Metraipolis › archive › dc_137c8ef7f196

Learning Defensive Policies against Diverse Inference Attacks for Smart Meter Privacy — arXiv:2609.25484

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25484
License (as archived)
CC0-1.0
Archived
2026-10-08T15:07:27.409Z
SHA-256 of the archived text
2c739ce56a57c20ad6e6b71acaa7f4d7ddda3d15dede03a14600be19ef65e44d
Stable URL of this page
https://metraipolis.com/documento/dc_137c8ef7f196

How to cite

Learning Defensive Policies against Diverse Inference Attacks for Smart Meter Privacy — arXiv:2609.25484 — arXiv (en), https://arxiv.org/abs/2609.25484 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_137c8ef7f196 (Metraipolis archive dc_137c8ef7f196, sha256 2c739ce56a57c20ad6e6b71acaa7f4d7ddda3d15dede03a14600be19ef65e44d)
BibTeX
@misc{dc137c8ef7f196,
  title = {Learning Defensive Policies against Diverse Inference Attacks for Smart Meter Privacy — arXiv:2609.25484},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25484},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_137c8ef7f196; sha256 2c739ce56a57c20ad6e6b71acaa7f4d7ddda3d15dede03a14600be19ef65e44d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25484. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Smart meter (SM) data provides fine-grained visibility into household energy consumption, but also exposes users to privacy risks. Inference attacks, known as non-intrusive load monitoring (NILM), can perform appliance-level inference from aggregate signals and recover sensitive behavioral patterns. In practice, attacker models are unknown and heterogeneous, making robust defense challenging. We formulate SM privacy protection as a black-box inference defense problem, aiming to reduce the recoverability of appliance-level information while generalizing across diverse and unseen attackers. We propose a proxy-guided hierarchical reinforcement learning framework that learns battery-based load-shaping policies to inject realistic but misleading appliance-level signatures into the aggregate signal, thereby disrupting the structured patterns exploited by NILM. A self-supervised aggregate-structure privacy probe provides a reconstruction-error-based surrogate reward for disrupting recoverable load structure, while a signature library makes the perturbations appliance-relevant and physically realizable through battery control. We provide theoretical rationale showing that proxy-guided optimization improves inference robustness under attacker diversity. Experiments on real-world datasets UK-DALE and REDD demonstrate strong cross-model and cross-appliance generalization. Across six unseen NILM attackers, covering four appliances on UK-DALE and five on REDD, our proposed defense increases average appliance-level RMSE by 107% and 166%, respectively, while reducing F1 score by 79% and 80%.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.25484 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T14:37:29.397Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).