EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Adaptive Sensitivity-Aware Differential Privacy Accounting for Federated Smart-Meter Theft Detection

Diego Labate, Dipanwita Thakur, Giancarlo Fortino

Big Data and Cognitive Computing · 08.04.2026 · 10 (4) · 113

DOI: 10.3390/bdcc10040113 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 08.04.2026. Verfasst von Diego Labate und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 58 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: PNRR project FAIR—Future AI Research, Spoke 9-Green-aware AI, NRRP MUR program funded by the NextGenerationEU.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Smart-meter theft detection requires learning from fine-grained electricity consumption data, whose centralized processing poses significant privacy risks. Federated learning (FL) mitigates these risks by decentralizing training, but providing rigorous user-level differential privacy (DP) under non-IID data and heterogeneous client behavior remains challenging. Existing DP-FL approaches rely on fixed global clipping bounds for client updates, which substantially overestimate sensitivity when privacy loss is composed using Rényi Differential Privacy (RDP), zero-Concentrated DP (zCDP), or Moments Accountant (MA) frameworks, leading to excessive noise and degraded utility. This work proposes an adaptive clipping-based RDP accountant that incorporates empirical, round-wise update magnitudes into privacy accounting by rescaling each round’s RDP contribution according to the observed clipping ratio. The method is optimizer-agnostic and is evaluated with FedAvg, FedProx, and SCAFFOLD on the SGCC smart-meter theft dataset under IID and Dirichlet non-IID partitions. Experimental results show consistently tighter privacy bounds and improved model utility compared to classical DP accountants, demonstrating the effectiveness of sensitivity-aware privacy accounting for practical differentially private FL.

Förderung

  • PNRR project FAIR—Future AI Research
  • Spoke 9-Green-aware AI
  • NRRP MUR program funded by the NextGenerationEU

Zitieren

APA

Labate, D., Thakur, D., & Fortino, G. (2026). Adaptive Sensitivity-Aware Differential Privacy Accounting for Federated Smart-Meter Theft Detection. Big Data and Cognitive Computing, 10(4), 113. https://doi.org/10.3390/bdcc10040113

Vancouver

Labate D, Thakur D, Fortino G. Adaptive Sensitivity-Aware Differential Privacy Accounting for Federated Smart-Meter Theft Detection. Big Data and Cognitive Computing. 2026;10(4):113. doi:10.3390/bdcc10040113

BibTeX
@article{Labate2026,
  author = {Labate, Diego and Thakur, Dipanwita and Fortino, Giancarlo},
  title = {Adaptive Sensitivity-Aware Differential Privacy Accounting for Federated Smart-Meter Theft Detection},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {113},
  doi = {10.3390/bdcc10040113}
}
Kostenlos starten →