FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909718013804544 |
|---|---|
| author | Yan, Xinhai Wu, Libing Zhang, Zhuangzhuang Liu, Bingyi Huo, Lijuan Wang, Jing |
| author_facet | Yan, Xinhai Wu, Libing Zhang, Zhuangzhuang Liu, Bingyi Huo, Lijuan Wang, Jing |
| contents | Federated Learning (FL) enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL have limited effectiveness due to their neglect of the model's over-reliance on backdoor triggers, particularly as the proportion of malicious clients increases. In this paper, we propose FedBAP, a novel defense framework for mitigating backdoor attacks in FL by reducing the model's reliance on backdoor triggers. Specifically, first, we propose a perturbed trigger generation mechanism that creates perturbation triggers precisely matching backdoor triggers in location and size, ensuring strong influence on model outputs. Second, we utilize these perturbation triggers to generate benign adversarial perturbations that disrupt the model's dependence on backdoor triggers while forcing it to learn more robust decision boundaries. Finally, we design an adaptive scaling mechanism to dynamically adjust perturbation intensity, effectively balancing defense strength and model performance. The experimental results demonstrate that FedBAP reduces the attack success rates by 0.22%-5.34%, 0.48%-6.34%, and 97.22%-97.6% under three types of backdoor attacks, respectively. In particular, FedBAP demonstrates outstanding performance against novel backdoor attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21177 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning Yan, Xinhai Wu, Libing Zhang, Zhuangzhuang Liu, Bingyi Huo, Lijuan Wang, Jing Cryptography and Security Machine Learning Federated Learning (FL) enables collaborative model training while preserving data privacy, but it is highly vulnerable to backdoor attacks. Most existing defense methods in FL have limited effectiveness due to their neglect of the model's over-reliance on backdoor triggers, particularly as the proportion of malicious clients increases. In this paper, we propose FedBAP, a novel defense framework for mitigating backdoor attacks in FL by reducing the model's reliance on backdoor triggers. Specifically, first, we propose a perturbed trigger generation mechanism that creates perturbation triggers precisely matching backdoor triggers in location and size, ensuring strong influence on model outputs. Second, we utilize these perturbation triggers to generate benign adversarial perturbations that disrupt the model's dependence on backdoor triggers while forcing it to learn more robust decision boundaries. Finally, we design an adaptive scaling mechanism to dynamically adjust perturbation intensity, effectively balancing defense strength and model performance. The experimental results demonstrate that FedBAP reduces the attack success rates by 0.22%-5.34%, 0.48%-6.34%, and 97.22%-97.6% under three types of backdoor attacks, respectively. In particular, FedBAP demonstrates outstanding performance against novel backdoor attacks. |
| title | FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2507.21177 |