A5068047117- Privacy-Preserving Technologies in Data
- Mobile Crowdsensing and Crowdsourcing
- Blockchain Technology Applications and Security
- Cryptography and Data Security
- Data Quality and Management
- Cloud Data Security Solutions
- Stochastic Gradient Optimization Techniques
- Privacy, Security, and Data Protection
Harbin Institute of Technology
2023-2025
Federated Learning (FL), allowing data owners to conduct model training without sending their raw third-party servers, can enhance privacy in Mobile Edge Computing (MEC) which brings processing closer the sources. However, heterogeneity of local and constrained resources MEC bring new challenges hindering development FL. To this end, we propose an Auction-based Cluster scheme, called ACFL, comprising a clustered FL framework auction-based client selection strategy. Our first introduces...
Federated Learning empowers data owners to collectively train an artificial intelligence model without exposing data. However, the heterogeneous resources and self-interested users bring new challenges hindering development of federated learning. To this end, we propose a Multi-attribute Auction-based Grouped scheme, called MAGFL, comprising grouped learning framework multi-attribute auction-based group selection strategy. Initially, our clusters clients into groups according local...