Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

3 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ENEM microdata privacy verification package

This repository is the public verification supplement for the study of high-precision ENEM performance scores as quasi-identifiers. It publishes aggregate evidence, declarative schemas, claim-facing metadata, synthetic examples, and presentation generators. It does not reproduce the restricted record-level linkage pipelines.

Accompanying study

Knowing Millions of Students Too Well: High-Entropy Scores as Deterministic Quasi-Identifiers for Re-Identification and Data Leakage in the Brazilian High School Exam

Authors:

  • Henrique Lindemann
  • Eder John Scheid
  • Lisandro Zambenedetti Granville
  • Muriel Figueredo Franco

Published in Computers & Security (Elsevier), 2026. DOI: 10.1016/j.cose.2026.105080

Verification boundary

The package supports verification of reported populations, equivalence-class counts, linkage outcomes, sensitivity analyses, privacy--utility results, accessibility-proxy exposure, and release-specific recalculability. It excludes nominal source files, candidate-level joins, identity crosswalks, canonical name pairs, person trackers, deterministic record hashes, and operational loaders. See scope and boundary.

Evidence map

Manuscript pointers use the directory names below. Open the family README first; it gives the scope and points to the relevant files.

Run the public gates

python3 tools/build_release.py --verify-only

The command reads only files in this repository and checks all aggregate invariants and claims, deterministic tables and figures, manifest hashes, and the publication boundary. Maintainers separately verify the allowlisted schemas against real CSV headers before updating release metadata.

The exact aggregate source commit is recorded in verification/manifest.json; do not infer it from the public repository HEAD. This package records a2c43903d3249807bf86b387f09c48996fed411d. Start with the verification guide, then consult data sources, provenance, and the glossary.

License

Repository-authored software and documentation are available under the MIT License.

About

Supplementary material, reproducibility pipelines, and extended results for the paper "Knowing Millions of Students Too Well: High-Entropy Scores as Deterministic Quasi-Identifiers for Re-Identification and Data Leakage in the Brazilian High School Exam"

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages