BiSample: Bidirectional Sampling for Handling Missing Data with Local Differential Privacy
This work addresses data quality issues in privacy-preserving data collection for users with diverse privacy preferences, representing an incremental improvement in LDP methods.
The paper tackles the problem of data perturbation under local differential privacy when users have varying privacy preferences leading to missing data, proposing a bidirectional sampling technique combined with privacy preferences to handle missing data perturbation, with theoretical analysis and experiments confirming its effectiveness.
Local differential privacy (LDP) has received much interest recently. In existing protocols with LDP guarantees, a user encodes and perturbs his data locally before sharing it to the aggregator. In common practice, however, users would prefer not to answer all the questions due to different privacy-preserving preferences for different questions, which leads to data missing or the loss of data quality. In this paper, we demonstrate a new approach for addressing the challenges of data perturbation with consideration of users' privacy preferences. Specifically, we first propose BiSample: a bidirectional sampling technique value perturbation in the framework of LDP. Then we combine the BiSample mechanism with users' privacy preferences for missing data perturbation. Theoretical analysis and experiments on a set of datasets confirm the effectiveness of the proposed mechanisms.