EUVIMEDEUVIMED entdecken
Crossref

FRISC: Mitigating Privacy Leakage in Federated Learning through Frequency‐domain Feature Screening

Shangbo Wu, Thar Baker, Yajie Wang, Yu‐an Tan, Yuanzhang Li, Mengxia Ren

Concurrency and Computation: Practice and Experience · 2026-03 · 38 (6)

DOI: 10.1002/cpe.70640 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 10.03.2026. Verfasst von Shangbo Wu und 5 weiteren Autor:innen. Die Arbeit nennt 61 Literaturangaben. Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) is an emerging paradigm for privacy‐preserving collaborative machine learning that coordinates the training of a global model by sharing model updates (i.e., gradients) instead of sensitive raw information. Yet, sensitive information can be reconstructed from exposed gradients through inversion attacks, challenging the privacy promises of federated learning. Current defenses for federated learning either introduce unnecessary overhead to the training framework to adapt complex cryptographic algorithms or sacrifice model performance through noise injection. In this paper, we approach this challenge from a frequency‐domain perspective. We observe that models' overfitting to sample‐specific, high‐frequency data components ultimately induces privacy vulnerabilities. To this end, we propose FRISC , a lightweight privacy protection scheme for federated learning. FRISC employs a frequency‐aware, feature‐wise regularization during training, to precisely screen out exploitable information within the training data. This design allows FRISC to be integrated seamlessly into existing federated learning systems with minimal computational cost. We validate the efficacy of our approach through a comprehensive theoretical analysis and extensive empirical evaluations on multiple datasets, including MNIST, Fashion‐MNIST, and CIFAR‐10. The results demonstrably prove that FRISC significantly improves privacy protection while maintaining model performance, offering a promising solution for improving privacy in federated learning.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wu, S., Baker, T., Wang, Y., Tan, Y., Li, Y., & Ren, M. (2026). FRISC: Mitigating Privacy Leakage in Federated Learning through Frequency‐domain Feature Screening. Concurrency and Computation: Practice and Experience, 38(6). https://doi.org/10.1002/cpe.70640

Vancouver

Wu S, Baker T, Wang Y, Tan Y, Li Y, Ren M. FRISC: Mitigating Privacy Leakage in Federated Learning through Frequency‐domain Feature Screening. Concurrency and Computation: Practice and Experience. 2026;38(6). doi:10.1002/cpe.70640

BibTeX
@article{Wu2026,
  author = {Wu, Shangbo and Baker, Thar and Wang, Yajie and Tan, Yu‐an and Li, Yuanzhang and Ren, Mengxia},
  title = {FRISC: Mitigating Privacy Leakage in Federated Learning through Frequency‐domain Feature Screening},
  journal = {Concurrency and Computation: Practice and Experience},
  year = {2026},
  volume = {38},
  number = {6},
  doi = {10.1002/cpe.70640}
}
Kostenlos starten →