DP2Guard: A Lightweight and Byzantine-Robust Privacy-Preserving Federated Learning Scheme for Industrial IoT
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913096050671616 |
|---|---|
| author | Han, Baofu Li, Bing Qi, Yining Liu, Zhiquan Jurdak, Raja Huang, Kaibin Yuen, Chau |
| author_facet | Han, Baofu Li, Bing Qi, Yining Liu, Zhiquan Jurdak, Raja Huang, Kaibin Yuen, Chau |
| contents | Privacy-Preserving Federated Learning (PPFL) has emerged as a secure distributed Machine Learning (ML) paradigm that aggregates locally trained gradients without exposing raw data. To defend against model poisoning threats, several robustness-enhanced PPFL schemes have been proposed by integrating anomaly detection. Nevertheless, they still face two major challenges: (1) the reliance on heavyweight encryption techniques results in substantial communication and computation overhead; and (2) single-strategy defense mechanisms often fail to provide sufficient robustness against adaptive adversaries. To overcome these challenges, we propose DP2Guard, a lightweight PPFL framework that enhances both privacy and robustness. DP2Guard leverages a lightweight gradient masking mechanism to replace costly cryptographic operations while ensuring the privacy of local gradients. A hybrid defense strategy is proposed, which extracts gradient features using singular value decomposition and cosine similarity, and applies a clustering algorithm to effectively identify malicious gradients. Additionally, DP2Guard adopts a trust score-based adaptive aggregation scheme that adjusts client weights according to historical behavior, while blockchain records aggregated results and trust scores to ensure tamper-proof and auditable training. Extensive experiments conducted on two public datasets demonstrate that DP2Guard effectively defends against four advanced poisoning attacks while ensuring privacy with reduced communication and computation costs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_16134 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DP2Guard: A Lightweight and Byzantine-Robust Privacy-Preserving Federated Learning Scheme for Industrial IoT Han, Baofu Li, Bing Qi, Yining Liu, Zhiquan Jurdak, Raja Huang, Kaibin Yuen, Chau Cryptography and Security Distributed, Parallel, and Cluster Computing Privacy-Preserving Federated Learning (PPFL) has emerged as a secure distributed Machine Learning (ML) paradigm that aggregates locally trained gradients without exposing raw data. To defend against model poisoning threats, several robustness-enhanced PPFL schemes have been proposed by integrating anomaly detection. Nevertheless, they still face two major challenges: (1) the reliance on heavyweight encryption techniques results in substantial communication and computation overhead; and (2) single-strategy defense mechanisms often fail to provide sufficient robustness against adaptive adversaries. To overcome these challenges, we propose DP2Guard, a lightweight PPFL framework that enhances both privacy and robustness. DP2Guard leverages a lightweight gradient masking mechanism to replace costly cryptographic operations while ensuring the privacy of local gradients. A hybrid defense strategy is proposed, which extracts gradient features using singular value decomposition and cosine similarity, and applies a clustering algorithm to effectively identify malicious gradients. Additionally, DP2Guard adopts a trust score-based adaptive aggregation scheme that adjusts client weights according to historical behavior, while blockchain records aggregated results and trust scores to ensure tamper-proof and auditable training. Extensive experiments conducted on two public datasets demonstrate that DP2Guard effectively defends against four advanced poisoning attacks while ensuring privacy with reduced communication and computation costs. |
| title | DP2Guard: A Lightweight and Byzantine-Robust Privacy-Preserving Federated Learning Scheme for Industrial IoT |
| topic | Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2507.16134 |