Locally Differentially Private Truth Discovery over Data Streams

Pengfei Zhang, Zhikun Zhang, Yang Cao, Shaowei Wang, Xiang Cheng, Zhang JiIEEE Trans. Mobile Computing 2025 · DOI

Abstract

Data inconsistency often arises from multiple observed sensory data due to varying participant reliability for crowdsensing systems. Truth discovery, which includes <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Weight Estimation</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Truth Aggregation</i>, for estimating participant reliability weights and aggregating uploaded values from inconsistent observations respectively, has emerged as an effective solution to address this issue. While local differential privacy (LDP) provides strong privacy guarantees by allowing participants to perturb their data locally before submission, existing LDP-based studies are either designed for static scenarios or compromise on privacy and accuracy trade-off for data streams, satisfying only weaker versions of LDP or mere differential privacy. To effectively and efficiently obtain truths over streams under rigorous LDP, we propose <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">NANO</i> which is locally differe<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i>tially priv<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">A</i>te truth discovery via updati<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">N</i>g time stamp determinati<italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">O</i>n. The main idea lies in its integration of Laplacian noise for privacy protection and inherent Gaussian noise representing natural data variability for effective weight and truth estimations, coupled with the adaptive determination of updating time stamps. In <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">NANO</i>, to obtain the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Weight Estimation</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Truth Aggregation</i> under LDP, we design a mixed noise-aware truth discovery method <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">MixTD</i> by modeling the mixed noise. To capture the dynamic nature of weight and truth evolutions, we develop a changing-aware updating time stamp determination method <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">CUD</i> to selectively re-conduct truth discovery at specific time stamps. We also introduce a dynamic privacy budget management strategy, which accumulates unused budgets from skipped updates for critical timestamps. In this way, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Weight Estimation</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Truth Aggregation</i> are limited to critical time stamps, which significantly reduces the privacy budget segmentation and computational costs. We demonstrate that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">NANO</i> provides rigorous LDP guarantees while achieving bounded utility and computational complexity. Extensive experimental results over four real-world datasets and three synthetic datasets showcase that <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">NANO</i> outperforms the state-of-the-arts by at least 20% improvement with negligible extra efficiency loss.
BibTeX
@article{zhang2025locally,
  author = {Pengfei Zhang and Zhikun Zhang and Yang Cao and Shaowei Wang and Xiang Cheng and Zhang Ji},
  title = {{Locally Differentially Private Truth Discovery over Data Streams}},
  journal = {IEEE Transactions on Mobile Computing},
  year = {2025},
  doi = {10.1109/tmc.2025.3642569},
}

Loading related content...

Figure