EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adversarial Training and Differential Privacy-Style Noise Injection for Privacy-Preserving Vertical Federated Learning

Nureni Ayofe Azeez, Oluwatobi Sunday Malomo, Omotolani Mary Okerinde, Abdullateef Akorede Ademoye, Damilola Seun Aaron, Charles Van Der Vyver, Chijioke Erasmus Ogbonna

Informatics · 09.08.2026 · 13 (8) · 127

DOI: 10.3390/informatics13080127 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Informatics, online erschienen am 09.08.2026. Verfasst von Nureni Ayofe Azeez und 6 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: School of Computer Science and Information Systems, Faculty of Natural and Agricultural Sciences, Vaal Triangle Campus, North-West University.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The adoption of federated learning (FL) has been on the rise in recent years due to the decentralized approach to data handling. Vertical federated learning is a type of FL that allows different parties to train shared models on complementary feature spaces without the direct exchange of data. However, the gradients these parties exchange can inadvertently carry sensitive information. Adversaries exploit this leakage to mount label inference attacks (LIAs) and adversarial attacks. To curb this, defense mechanisms have been deployed, but most of them either trade robustness for privacy and model utility or vice versa. This study addresses this gap by introducing an improved defense mechanism that combines adversarial training (to harden the model against adversarial perturbations) and differential-privacy-style noise injection (aimed at restoring the label privacy weakened by adversarial training) to collectively enhance the robustness of the existing KDk defense mechanism with marginal model utility trade-off. Instead of relying on heavy encryption or post-processing techniques, it builds privacy directly into the learning dynamics of the model. It was evaluated using five publicly available datasets spanning three data modalities with the proposed mechanism achieving competitive near-baseline accuracy while significantly reducing label-inference success. Under FGSM-based adversarial evaluation, the robustness gap of this mechanism was found to be approximately 1% compared to the 36% robustness gap of the existing KDk mechanism. The Privacy Leakage Index (PLI) reached 81.32%, 96.08%, 82.41%, 86.68% and 73.88% for CIFAR-10, CIFAR-100, CINIC-10, Yahoo! Answers and Criteo datasets, respectively. The results suggest that robustness and privacy security objectives can coexist to secure VFL with minimal effect on model accuracy.

Förderung

  • School of Computer Science and Information Systems, Faculty of Natural and Agricultural Sciences, Vaal Triangle Campus, North-West University

Zitieren

APA

Azeez, N. A., Malomo, O. S., Okerinde, O. M., Ademoye, A. A., Aaron, D. S., Vyver, C. V. D., & Ogbonna, C. E. (2026). Adversarial Training and Differential Privacy-Style Noise Injection for Privacy-Preserving Vertical Federated Learning. Informatics, 13(8), 127. https://doi.org/10.3390/informatics13080127

Vancouver

Azeez NA, Malomo OS, Okerinde OM, Ademoye AA, Aaron DS, Vyver CVD, et al. Adversarial Training and Differential Privacy-Style Noise Injection for Privacy-Preserving Vertical Federated Learning. Informatics. 2026;13(8):127. doi:10.3390/informatics13080127

BibTeX
@article{Azeez2026,
  author = {Azeez, Nureni Ayofe and Malomo, Oluwatobi Sunday and Okerinde, Omotolani Mary and Ademoye, Abdullateef Akorede and Aaron, Damilola Seun and Vyver, Charles Van Der and Ogbonna, Chijioke Erasmus},
  title = {Adversarial Training and Differential Privacy-Style Noise Injection for Privacy-Preserving Vertical Federated Learning},
  journal = {Informatics},
  year = {2026},
  volume = {13},
  number = {8},
  pages = {127},
  doi = {10.3390/informatics13080127}
}
Kostenlos starten →