Salil Vadhan: Differential Privacy: From Theory to Practice and Back

Abstract: Since it was introduced in 2006 by theoretical computer scientists Dwork, McSherry, Nissim, and Smith, differential privacy has become the leading framework for ensuring that individual-level information is not leaked through statistical releases or machine learning models built from sensitive datasets. In addition to a rich theoretical literature, differential privacy has also made an impressive transition to practice, with large-scale applications by the US Census Bureau and technology companies like Google, Apple, Microsoft, and Meta, and many other smaller-scale deployments. I will discuss some of my own journey from working on the theory of differential privacy to working on its practice, leading to OpenDP, a community effort to advance the practice of differential privacy that we launched in 2019. I will also describe how these efforts to bring differential privacy to practice raise new intriguing research questions, and the opportunities it raises for researchers in this space. Bio: Salil Vadhan is the Vicky Joseph Professor of Computer Science and Applied Mathematics at the Harvard John A. Paulson School of Engineering & Applied Sciences and co-leads the OpenDP open-source software project and the Harvard Privacy Tools Project. Vadhan’s research in theoretical computer science spans computational complexity, data privacy, and cryptography. Vadhan is a Simons Investigator and an ACM Fellow, and has received a Godel Prize, a Guggenheim Fellowship, a Bowden Award for Outstanding Research in Privacy-Enhancing Technologies, and the ACM Doctoral Dissertation Award. OpenMined is a non-profit foundation creating open-source technology infrastructure that helps researchers get answers from data without needing a copy or direct access. Our community of technologists is building Syft: the public network for non-public information. Learn more → www.openmined.org Supported by the OpenMined Foundation, the OpenMined Community is an online ecosystem of over 17,000 technologists, researchers, and industry professionals keen to unlock 1000x more data in every scientific field and industry. Join us on Slack → slack.openmined.org LinkedIn → www.linkedin.com/company/openmined X/Twitter → x.com/openminedorg Facebook → fb.com/openminedorg