Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918160806969344 |
|---|---|
| author | Behnia, Rouzbeh Birrell, Jeremiah Riasi, Arman Ebrahimi, Reza Dutta, Kaushik Hoang, Thang |
| author_facet | Behnia, Rouzbeh Birrell, Jeremiah Riasi, Arman Ebrahimi, Reza Dutta, Kaushik Hoang, Thang |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_12908 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy Behnia, Rouzbeh Birrell, Jeremiah Riasi, Arman Ebrahimi, Reza Dutta, Kaushik Hoang, Thang Cryptography and Security 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. |
| title | Local Differential Privacy for Federated Learning with Fixed Memory Usage and Per-Client Privacy |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2510.12908 |