, the Exponential mechanism) for private selection, which previously lacked GDP analyses.
New methods tighten privacy accounting for DP synthetic data pipelines
The authors derive GDP analysis of bounded-range mechanisms and introduce AIM-GDP and MixCal for tighter end-to-end composability, better utility, and auditable guarantees.
Big Tech
Georgi Ganev · Vadym Doroshenko · Arun Ganesh · Juan Felipe Gomez · Ryan McKenna · Bogdan Kulynych
UCL · SAS · Google · Google Research · Hasso Plattner Institute
Research Digest··2 min read
The authors develop privacy loss distribution (PLD) and Gaussian DP (GDP) analyses for bounded-range mechanisms such as the Exponential mechanism, enabling tighter accounting than prior zCDP-based approaches.
Why this paper
From Google and 5 others · Released code
In one line
GDP and PLD analyses of bounded-range mechanisms enable tighter end-to-end accounting for mixed DP synthetic data pipelines, improving utility at the same privacy level.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ✓Limitations stated by the authors (3 noted)
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§