Back to Explorer
Research PaperResearchia:202602.18007[Computer Science > Cybersecurity]

Natural Privacy Filters Are Not Always Free: A Characterization of Free Natural Filters

Matthew Regehr

Abstract

We study natural privacy filters, which enable the exact composition of differentially private (DP) mechanisms with adaptively chosen privacy characteristics. Earlier privacy filters consider only simple privacy parameters such as Rényi-DP or Gaussian DP parameters. Natural filters account for the entire privacy profile of every query, promising greater utility for a given privacy budget. We show that, contrary to other forms of DP, natural privacy filters are not free in general. Indeed, we show that only families of privacy mechanisms that are well-ordered when composed admit free natural privacy filters.


Source: arXiv:2602.15815v1 - http://arxiv.org/abs/2602.15815v1 PDF: https://arxiv.org/pdf/2602.15815v1 Original Link: http://arxiv.org/abs/2602.15815v1

Submission:2/18/2026
Comments:0 comments
Subjects:Cybersecurity; Computer Science
Original Source:
View Original PDF
arXiv: This paper is hosted on arXiv, an open-access repository
Was this helpful?

Discussion (0)

Please sign in to join the discussion.

No comments yet. Be the first to share your thoughts!

Natural Privacy Filters Are Not Always Free: A Characterization of Free Natural Filters | Researchia | Researchia