SIAIApr 4, 2020

Privacy Shadow: Measuring Node Predictability and Privacy Over Time

arXiv:2004.02047v1
AI Analysis

This addresses privacy concerns for users in network applications, but it is incremental as it builds on existing predictive models and privacy measurement concepts.

The paper tackles the problem of user data being re-inferred from network structure after they leave an application, proposing the 'privacy shadow' to measure how long a user remains predictable over time, and demonstrates that this length can be predicted for individual users in three real-world datasets.

The structure of network data enables simple predictive models to leverage local correlations between nodes to high accuracy on tasks such as attribute and link prediction. While this is useful for building better user models, it introduces the privacy concern that a user's data may be re-inferred from the network structure, after they leave the application. We propose the privacy shadow for measuring how long a user remains predictive from an arbitrary time within the network. Furthermore, we demonstrate that the length of the privacy shadow can be predicted for individual users in three real-world datasets.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes