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.