# A Vision-Language Pre-training Model-Guided Approach for Mitigating Backdoor Attacks in Federated Learning

arXiv: https://arxiv.org/abs/2508.10315 · HTML: https://mlsanity.com/paper/2508.10315/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 14 Aug 2025.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Model-Contrastive Federated Learning](https://mlsanity.com/paper/2103.16257/) (2021)
- [How To Backdoor Federated Learning](https://mlsanity.com/paper/1807.00459/) (2018)
- [Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates](https://mlsanity.com/paper/1803.01498/) (2018)
- [FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping](https://mlsanity.com/paper/2012.13995/) (2020)
- [LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement](https://mlsanity.com/paper/2403.15042/) (2024)
- [FreqFed: A Frequency Analysis-Based Approach for Mitigating Poisoning Attacks in Federated Learning](https://mlsanity.com/paper/2312.04432/) (2023)
- [Backdoor Federated Learning by Poisoning Backdoor-Critical Layers](https://mlsanity.com/paper/2308.04466/) (2023)
- [Towards Attack-tolerant Federated Learning via Critical Parameter Analysis](https://mlsanity.com/paper/2308.09318/) (2023)
- [Robust Asymmetric Heterogeneous Federated Learning with Corrupted Clients](https://mlsanity.com/paper/2503.09206/) (2025)
- [Byzantine-Robust Federated Learning via Credibility Assessment on Non-IID Data](https://mlsanity.com/paper/2109.02396/) (2021)

## Built on by (most cited first, 1 of 1)

- [From Internal Diagnosis to External Auditing: A VLM-Driven Paradigm for Data-Free Online Backdoor Defense](https://mlsanity.com/paper/2601.19448/) (2026)

## Abstract (arXiv)

Defending backdoor attacks in Federated Learning (FL) under heterogeneous client data distributions encounters limitations balancing effectiveness and privacy-preserving, while most existing methods highly rely on the assumption of homogeneous client data distributions or the availability of a clean serve dataset. In this paper, we propose an FL backdoor defense framework, named CLIP-Fed, that utilizes the zero-shot learning capabilities of vision-language pre-training models. Our scheme overcomes the limitations of Non-IID imposed on defense effectiveness by integrating pre-aggregation and post-aggregation defense strategies. CLIP-Fed aligns the knowledge of the global model and CLIP on the augmented dataset using prototype contrastive loss and Kullback-Leibler divergence, so that class prototype deviations caused by backdoor samples are ensured and the correlation between trigger patterns and target labels is eliminated. In order to balance privacy-preserving and coverage enhancement of the dataset against diverse triggers, we further construct and augment the server dataset via using the multimodal large language model and frequency analysis without any client samples. Extensive experiments on representative datasets evidence the effectiveness of CLIP-Fed. Comparing to other existing methods, CLIP-Fed achieves an average reduction in Attack Success Rate, em i.e., 2.03% on CIFAR-10 and 1.35% on CIFAR-10-LT, while improving average Main Task Accuracy by 7.92% and 0.48%, respectively. Our codes are available at https://anonymous.4open.science/r/CLIP-Fed.