What question did this study set out to answer?

To verify that federated genomic sites apply the same preprocessing without sharing raw data.

March 28, 2026Open Access

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

Key Points

To verify that federated genomic sites apply the same preprocessing without sharing raw data.
Institutions apply local differential privacy to perturb genomic data.
A RandomForest classifier is trained locally at each site.
One LIME explanation vector is sent to a coordinating server.
The server simulates various preprocessing combinations and trains a classifier.
The framework is tested with centralized simulations and distributed experiments across multiple sites.
Achieved 80% accuracy in centralized simulations with 15 preprocessing configurations.
Maintained membership-inference attack power below 0.05.
In distributed experiments, binary compatibility detection reached 70% accuracy at 500 SNPs.

Abstract

Abstract 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.

Read Full Paperexternally

AI से पूछें

Bookmark

View Full Paper