EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Can Differential Privacy Hinder Poisoning Attack Detection in Federated Learning?

Chaitanya Aggarwal, Divya G. Nair, Jafar Aco Mohammadi, Jyothisha J. Nair, Jörg Ott

Journal of Sensor and Actuator Networks · 06.08.2025 · 14 (4) · 83

DOI: 10.3390/jsan14040083 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Sensor and Actuator Networks, online erschienen am 06.08.2025. Verfasst von Chaitanya Aggarwal und 4 weiteren Autor:innen. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We consider the problem of data poisoning attack detection in a federated learning (FL) setup with differential privacy (DP). Local DP in FL ensures that privacy leakage caused by shared gradients is controlled by adding randomness to the process. We are interested in studying the effect of the Gaussian mechanism in the detection of different data poisoning attacks. As the additive noise from DP could hide poisonous data, the effectiveness of detection algorithms should be analyzed. We present two poisonous data detection algorithms and one malicious client identification algorithm. For the latter, we show that the effect of DP noise decreases as the size of the neural network increases. We further demonstrate this effect alongside the performance of these algorithms on three publicly available datasets.

Zitieren

APA

Aggarwal, C., Nair, D. G., Mohammadi, J. A., Nair, J. J., & Ott, J. (2025). Can Differential Privacy Hinder Poisoning Attack Detection in Federated Learning?. Journal of Sensor and Actuator Networks, 14(4), 83. https://doi.org/10.3390/jsan14040083

Vancouver

Aggarwal C, Nair DG, Mohammadi JA, Nair JJ, Ott J. Can Differential Privacy Hinder Poisoning Attack Detection in Federated Learning?. Journal of Sensor and Actuator Networks. 2025;14(4):83. doi:10.3390/jsan14040083

BibTeX
@article{Aggarwal2025,
  author = {Aggarwal, Chaitanya and Nair, Divya G. and Mohammadi, Jafar Aco and Nair, Jyothisha J. and Ott, Jörg},
  title = {Can Differential Privacy Hinder Poisoning Attack Detection in Federated Learning?},
  journal = {Journal of Sensor and Actuator Networks},
  year = {2025},
  volume = {14},
  number = {4},
  pages = {83},
  doi = {10.3390/jsan14040083}
}
Kostenlos starten →