# Backdoor Threats from Compromised Foundation Models to Federated Learning

arXiv: https://arxiv.org/abs/2311.00144 · HTML: https://mlsanity.com/paper/2311.00144/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Oct 2023.

## Built on by (most cited first, 8 of 8)

- [Chain-of-Scrutiny: Detecting Backdoor Attacks for Large Language Models](https://mlsanity.com/paper/2406.05948/) (2024)
- [Grounding Foundation Models through Federated Transfer Learning: A General Framework](https://mlsanity.com/paper/2311.17431/) (2023)
- [Synergizing Foundation Models and Federated Learning: A Survey](https://mlsanity.com/paper/2406.12844/) (2024)
- [AugFL: Augmenting Federated Learning with Pretrained Models](https://mlsanity.com/paper/2503.02154/) (2025)
- [PEFT-as-an-Attack! Jailbreaking Language Models during Federated Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2411.19335/) (2024)
- [Foundation Models in Federated Learning: Assessing Backdoor Vulnerabilities](https://mlsanity.com/paper/2401.10375/) (2024)
- [Securing Federated Learning against Backdoor Threats with Foundation Model Integration](https://mlsanity.com/paper/2410.17573/) (2024)
- [Zero-Trust Foundation Models: A New Paradigm for Secure and Collaborative Artificial Intelligence for Internet of Things](https://mlsanity.com/paper/2505.23792/) (2025)

## Abstract (arXiv)

Federated learning (FL) represents a novel paradigm to machine learning, addressing critical issues related to data privacy and security, yet suffering from data insufficiency and imbalance. The emergence of foundation models (FMs) provides a promising solution to the problems with FL. For instance, FMs could serve as teacher models or good starting points for FL. However, the integration of FM in FL presents a new challenge, exposing the FL systems to potential threats. This paper investigates the robustness of FL incorporating FMs by assessing their susceptibility to backdoor attacks. Contrary to classic backdoor attacks against FL, the proposed attack (1) does not require the attacker fully involved in the FL process; (2) poses a significant risk in practical FL scenarios; (3) is able to evade existing robust FL frameworks/ FL backdoor defenses; (4) underscores the researches on the robustness of FL systems integrated with FMs. The effectiveness of the proposed attack is demonstrated by extensive experiments with various well-known models and benchmark datasets encompassing both text and image classification domains.