EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Privacy-preserving verification of preprocessing in federated learning for genomic data

Wenbiao Li iD, Anisa Halimi, Jaideep Vaidya iD, Xiaoqian Jiang iD, Erman Ayday

JAMIA Open · 06.03.2026 · 9 (2)

DOI: 10.1093/jamiaopen/ooag040 ↗

Kurz gefasst

Fachartikel in der Zeitschrift JAMIA Open, online erschienen am 26.03.2026. Verfasst von Wenbiao Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Case Western Reserve University, Cleveland, OH, United States. Die Arbeit nennt 23 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Science Foundation, National Institutes of Health, CPRIT Scholar in Cancer Research.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

To verify that federated genomic study sites applied identical preprocessing pipelines without disclosing raw genotypes. Materials and Methods Each institution perturbs a 100-SNP slice using local differential privacy (LDP), trains a RandomForest classifier, and transmits one LIME explanation vector to a coordinating server. The server simulates 15 preprocessing combinations and trains a RandomForest classifier to predict each site’s configuration.

Results

In centralized simulation, the verifier achieved 80% accuracy across 15 preprocessing configurations on the GMMAT (n = 400) and synthetic genome (n = 2504) datasets while maintaining membership-inference attack power below 0.05 at ε = 3. In distributed Flower FL experiments with data partitioned across three sites, binary compatibility detection reached 70% accuracy at 500 SNPs.

Discussion

A single differentially private explanation vector provides an auditable preprocessing fingerprint. The gap between centralized and distributed accuracy reflects expected FL data partitioning effects.

Conclusion

This framework demonstrates the feasibility of automated preprocessing verification in federated genomic consortia without compromising participant privacy.

Schlagwörter

Stichwörter der Autor:innen

Federated learningdata preprocessingdifferential privacygenomic data sharingquality control

Autor:innen und Institutionen

  • Case Western Reserve University, Cleveland, OH, United States.
  • IBM Research Europe, Dublin, Ireland.
  • Rutgers University, Newark, NJ, United States.
  • UTHealth, Houston, TX, United States.

ORCID-Profile: Wenbiao Li, Jaideep Vaidya, Xiaoqian Jiang

Förderung

  • National Science Foundation
  • National Institutes of Health
  • CPRIT Scholar in Cancer Research
  • Christopher Sarofim Family Professorship, UT Stars
  • UTHealth startup, the National Institutes of Health

Zitieren

APA

Li, W., Halimi, A., Vaidya, J., Jiang, X., & Ayday, E. (2026). Privacy-preserving verification of preprocessing in federated learning for genomic data. JAMIA Open, 9(2). https://doi.org/10.1093/jamiaopen/ooag040

Vancouver

Li W, Halimi A, Vaidya J, Jiang X, Ayday E. Privacy-preserving verification of preprocessing in federated learning for genomic data. JAMIA Open. 2026;9(2). doi:10.1093/jamiaopen/ooag040

BibTeX
@article{Li2026,
  author = {Li, Wenbiao and Halimi, Anisa and Vaidya, Jaideep and Jiang, Xiaoqian and Ayday, Erman},
  title = {Privacy-preserving verification of preprocessing in federated learning for genomic data},
  journal = {JAMIA Open},
  year = {2026},
  volume = {9},
  number = {2},
  doi = {10.1093/jamiaopen/ooag040}
}
Kostenlos starten →