Explore a framework designed to enhance the usability of Differential Privacy (DP) in this 21-minute conference talk from USENIX's PEPR '20. Learn how to quantify and visualize privacy vs utility trade-offs in DP, bridging the gap between theory, implementation, and practical application. Discover how this system helps practitioners think in terms of utility loss and user anonymity gains, rather than complex concepts like epsilons, deltas, and sensitivity bounds. Follow along as the speakers provide a quick primer on DP, explain the framework's development, and demonstrate its real-time application using an actual dataset.
Overview
Syllabus
PEPR '20 - Improving Usability of Differential Privacy at Scale
Taught by
USENIX