Local Graph-homomorphic Processing for Privatized Distributed Systems
We study the generation of dependent random numbers in a distributed fashion in order to enable privatized distributed learning by networked agents. We propose a method that we refer to as local graph-homomorphic processing; it relies on the construction of particular noises over the edges to ensure a certain level of differential privacy. We show that the added noise does not affect the performance of the learned model. This is a significant improvement to previous works on differential privacy for distributed algorithms, where the noise was added in a less structured manner without respecting the graph topology and has often led to performance deterioration. We illustrate the theoretical results by considering a linear regression problem over a network of agents.
Code (0)
등록된 구현이 없습니다.
Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Privatized Graph Federated Learning
Federated learning is a semi-distributed algorithm, where a server communicates with multiple dispersed clients to learn a global model. The federated architecture is not robust and is sensitive to communication and comp…
Federated LearningAdvancing Federated Learning in 6G: A Trusted Architecture with Graph-based Analysis
Integrating native AI support into the network architecture is an essential objective of 6G. Federated Learning (FL) emerges as a potential paradigm, facilitating decentralized AI model training across a diverse range of…
Federated LearningGraph Neural NetworkManagementMembership-Mappings for Practical Secure Distributed Deep Learning
This study leverages the data representation capability of fuzzy based membership-mappings for practical secure distributed deep learning using fully homomorphic encryption. The impracticality issue of secure machine (de…
Deep LearningMental Stress DetectionHomomorphic Encryption-Enabled Distance-Based Distributed Formation Control with Distance Mismatch Estimators
This paper considers the use of fully homomorphic encryption for the realisation of distributed formation control of multi-agent systems via edge computer. In our proposed framework, the distributed control computation i…
QuantizationPrivacy-Preserving Visual Learning Using Doubly Permuted Homomorphic Encryption
We propose a privacy-preserving framework for learning visual classifiers by leveraging distributed private image data. This framework is designed to aggregate multiple classifiers updated locally using private data and …
Privacy Preserving