paperAugust 2026UnreviewedOpen access

Efficient and Differentially Private Federated LLM Fine-Tuning on Heterogeneous Clients

Nan Yan, Yu-Qing Li, Xiong Wang, Jing Chen, Wei Wang, Kun He, Ruiying Du, Shuhua Li

Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2

Abstract

Federated low-rank adaptation (FedLoRA) allows multiple clients to collaboratively fine-tune large language models (LLMs) on downstream tasks without exposing their private data. To mitigate privacy leakage during aggregation, differential privacy (DP) is widely used to clip and perturb local model updates with noise, yet it can compromise model accuracy due to the inherent privacy-utility trade-off. The performance degradation becomes worse under the FedLoRA setting with the amplified DP noise

Framework mappings

OWASP Top 10 for LLM Applications

LLM02Sensitive Information Disclosure

MITRE ATLAS

AML.T0024.000Infer Training Data Membership

Suggested from the entry's categories.

Cite

@inproceedings{yan2026efficient,
  title = {{Efficient and Differentially Private Federated LLM Fine-Tuning on Heterogeneous Clients}},
  author = {Nan Yan and Yu-Qing Li and Xiong Wang and Jing Chen and Wei Wang and Kun He and Ruiying Du and Shuhua Li},
  year = {2026},
  month = aug,
  booktitle = {Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2},
  doi = {10.1145/3770855.3817914},
  url = {https://www.semanticscholar.org/paper/e07ea3aaf72821d49acb1c5174f80cabeb43b1c1}
}