Differentially private publication of database streams via hybrid video coding

While most anonymization technology available today is designed for static and small data, the current picture of massive volumes dynamic data arriving at unprecedented velocities. From standpoint anonymization, challenging type streams. However, while majority proposals deal with publishing either count-based or aggregated statistics about underlying stream, little attention has been paid to problem continuously stream itself differential privacy guarantees. In this work, we propose an method that can publish multiple numerical-attribute, finite microdata streams high protection as well utility, latter aspect measured distortion, delay record reordering. Our method, which relies on well-known pulse-code modulation scheme, adapts techniques originally intended hybrid video encoding, favor leverage dependencies among blocks original thereby reduce distortion. The proposed solution assessed experimentally two largest sets in scientific community working anonymization. extensive empirical evaluation shows trade-off protection, reordering, demonstrates suitability adapting video-compression anonymize database