Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914334056120320 |
|---|---|
| author | Foroughi, Mohammad Hadi Rastegar, Seyed Hamed Sabokrou, Mohammad Khonsari, Ahmad |
| author_facet | Foroughi, Mohammad Hadi Rastegar, Seyed Hamed Sabokrou, Mohammad Khonsari, Ahmad |
| contents | Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively addressing the longstanding privacy concerns inherent in centralized systems. However, the decentralized nature of FL exposes new security vulnerabilities, especially backdoor attacks that threaten model integrity. To investigate this critical concern, this paper presents the Layer Smoothing Attack (LSA), a novel backdoor attack that exploits layer-specific vulnerabilities in neural networks. First, a Layer Substitution Analysis methodology systematically identifies backdoor-critical (BC) layers that contribute most significantly to backdoor success. Subsequently, LSA strategically manipulates these BC layers to inject persistent backdoors while remaining undetected by state-of-the-art defense mechanisms. Extensive experiments across diverse model architectures and datasets demonstrate that LSA achieves a remarkably backdoor success rate of up to 97% while maintaining high model accuracy on the primary task, consistently bypassing modern FL defenses. These findings uncover fundamental vulnerabilities in current FL security frameworks, demonstrating that future defenses must incorporate layer-aware detection and mitigation strategies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_15161 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning Foroughi, Mohammad Hadi Rastegar, Seyed Hamed Sabokrou, Mohammad Khonsari, Ahmad Cryptography and Security Artificial Intelligence Machine Learning Federated learning (FL) enables distributed model training across edge devices while preserving data locality. This decentralized approach has emerged as a promising solution for collaborative learning on sensitive user data, effectively addressing the longstanding privacy concerns inherent in centralized systems. However, the decentralized nature of FL exposes new security vulnerabilities, especially backdoor attacks that threaten model integrity. To investigate this critical concern, this paper presents the Layer Smoothing Attack (LSA), a novel backdoor attack that exploits layer-specific vulnerabilities in neural networks. First, a Layer Substitution Analysis methodology systematically identifies backdoor-critical (BC) layers that contribute most significantly to backdoor success. Subsequently, LSA strategically manipulates these BC layers to inject persistent backdoors while remaining undetected by state-of-the-art defense mechanisms. Extensive experiments across diverse model architectures and datasets demonstrate that LSA achieves a remarkably backdoor success rate of up to 97% while maintaining high model accuracy on the primary task, consistently bypassing modern FL defenses. These findings uncover fundamental vulnerabilities in current FL security frameworks, demonstrating that future defenses must incorporate layer-aware detection and mitigation strategies. |
| title | Exploiting Layer-Specific Vulnerabilities to Backdoor Attack in Federated Learning |
| topic | Cryptography and Security Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2602.15161 |