Composable and versatile privacy via truncated CDP
Mark Bun, Cynthia Dwork, Guy N. Rothblum, Thomas Steinke · 2018
We propose truncated concentrated differential privacy (tCDP), a refinement of differential privacy and of concentrated differential privacy. This new definition provides robust and efficient composition guarantees, supports powerful algorithmic techniques such as privacy amplification via sub-sampling, and enables more accurate statistical analyses. In particular, we show a central task for which the new definition enables exponential accuracy improvement.