Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy

2025/10/14 by Rouzbeh Behnia, Jeremiah Birrell, Behnia, Rouzbeh +9 · 2 citations
Computer Science · #Cryptography and Data Security #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Privacy-Preserving Technologies in Data #Stochastic Gradient Optimization Techniques

paper · pdf · doi:10.48550/arxiv.2510.12908

openalex publication_date 2025/10/14 · openalex created_date 2025/10/17 · openalex updated_date 2026/07/28

Abstract

Federated learning (FL) enables organizations to collaboratively train models without sharing their datasets. Despite this advantage, recent studies show that both client updates and the global model can leak private information, limiting adoption in sensitive domains such as healthcare. Local differential privacy (LDP) offers strong protection by letting each participant privatize updates before transmission. However, existing LDP methods were designed for centralized training and introduce challenges in FL, including high resource demands that can cause client dropouts and the lack of reliable privacy guarantees under asynchronous participation. These issues undermine model generalizability, fairness, and compliance with regulations such as HIPAA and GDPR. To address them, we propose L-RDP, a DP method designed for LDP that ensures constant, lower memory usage to reduce dropouts and provides rigorous per-client privacy guarantees by accounting for intermittent participation.

Citations

• Private Federated Learning In Real World Application -- A Case Study
• Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey
• Differentially Private Stochastic Gradient Descent with Fixed-Size Minibatches: Tighter RDP Guarantees with or without Replacement
• Exploring adversarial attacks in federated learning for medical imaging
• Extracting Training Data from Diffusion Models
• Federated and Privacy-Preserving Learning of Accounting Data in Financial Statement Audits
• Numerical Composition of Differential Privacy
• Extracting Training Data from Large Language Models
• Flower: A Friendly Federated Learning Research Framework
• Advances and Open Problems in Federated Learning
• Advances and Open Problems in Federated Learning
• Applied Federated Learning: Improving Google Keyboard Query Suggestions
• Differentially Private Federated Learning: A Client Level Perspective

Cited by

• FedVideoMAE: Efficient Privacy-Preserving Federated Video Moderation
• Differential Privacy as a Perk: Federated Learning over Multiple-Access Fading Channels with a Multi-Antenna Base Station
• Strategic Incentivization for Locally Differentially Private Federated Learning

Related

• Local Differential Privacy for Federated Learning
• LDP-Fed: Federated Learning with Local Differential Privacy
• LDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
• Optimal Strategies for Federated Learning Maintaining Client Privacy
• FedSDP: Explainable Differential Privacy in Federated Learning via Shapley Values