Technical Privacy Metrics: a Systematic Survey
Not on the map. Why?
Abstract (arXiv)
The goal of privacy metrics is to measure the degree of privacy enjoyed by users in a system and the amount of protection offered by privacy-enhancing technologies. In this way, privacy metrics contribute to improving user privacy in the digital world. The diversity and complexity of privacy metrics in the literature makes an informed choice of metrics challenging. As a result, instead of using existing metrics, new metrics are proposed frequently, and privacy studies are often incomparable. In this survey we alleviate these problems by structuring the landscape of privacy metrics. To this end, we explain and discuss a selection of over eighty privacy metrics and introduce categorizations based on the aspect of privacy they measure, their required inputs, and the type of data that needs protection. In addition, we present a method on how to choose privacy metrics based on nine questions that help identify the right privacy metrics for a given scenario, and highlight topics where additional work on privacy metrics is needed. Our survey spans multiple privacy domains and can be understood as a general framework for privacy measurement.
Key facts. Cited by 11 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Dec 2015.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 3; 2023: 2; 2024: 4.
11 papers.
- 2022How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processingcited by 16
- 2024Data Readiness for AI: A 360-Degree Surveycited by 15
- 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Surveycited by 14
- 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challengescited by 12
- 2024Synthetic Data: Revisiting the Privacy-Utility Trade-offcited by 7
- 2021A Review on Visual Privacy Preservation Techniques for Active and Assisted Livingcited by 6
- 2023FederatedTrust: A Solution for Trustworthy Federated Learningcited by 6
- 2022Private Quantiles Estimation in the Presence of Atomscited by 5
- 2022Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Studycited by 2
- 2023Privacy Preserving Federated Learning with Convolutional Variational Bottleneckscited by 2
- 2021HydraGAN A Multi-head, Multi-objective Approach to Synthetic Data Generationcited by 0
- 2024Establishing and Evaluating Trustworthy AI: Overview and Research Challenges15 Nov 2024
- 2024Synthetic Data: Revisiting the Privacy-Utility Trade-off9 Jul 2024
- 2024Vertical Federated Learning for Effectiveness, Security, Applicability: A Survey25 May 2024
- 2024Data Readiness for AI: A 360-Degree Survey8 Apr 2024
- 2023Privacy Preserving Federated Learning with Convolutional Variational Bottlenecks8 Sep 2023
- 2023FederatedTrust: A Solution for Trustworthy Federated Learning20 Feb 2023
- 2022Combining Stochastic Defenses to Resist Gradient Inversion: An Ablation Study9 Aug 2022
- 2022How to keep text private? A systematic review of deep learning methods for privacy-preserving natural language processing20 May 2022
- 2022Private Quantiles Estimation in the Presence of Atoms15 Feb 2022
- 2021A Review on Visual Privacy Preservation Techniques for Active and Assisted Living17 Dec 2021
- 2021HydraGAN A Multi-head, Multi-objective Approach to Synthetic Data Generation13 Nov 2021