Published June 24, 2022 | Version v1
Conference paper Open

FLVoogd: Robust And Privacy Preserving Federated Learning

  • 1. Delft University of Technology
  • 2. University of Greenwich

Description

In this work, we propose FLVoogd, an updated federated learning method in which servers and clients collaboratively eliminate Byzantine attacks while preserving privacy. In particular, servers use automatic Density-based Spatial Clustering of Applications with Noise (DBSCAN) combined with S2PC to cluster the benign majority without acquiring sensitive personal information. Meanwhile, clients build dual models and perform test-based distance controlling to adjust their local models toward the global one to achieve personalizing. Our framework is automatic and adaptive that servers/clients don't need to tune the parameters during the training. In addition, our framework leverages Secure Multi-party Computation (SMPC) operations, including multiplications, additions, and comparison, where costly operations, like division and square root, are not required. Evaluations are carried out on some conventional datasets from the image classification field. The result shows that FLVoogd can effectively reject malicious uploads in most scenarios; meanwhile, it avoids data leakage from the server-side.

Files

2207.00428v1.pdf

Files (1.1 MB)

Name Size Download all
md5:60050d8f929ca73e118523fdffa81510
1.1 MB Preview Download

Additional details

Funding

European Commission
ASSURED - Future Proofing of ICT Trust Chains: Sustainable Operational Assurance and Verification Remote Guards for Systems-of-Systems Security and Privacy 952697