Zoom Meeting: https://umass-amherst.zoom.us/j/6346823846
Abstract:
As the collection of personal data has increased, many institutions face an urgent need for reliable protection of sensitive data. Among the emerging privacy protection mechanisms, differential privacy offers a persuasive and provable assurance to individuals and has become the dominant model in the research community. However, despite growing adoption, the complexity of designing differentially private algorithms and effectively deploying them in real-world applications remains high.
We propose to address two main questions: 1) how can we aid programmers in developing private programs with high utility? and 2) how can we deploy differentially private algorithms to visual analysis systems which are widely used across sensitive domains such as health care and civic decision making? We first propose a programming framework and system which can be used to author programs for a variety of statistical tasks that involve answering counting queries. In the framework, programs are described as compositions of reusable modules and automatically satisfy differential privacy. Next, we investigate the challenges of deploying differentially private algorithms in visualization tasks. Specifically, we conduct a study to better understand the relationship between noise introduced for privacy protection, visual analysis tasks, visualization, and accuracy. Third, we demonstrate how directly deployment of differentially private algorithms causes both efficiency and accuracy issues in an interactive visualization dashboard and propose a solution using a middle layer proxy that delegate and process any front-end queries.
Advisor: Gerome Miklau