VFF: Exploring Privacy-Accuracy Tradeoffs using DPCOMP
Friday, September 22, 2017
12:00 pm - 1:00 pm
Ashwin Machanavajjhala · CS
Privacy is an important constraint that algorithms must satisfy when analyzing sensitive data from individuals. Differential privacy has arisen as the gold standard for exploring the tradeoff between the privacy ensured to individuals and the utility of the statistical insights mined from the data. Differentially private algorithms guarantee privacy by adding noise and are in use by some commercial (e.g., Google and Apple) and government entities (e.g., US Census) for collecting and sharing sensitive user data. Yet deployment of these techniques has been slowed by the complexity of algorithms and an incomplete understanding of the cost to accuracy implied by the adoption of differential privacy. In this talk, I will describe DPCOMP.org, a publicly-accessible web-based system, designed to support a broad community of users, including data analysts, privacy researchers, and data owners. Users can use DPCOMP to visualize the accuracy of state-of-the-art privacy algorithms and interactively explore algorithm output in order to understand, both quantitatively and qualitatively, the error introduced by differentially private algorithms.