June 2026Unreviewed
When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems
Chenqing Zhu, Yanbo Dai, Yulong Tian, Qingming Li, Songze Li
Abstract
Large Language Model (LLM)-based question-answering (QA) systems are increasingly deployed in sensitive domains such as healthcare, mental health counseling, and legal consultation. Federated learning (FL) enables collaborative training without sharing raw client data, for which locally trained models are aggregated at a central server (i.e., a cloud service provider) to obtain a global model. In this paper, we explore the potential vulnerability where a malicious aggregator, who may collude wit
Categories
Framework mappings
OWASP Top 10 for LLM Applications
- LLM04Data and Model Poisoning
MITRE ATLAS
- AML.T0020Poison Training Data
Suggested from the entry's categories.
Cite
@misc{zhu2026whena,
title = {{When the Aggregator Cheats: Data-Free Backdoors in Federated LLM-based QA Systems}},
author = {Chenqing Zhu and Yanbo Dai and Yulong Tian and Qingming Li and Songze Li},
year = {2026},
month = jun,
eprint = {2606.27511},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.27511}
}