Provable Privacy with Non-Private Pre-Processing

arXiv:2403.13041v1 Announce Type: cross
Abstract: When analysing Differentially Private (DP) machine learning pipelines, the potential privacy cost of data-dependent pre-processing is frequently overlooked in privacy accounting. In this work, we propose a general framework to evaluate the additional privacy cost incurred by non-private data-dependent pre-processing algorithms. Our framework establishes upper bounds on the overall privacy guarantees by utilising two new technical notions: a variant of DP termed Smooth DP and the bounded sensitivity of the pre-processing algorithms. In addition to …

abstract accounting algorithms arxiv cost cs.ai cs.cr cs.lg data framework general machine machine learning pipelines pre-processing privacy private data processing stat.ml type work