Privacy-Preserving Technologies Meet Machine Learning

• Activity Number: 633 - Foundations of Data Science: Privacy-Preserving Inference
• Type: Invited
• Date/Time: Thursday, August 1, 2019 : 10:30 AM to 12:20 PM
• Sponsor: Business and Economic Statistics Section
• Author(s): Jeannette Wing*
• Companies: Columbia University, Data Science Institute
• Keywords: Privacy; Differential Privacy; Secure Multi-Party Computation; Homomorphic Encryption

Abstract

This talk will relate technologies that can help preserve the privacy of data to methods in machine learning. These technologies include statistics-based approaches, such as differential privacy; cryptographic approaches, such as secure multi-party computation and homomorphic encryption; and hardware approaches, such as secure enclaves.