EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Communication-Efficient and Privacy-Preserving Verifiable Aggregation for Federated Learning

Kaixin Peng, Xiaoying Shen, Le Gao iD, Baocang Wang, Yichao Lu

Entropy · 27.07.2023 · 25 (8) · 1125

DOI: 10.3390/e25081125 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Entropy, online erschienen am 27.07.2023. Verfasst von Kaixin Peng und 4 weiteren Autor:innen. Beteiligte Einrichtung: The Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Open Research Fund of Key Laboratory of Cryptography of Zhejiang Province, Fundamental Research Funds for the Central Universities.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning is a distributed machine learning framework, which allows users to save data locally for training without sharing data. Users send the trained local model to the server for aggregation. However, untrusted servers may infer users’ private information from the provided data and mistakenly execute aggregation protocols to forge aggregation results. In order to ensure the reliability of the federated learning scheme, we must protect the privacy of users’ information and ensure the integrity of the aggregation results. This paper proposes an effective secure aggregation verifiable federated learning scheme, which has both high communication efficiency and privacy protection function. The scheme encrypts the gradients with a single mask technology to securely aggregate gradients, thus ensuring that malicious servers cannot deduce users’ private information from the provided data. Then the masked gradients are hashed to verify the aggregation results. The experimental results show that our protocol is more suited for bandwidth-constraint and offline-users scenarios.

Schlagwörter

Stichwörter der Autor:innen

federated learninghomomorphic hash functionprivacy protectionverifiability

Autor:innen und Institutionen

  • The Faculty of Intelligent Manufacturing, Wuyi University, Jiangmen 529020, China.
  • The State Key Laboratory of Integrated Service Networks, Xidian University, Xi'an 710071, China.
  • The Key Laboratory of Cryptography of Zhejiang Province, Hangzhou Normal University, Hangzhou 311121, China.

ORCID-Profile: Le Gao

Förderung

  • National Natural Science Foundation of China
  • Open Research Fund of Key Laboratory of Cryptography of Zhejiang Province
  • Fundamental Research Funds for the Central Universities
  • the Teaching Reform Project of Guangdong Province
  • Information Security Teaching Reform Project of Wuyi University
  • National Key R&D Program of China
  • Teaching Reform Project of Guangdong Province

Zitieren

APA

Peng, K., Shen, X., Gao, L., Wang, B., & Lu, Y. (2023). Communication-Efficient and Privacy-Preserving Verifiable Aggregation for Federated Learning. Entropy, 25(8), 1125. https://doi.org/10.3390/e25081125

Vancouver

Peng K, Shen X, Gao L, Wang B, Lu Y. Communication-Efficient and Privacy-Preserving Verifiable Aggregation for Federated Learning. Entropy. 2023;25(8):1125. doi:10.3390/e25081125

BibTeX
@article{Peng2023,
  author = {Peng, Kaixin and Shen, Xiaoying and Gao, Le and Wang, Baocang and Lu, Yichao},
  title = {Communication-Efficient and Privacy-Preserving Verifiable Aggregation for Federated Learning},
  journal = {Entropy},
  year = {2023},
  volume = {25},
  number = {8},
  pages = {1125},
  doi = {10.3390/e25081125}
}
Kostenlos starten →