Command Palette

Search for a command to run...

GitHub

Can Several Minimal Findings Reveal a Hidden Attribute?

An Exactly Solvable Pilot on Linked, Coarsened and Task-Output Releases, with a Release-Audit Toolkit

Anish Prashun · Independent researcher · Technical report ·

Read the paper (PDF)Code and data (GitHub)DOI 10.5281/zenodo.24304575

Summary

Multi-stage AI workflows often pass a few structured findings between stages instead of raw records. This study measures how much several such findings, combined, reveal about an attribute that none of them states, in a synthetic testbed where the best possible attacker is computed exactly. It ships release_audit, a standard-library toolkit that computes the same leakage budget and the best release designs for your own pipeline.

Key findings

  • Linking two releases about the same household raised attacker accuracy to 60.0%, against 51.9% and 53.3% for either release alone (38.9% for always guessing the most common band).
  • In 193 of 3,000 test households the linked releases ruled out the low reserve band with certainty, which neither release allows on its own.
  • Coarsening the linked releases removed 1.8 points of accuracy while keeping 80% of report action items, and met its pre-set criterion in only 3 of 6 seed runs.
  • Releasing only the report-checklist answers kept full report utility but still leaked more than either single release.

Reproduce it

Python 3 standard library only, synthetic data, no network access. Clone the repository and run:

python3 run_pilot.py

Cite

Prashun, A. (2026). Can Several Minimal Findings Reveal a Hidden Attribute? An Exactly Solvable Pilot on Linked, Coarsened and Task-Output Releases, with a Release-Audit Toolkit [Technical report]. Zenodo. https://doi.org/10.5281/zenodo.24304575

@misc{prashun2026findings,
  author    = {Prashun, Anish},
  title     = {Can Several Minimal Findings Reveal a Hidden Attribute? An Exactly Solvable Pilot on Linked, Coarsened and Task-Output Releases, with a Release-Audit Toolkit},
  year      = {2026},
  publisher = {Zenodo},
  doi       = {10.5281/zenodo.24304575},
  url       = {https://doi.org/10.5281/zenodo.24304575},
  note      = {Technical report, code and data}
}

Paper and data: CC BY 4.0. Code: MIT. All data in the study is synthetic.

  • Privacy engineering
  • Attribute inference
  • Composition attacks
  • Data minimisation
  • AI workflows

More research