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

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

Framework mappings

Suggested from the entry's categories.

@misc{zhu2026feddetox,
  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},
  month = apr,
  eprint = {2604.06833},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2604.06833}
}