Efficient and Differentially Private Federated LLM Fine-Tuning on Heterogeneous Clients
Open Access
- 8 August 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 5939-5950
Abstract
No abstract availableThis publication has 7 references indexed in Scilit:
- LLM-Driven Synthetic Text Generation for Privacy-Preserving Federated LearningIEEE Transactions on Audio, Speech and Language Processing, 2026
- FedDAT: An Approach for Foundation Model Finetuning in Multi-Modal Heterogeneous Federated LearningProceedings of the AAAI Conference on Artificial Intelligence, 2024
- FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations2024
- Differentially Private Federated Learning With an Adaptive Noise MechanismIEEE Transactions on Information Forensics and Security, 2023
- Membership Inference Attacks From First Principles2022
- An Adaptive and Fast Convergent Approach to Differentially Private Deep Learning2020
- The Algorithmic Foundations of Differential PrivacyFoundations and Trends® in Theoretical Computer Science, 2014