# Securing Genomic Data Against Inference Attacks in Federated Learning Environments

arXiv: https://arxiv.org/abs/2505.07188 · HTML: https://mlsanity.com/paper/2505.07188/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security.
- Builds on 22 of its 44 references that are in the map.
- First posted on arXiv 12 May 2025.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 22 of 22)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Advances and Open Problems in Federated Learning](https://mlsanity.com/paper/1912.04977/) (2019)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Federated Learning: Challenges, Methods, and Future Directions](https://mlsanity.com/paper/1908.07873/) (2019)
- [ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models](https://mlsanity.com/paper/1806.01246/) (2018)
- [When the Curious Abandon Honesty: Federated Learning Is Not Private](https://mlsanity.com/paper/2112.02918/) (2021)
- [Recent Advances on Federated Learning: A Systematic Survey](https://mlsanity.com/paper/2301.01299/) (2023)
- [Gradient Obfuscation Gives a False Sense of Security in Federated Learning](https://mlsanity.com/paper/2206.04055/) (2022)
- [Membership Inference Attacks and Defenses in Federated Learning: A Survey](https://mlsanity.com/paper/2412.06157/) (2024)
- [Subject Membership Inference Attacks in Federated Learning](https://mlsanity.com/paper/2206.03317/) (2022)
- [Active Membership Inference Attack under Local Differential Privacy in Federated Learning](https://mlsanity.com/paper/2302.12685/) (2023)
- [A Survey for Federated Learning Evaluations: Goals and Measures](https://mlsanity.com/paper/2308.11841/) (2023)
- [Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifiers](https://mlsanity.com/paper/2006.14576/) (2020)
- [The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscape](https://mlsanity.com/paper/2405.03636/) (2024)
- [Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attacks](https://mlsanity.com/paper/2403.03149/) (2024)
- [Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimation](https://mlsanity.com/paper/2406.12815/) (2024)
- [Differentially Private Federated Learning for Cancer Prediction](https://mlsanity.com/paper/2101.02997/) (2021)
- [Re-identification of Individuals in Genomic Datasets Using Public Face Images](https://mlsanity.com/paper/2102.08557/) (2021)
- [Security and Privacy Issues of Federated Learning](https://mlsanity.com/paper/2307.12181/) (2023)
- [Privacy in Federated Learning](https://mlsanity.com/paper/2408.08904/) (2024)
- [Technical and Legal Aspects of Federated Learning in Bioinformatics: Applications, Challenges and Opportunities](https://mlsanity.com/paper/2503.09649/) (2025)
- [Federated Learning in Genetics: Extended Analysis of Accuracy, Performance and Privacy Trade-offs](https://mlsanity.com/paper/2402.14527/) (2024)

## Built on by (most cited first, 1 of 1)

- [Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challenge](https://mlsanity.com/paper/2604.12737/) (2026)

## Abstract (arXiv)

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.