Noise Variance Optimization in Differential Privacy: A Game-Theoretic Approach Through Per-Instance Differential Privacy

arXiv:2404.15686v1 Announce Type: new
Abstract: The concept of differential privacy (DP) can quantitatively measure privacy loss by observing the changes in the distribution caused by the inclusion of individuals in the target dataset. The DP, which is generally used as a constraint, has been prominent in safeguarding datasets in machine learning in industry giants like Apple and Google. A common methodology for guaranteeing DP is incorporating appropriate noise into query outputs, thereby establishing statistical defense systems against privacy attacks such …

arxiv can concept cs.cr dataset differential privacy distribution game inclusion instance loss measure noise optimization privacy safeguarding target