We believe that science and technology are advanced through the ongoing, free dissemination of research and best practices. Zuva, in part, has been built on the work of others and as technology leaders, we continue the tradition of sharing our research.

Towards Protecting Sensitive Text with Differential Privacy

Natural language processing can often require handling privacy-sensitive text. To avoid revealing confidential information, data owners and practitioners can use differential privacy, which provides a mathematically guaranteeable definition of privacy preservation. In this work, we explore the possibility of applying differential privacy to feature hashing. Feature hashing is a common technique for handling out-of-dictionary vocabulary, and for creating a lookup table to find feature weights in constant time. Traditionally, differential privacy involves adding noise to hide the true value of data points.