Abstract
When collecting information, local differential privacy (LDP) relieves the concern of privacy leakage from users' perspective, as user's private information is randomized before sent to the aggregator. We study the problem of recovering the distribution over a numerical domain while satisfying LDP. While one can discretize a numerical domain and then apply the protocols developed for categorical domains, we show that taking advantage of the numerical nature of the domain results in better trade-off of privacy and utility. We introduce a new reporting mechanism, called the square wave (SW) mechanism, which exploits the numerical nature in reporting. We also develop an Expectation Maximization with Smoothing (EMS) algorithm, which is applied to aggregated histograms from the SW mechanism to estimate the original distributions. Extensive experiments demonstrate that our proposed approach, SW with EMS, consistently outperforms other methods in a variety of utility metrics.
Original language | English |
---|---|
Title of host publication | ACM SIGMOD 2020 |
Pages | 621-635 |
DOIs | |
Publication status | Published - Jun 2020 |
Externally published | Yes |
Event | ACM SIGMOD International Conference on Management of Data, SIGMOD/PODS 2020 - Hotel Double Tree by Hilton, Portland, United States Duration: 14 Jun 2020 → 19 Jun 2020 |
Conference
Conference | ACM SIGMOD International Conference on Management of Data, SIGMOD/PODS 2020 |
---|---|
Abbreviated title | SIGMOD/PODS 2020 |
Country/Territory | United States |
City | Portland |
Period | 14/06/20 → 19/06/20 |