EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DRFL: A Dual‐Encryption and Reputation Evaluation Defence Against Malicious Attacks on Federated Learning

Zheng Yuan, Youliang Tian, Zhou Zhou, Shuai Wang, Mengqian Li, Jinbo Xiong

IET Communications · 2026-01 · 20 (1)

DOI: 10.1049/cmu2.70173 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IET Communications, online erschienen am 28.05.2026. Verfasst von Zheng Yuan und 5 weiteren Autor:innen. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Program of Guizhou Province, Natural Science Foundation of Fujian Province.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) is a prominent paradigm in contemporary machine learning, renowned for its capability to aggregate efficient and accurate models without directly collecting user data. However, FL faces numerous security challenges, including potential privacy disclosure risks as well as poisoning and free‐rider attacks perpetrated by malicious users. To address these challenges, we propose a dual‐encryption and reputation evaluation defense mechanism on FL called DRFL to defend against malicious attacks. Specifically, we first design a dual‐encryption strategy to achieve secure aggregation while protecting user privacy. Subsequently, we construct a secure reputation evaluation mechanism within the ciphertext environment to evaluate users' local ciphertext gradients, thereby defending against poisoning and free‐rider attacks. Simultaneously, blockchain technology is integrated to document the entire FL process, enhancing transparency and openness in the training procedure. We further provide security analysis to justify the privacy guarantees of DRFL, and conduct extensive experiments on three real‐world datasets. Experimental results demonstrate that DRFL effectively defends against poisoning and free‐rider attacks and improves model utility by 3%–4% over Median, Trimmed‐Mean and Krum, while achieving accuracy comparable to the benign FedAvg baseline.

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Program of Guizhou Province
  • Natural Science Foundation of Fujian Province

Zitieren

APA

Yuan, Z., Tian, Y., Zhou, Z., Wang, S., Li, M., & Xiong, J. (2026). DRFL: A Dual‐Encryption and Reputation Evaluation Defence Against Malicious Attacks on Federated Learning. IET Communications, 20(1). https://doi.org/10.1049/cmu2.70173

Vancouver

Yuan Z, Tian Y, Zhou Z, Wang S, Li M, Xiong J. DRFL: A Dual‐Encryption and Reputation Evaluation Defence Against Malicious Attacks on Federated Learning. IET Communications. 2026;20(1). doi:10.1049/cmu2.70173

BibTeX
@article{Yuan2026,
  author = {Yuan, Zheng and Tian, Youliang and Zhou, Zhou and Wang, Shuai and Li, Mengqian and Xiong, Jinbo},
  title = {DRFL: A Dual‐Encryption and Reputation Evaluation Defence Against Malicious Attacks on Federated Learning},
  journal = {IET Communications},
  year = {2026},
  volume = {20},
  number = {1},
  doi = {10.1049/cmu2.70173}
}
Kostenlos starten →