CECMLP: new cipher-based evaluating collaborative multi-layer perceptron scheme in federated learning

DOI10.1007/978-3-030-78372-3_4zbMATH Open1489.68046OpenAlexW3167053152MaRDI QIDQ2117030FDOQ2117030

Meixia Miao, Yi Xie, Xu Ma, Yu-Qi Chen, Xiao-Yu Zhang

Publication date: 21 March 2022

Full work available at URL: https://doi.org/10.1007/978-3-030-78372-3_4

zbMATH Keywords

privacy preservationfederated learningcipher-based weighted method

Mathematics Subject Classification ID

Data encryption (aspects in computer science) (68P25) Cryptography (94A60) Computer security (68M25) Privacy of data (68P27)

Cites Work

• Gazelle
• Differential Privacy: A Survey of Results
• Public-Key Cryptosystems Based on Composite Degree Residuosity Classes
• DeepStack: Expert-level artificial intelligence in heads-up no-limit poker
• Privacy preservation for machine learning training and classification based on homomorphic encryption schemes

Cited In (1)

• Local differential privacy for federated learning

Uses Software

• ImageNet
• DeepStack
• Gazelle
• AlexNet

   Recommendations

• Federated learning in side-channel analysis 👍 👎
• Privacy-preserving federated learning on lattice quantization 👍 👎
• PFLM: privacy-preserving federated learning with membership proof 👍 👎
• FL-MAC-RDP: federated learning over multiple access channels with Rényi differential privacy 👍 👎
• X-Secure T-Private Federated Submodel Learning With Elastic Dropout Resilience 👍 👎

This page was built for publication: CECMLP: new cipher-based evaluating collaborative multi-layer perceptron scheme in federated learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2117030)