2022 Fiscal Year Annual Research Report
A Principled Framework for Explaining, Choosing and Negotiating Privacy Parameters of Differential Privacy
| Project/Area Number |
22H03595
|
|---|
| Allocation Type | Single-year Grants |
|---|
| Research Institution | Hokkaido University |
|---|
Principal Investigator |
曹 洋 北海道大学, 情報科学研究院, 准教授 (60836344)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
吉川 正俊 京都大学, 情報学研究科, 教授 (30182736)
|
|---|
| Project Period (FY) |
2022-04-01 – 2025-03-31
|
| Keywords | Differential Privacy |
|---|
| Outline of Annual Research Achievements |
We conduct research on privacy budgeting in the context of differentially private data analysis. Our focus areas include differentially private trajectory event stream publishing, spatiotemporal data releasing, differentially private streaming data release, and locally private streaming data release with shuffling and subsampling.
Preliminary experimental results indicate that the main factor affecting the trade-off between privacy risk and utility metrics is the specific scenario in which the analysis is conducted. A key takeaway from our research is that achieving an optimal privacy budget is not universally possible without considering the specific differentially private algorithms and data distributions involved.
|
| Current Status of Research Progress |
Current Status of Research Progress
2: Research has progressed on the whole more than it was originally planned.
Reason
Our findings have been published in reputable venues such as IEEE MDM, IEEE ICDE workshops, IEEE CSF, and the IEICE journal.
|
| Strategy for Future Research Activity |
We will now move on to our third topic of privacy budgeting: how to reconcile conflicts when different stakeholders have varying requirements for privacy parameters. Our basic idea is to use data market mechanisms.
|
Research Products
(14 results)
