Tag: privacy
-
DP Mobility Report: A Python package for quick explorations and mobility data reports with privacy guarantees
Exploratory data analysis is an essential step in any data science project, as it allows us to understand the data and identify patterns, trends, and anomalies. However, exploratory analyses can often be time-consuming and repetitive. While there are existing packages for performing exploratory analyses on tabular data, e.g., ydata_profiling (formerly known as pandas_profiling) for Python,…
-
You’re more unique than you think – about the difficulty of anonymizing mobility data
One of the main reasons why people can easily be re-identified in mobility data is because mobility patterns are highly unique. Consider your visited locations over the last few days, where did you go and when? E.g., you have been to your home, university, fitness studio, and your favorite supermarket. This combination of locations visited…
-
Publication: Towards mobility reports with user-level privacy
Mobility data, even aggregated statistics, can usually not be shared without privacy concerns. Within this publication, my co-authors Saskia Nuñez von Voigt, Helena Mihaljević, and Florian Tschorsch and I aim to provide a report that compiles typical analyses of urban human mobility and provides privacy guarantees so that it can be shared freely. [Download paper]…
-
How much privacy do “Privacy Zones” provide?
In this post, I gave an overview of different privacy-enhancing techniques for mobility data. This post is the first to deep-dive into single specific techniques by looking into privacy zones. Social-network sports apps like Strava are used to track and share personal sporting performances, including pictures and GPS traces. This has led to undesired events:…
-
Attack scenarios – how adversaries retrieve sensitive information
Attack scenarios are used in privacy research to describe how an adversary potentially obtains sensitive information about a person. Such a scenario entails assumptions on side information available to an adversary, which sensitive information the adversary wants to retrieve, and how they use the side information to retrieve the sensitive information. Such scenarios are used…
-
How is mobility data sensitive information?
Political opinions, religious beliefs, sexual orientation, or health issues are typical examples of obvious sensitive information in the need of data protection. While human mobility data is also personal data, it is inherently complex and thus there are different aspects that can be considered sensitive. Is only the information about a person’s home and their…
-
Privacy-preserving techniques and how they apply to mobility data
What does it actually mean to “anonymize” data? With this blog post, I want to give an overview of different established methods and how they apply to mobility data. (The survey of Fiore et al., 2020 has been a major source for this overview). First of all, it should be noted, that there is a…
-
Real-Life Privacy Breaches: Why Mobility Data needs Protection
The General Data Protection Regulation (GDPR) of 2016 was a novel and unique law to secure the privacy and security of personal data, but it was not introduced without criticism. Companies see the GDPR as an obstacle that hinders them to pursue their use cases and which poses unrealistically high demands. Privacy threats on the…
Alexandra Kapp 