Age-Dependent Differential Privacy
Meng Zhang, Ermin Wei, Randall Berry, Jianwei Huang

TL;DR
This paper introduces age-dependent differential privacy, a new framework that considers data staleness and temporal correlations, enabling improved privacy guarantees with bounded accuracy loss compared to traditional noise-based methods.
Contribution
It establishes a novel age-dependent DP framework, linking it to classical DP, and demonstrates how aging strategies can enhance privacy while maintaining utility.
Findings
Aging can protect privacy similarly to noise injection.
Sequential composition of age-dependent DP is characterized.
Combining aging with noise injection bounds accuracy loss.
Abstract
The proliferation of real-time applications has motivated extensive research on analyzing and optimizing data freshness in the context of \textit{age of information}. However, classical frameworks of privacy (e.g., differential privacy (DP)) have overlooked the impact of data freshness on privacy guarantees, which may lead to unnecessary accuracy loss when trying to achieve meaningful privacy guarantees in time-varying databases. In this work, we introduce \textit{age-dependent DP}, taking into account the underlying stochastic nature of a time-varying database. In this new framework, we establish a connection between classical DP and age-dependent DP, based on which we characterize the impact of data staleness and temporal correlation on privacy guarantees. Our characterization demonstrates that \textit{aging}, i.e., using stale data inputs and/or postponing the release of outputs, can…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAge of Information Optimization · Privacy-Preserving Technologies in Data
