# Concurrent Composition for Interactive Differential Privacy with Adaptive Privacy-Loss Parameters

arXiv: https://arxiv.org/abs/2309.05901 · HTML: https://mlsanity.com/paper/2309.05901/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Sep 2023.

## Built on by (most cited first, 2 of 2)

- [Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion](https://mlsanity.com/paper/2507.08163/) (2025)
- [Continual Learning With Participation Privacy: An Auditable Buffering-Aggregation Recipe](https://mlsanity.com/paper/2607.07209/) (2026)

## Abstract (arXiv)

In this paper, we study the concurrent composition of interactive mechanisms with adaptively chosen privacy-loss parameters. In this setting, the adversary can interleave queries to existing interactive mechanisms, as well as create new ones. We prove that every valid privacy filter and odometer for noninteractive mechanisms extends to the concurrent composition of interactive mechanisms if privacy loss is measured using (ε, δ)-DP, f-DP, or R'enyi DP of fixed order. Our results offer strong theoretical foundations for enabling full adaptivity in composing differentially private interactive mechanisms, showing that concurrency does not affect the privacy guarantees. We also provide an implementation for users to deploy in practice.