FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization

Shunan Zhu, Jiawei Chen, Yonghao Yu, Hideya Ochiai

Abstract

As high quality public data becomes scarce, Federated Learning (FL) provides a vital pathway to leverage valuable private user data while preserving privacy. However, real-world client data often contains toxic or unsafe information. This leads to a critical issue we define as unintended data poisoning, which can severely damage the safety alignment of global models during federated alignment. To address this, we propose FedDetox, a robust framework tailored for Small Language Models (SLMs) on r

Categories

Cite This Resource

@article{llmsec202600151,
  title = {FedDetox: Robust Federated SLM Alignment via On-Device Data Sanitization},
  author = {Shunan Zhu and Jiawei Chen and Yonghao Yu and Hideya Ochiai},
  year = {2026},
  url = {https://arxiv.org/abs/2604.06833},
}