Protecting Privacy with MATH (Collab with the Census)

minutephysics explains how differential privacy uses mathematical noise to protect individual data in the US Census.

This video was made in collaboration with the US Census Bureau and fact-checked by Census Bureau scientists. Any opinions and errors are my own. For more information, visit census.gov/about/policies/privacy/statistical_safeguards.htm… or search "differential privacy" at census.gov. REFERENCES Differential Privacy in the Wild: vldb.org/pvldb/vol9/p1611-machanavajjhala.pdf Harvard University Privacy Tools Project: privacytools.seas.harvard.edu/differential-privacy Simons Institute Workshop Video Recordings and Articles Archive: simons.berkeley.edu/workshops/schedule/6281 Cynthia Dwork (key inventor of Differential Privacy), giving a great intro talk about differential privacy: youtube.com/watch?v=lg-VhHlztqo Shiva P Kasiviswanathan and Adam Smith. On the semantics of differential privacy: A Bayesian formulation. Journal of Privacy and Confidentiality, 6(1):1–16, 2014. Shiva Prasad Kasiviswanathan and Adam Smith. On the ‘semantics’ of differential privacy: A Bayesian formulation. 2015. arxiv.org/abs/0803.3946 Daniel Kifer and Ashwin Machanavajjhala. A rigorous and customizable framework for privacy. In ACM Symposium on Principles of Database Systems (PODS), 2012. Daniel Kifer and Ashwin Machanavajjhala. Pufferfish: A framework for mathematical privacy definitions. ACM Trans. Database Syst., 39(1):3, 2014. Support MinutePhysics on Patreon! patreon.com/minutephysics Link to Patreon Supporters: minutephysics.com/supporters/ MinutePhysics is on twitter - @minutephysics And facebook - facebook.com/minutephysics And Google+ (does anyone use this any more?) - bit.ly/qzEwc6 Minute Physics provides an energetic and entertaining view of old and new problems in physics -- all in a minute! Created by Henry Reich