Securing Genomic Data Against Inference Attacks in Federated Learning Environments

TL;DR

This paper evaluates the vulnerability of federated learning in genomic data sharing to inference attacks, demonstrating significant privacy risks and highlighting the need for enhanced protective measures.

Contribution

It provides a comprehensive simulation of inference attacks on federated genomic data, revealing vulnerabilities and guiding future privacy-preserving solutions.

Findings

Gradient-Based MIA achieves 0.79 precision and 0.87 F1-score

Gradient exposure poses significant privacy risks

Naive federated learning is inadequate for genomic privacy

Abstract

Federated Learning (FL) offers a promising framework for collaboratively training machine learning models across decentralized genomic datasets without direct data sharing. While this approach preserves data locality, it remains susceptible to sophisticated inference attacks that can compromise individual privacy. In this study, we simulate a federated learning setup using synthetic genomic data and assess its vulnerability to three key attack vectors: Membership Inference Attack (MIA), Gradient-Based Membership Inference Attack, and Label Inference Attack (LIA). Our experiments reveal that Gradient-Based MIA achieves the highest effectiveness, with a precision of 0.79 and F1-score of 0.87, underscoring the risk posed by gradient exposure in federated updates. Additionally, we visualize comparative attack performance through radar plots and quantify model leakage across clients. The findings emphasize the inadequacy of na\"ive FL setups in safeguarding genomic privacy and motivate the development of more robust privacy-preserving mechanisms tailored to the unique sensitivity of genomic data.