readme.md

On the Out-of-Distribution Backdoor Attack for Federated Learning

This is the official implementation for MobiHoc'25 paper "On the Out-of-Distribution Backdoor Attack for Federated Learning".

You can find the paper here.

Related Methods

If you found our methods SoDa and BNGuard are interesting, you may also refer to our other related works on robust federated learning systems:

• AlignIns (CVPR 2025, Highlight): https://github.com/JiiahaoXU/AlignIns
• MASA (WACV 2025): https://github.com/JiiahaoXU/MASA
• LASA (WACV 2025, Oral presentation): https://github.com/JiiahaoXU/LASA

All these methods are based on simple and effective ideas for protecting federated learning systems. They are easy to implement and can be directly integrated into this codebase or into existing federated learning frameworks.

Usage

If you have any issues using this repo, feel free to contact Jiahao @ jiahaox@unr.edu.

Environment

Our code does not rely on special libraries or tools, so it can be easily integrated with most environment settings.

If you want to use the same settings as us, we provide the conda environment we used in env.yaml for your convenience.

Dataset

All tested datasets are available on torchvision and will be downloaded automatically.

Example

Generally, to run a case with default settings, you can easily use the following command:

python federated.py --aggr bnguard --attack soda --data cifar10 --ood_data mnist

If you want to run a case with non-IID settings, you can easily use the following command:

python federated.py --aggr bnguard --attack soda --data cifar10 --ood_data mnist --non_iid --alpha 0.5

Here,

Argument	Type	Description	Choice
aggr	str	Defense method applied by the server	avg, mkrum, flame, rfa, foolsgold, deepsight, mmetric, rlr, signguard, bnguard
data	str	ID data for all clients	cifar10, cifar100
ood_data	str	OOD data for malicious clients	mnist, fmnist, svhn
non_iid	store_true	Enable non-IID settings or not	N/A
alpha	float	Data heterogeneous degree	from 0.1 to 1.0

For other arguments, you can check the federated.py file where the detailed explanation is presented.

Citation

We provide the following BibTeX entry for citation for your convenience.

@inproceedings{Xu_2025_MobiHoc_SoDa_BNGuard,
  title={On the Out-of-Distribution Backdoor Attack for Federated Learning},
  author={Xu, Jiahao and Zhang, Zikai and Hu, Rui},
  booktitle={Proceedings of the Twenty-sixth International Symposium on Theory, Algorithmic Foundations, and Protocol Design for Mobile Networks and Mobile Computing},
  pages={181--190},
  year={2025}
}