FLSwitch: towards secure and fast model aggregation for federated deep learning with a learning state-aware switch

DOI10.1007/978-3-031-33488-7_18MaRDI QIDQ6535091zbMATH OpenFDO

Authors Yunlong Mao, Ziqin Dang, Tianling Zhang, Yuan Zhang, Jingyu Hua, Sheng Zhong

Publication date 9 November 2023

Full work available at URL https://doi.org/10.1007/978-3-031-33488-7_18

zbMATH Keywords

deep neural networkfederated learninghomomorphic encryptionsecure aggregation

Mathematics Subject Classification ID

Computer security (68M25) Artificial neural networks and deep learning (68T07) Cryptography (94A60)

Recommendations

• CORK: a privacy-preserving and lossless federated learning scheme for deep neural network
• SPEED: secure, private, and efficient deep learning
• Privacy-preserving federated learning on lattice quantization
• FL-MAC-RDP: federated learning over multiple access channels with Rényi differential privacy
• RTGA: robust ternary gradients aggregation for federated learning

Cites work

• An NP-Complete Number-Theoretic Problem
• Gesammelte Abhandlungen. Bd. III: Analysis, Grundlagen der Mathematik, Physik, Verschiedenes. Nebst einer Lebensgeschichte.
• Homomorphic encryption for arithmetic of approximate numbers
• Reduction of an arbitrary diophantine equation to one in 13 unknowns
• Stochastic distributed learning with gradient quantization and double-variance reduction

This page was built for publication: FLSwitch: towards secure and fast model aggregation for federated deep learning with a learning state-aware switch

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6535091)