forward towards enforcing users' privacy, different inference attack…
AttributeFederated LearningPencil: Private and Extensible Collaborative Learning without the Non-Colluding Assumption
The escalating focus on data privacy poses significant challenges for collaborative neural network training, where data ownership and model training/deployment responsibilities reside with distinct entities. Our communit…
Federated LearningPrivacy Preserving