Do auto-regressive models protect privacy? Inferring fine-grained energy consumption from aggregated model parameters

Research output: Contribution to journalArticlepeer-review

Abstract

We investigate the extent to which statistical predictive models leak information about their training data. More specifically, based on the use case of household (electrical)energy consumption, we evaluate whether white-box access to auto-regressive (AR) models trained on such data together with background information, such as household energy data aggregates (e.g., monthly billing information) and publicly-available weather data, can lead to inferring fine-grained energy data of any particular household. We construct two adversarial models aiming to infer fine-grained energy consumption patterns. Both threat models use monthly billing information of target households. The second adversary has access to the AR model for a cluster of households containing the target household. Using two real-world energy datasets, we demonstrate that this adversary can apply maximum a posteriori estimation to reconstruct daily consumption of target households with significantly lower error than the first adversary, which serves as a baseline. Such fine-grained data can essentially expose private information, such as occupancy levels. Finally, we use differential privacy to alleviate the privacy concerns of the adversary in dis-aggregating energy data. Our evaluations show that differentially private model parameters offer strong privacy protection against the adversary with moderate utility, captured in terms of model fitness to the cluster.
Original languageEnglish
Number of pages12
JournalIEEE Transactions on Services Computing
DOIs
Publication statusE-pub ahead of print - 27 Jul 2021

Keywords

  • aggregate statistics, white-box attacks, inference attacks, auto-regressive models, differential privacy, energy data privacy.
  • auto-regressive models
  • Energy consumption
  • inference attacks
  • Biological system modeling
  • Predictive models
  • energy data privacy
  • white-box attacks
  • Analytical models
  • Privacy
  • Aggregates
  • aggregate statistics
  • Data models
  • differential privacy

Fingerprint

Dive into the research topics of 'Do auto-regressive models protect privacy? Inferring fine-grained energy consumption from aggregated model parameters'. Together they form a unique fingerprint.

Cite this