mlsanityData to 14 Oct 2026

Securing Genomic Data Against Inference Attacks in Federated Learning Environments

arXiv 2505.07188 ↗First posted 12 May 2025cs.CR cs.CLcited by 1

On the map: LLM safety and security → Federated unlearning and poisoning

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.

Key facts. Cited by 1 paper 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.

Builds on

22 of 44 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Membership Inference Attacks and Defenses in Federated Learning: A Survey9 Dec
  2. 2023Security and Privacy Issues of Federated Learning22 Jul
  3. 2023Active Membership Inference Attack under Local Differential Privacy in Federated Learning24 Feb
  4. 2022Subject Membership Inference Attacks in Federated Learning7 Jun

Other references · 18

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  4. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  5. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  6. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 127
  7. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 41
  8. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 39
  9. 2023A Survey for Federated Learning Evaluations: Goals and Measurescited by 16
  10. 2020Over-the-Air Membership Inference Attacks as Privacy Threats for Deep Learning-based Wireless Signal Classifierscited by 13
  11. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  12. 2024Robust Federated Learning Mitigates Client-side Training Data Distribution Inference Attackscited by 11
6 more
  1. 2024Privacy Preserving Federated Learning in Medical Imaging with Uncertainty Estimationcited by 9
  2. 2021Differentially Private Federated Learning for Cancer Predictioncited by 6
  3. 2021Re-identification of Individuals in Genomic Datasets Using Public Face Imagescited by 5
  4. 2024Privacy in Federated Learningcited by 2
  5. 2025Technical and Legal Aspects of Federated Learning in Bioinformatics: Applications, Challenges and Opportunitiescited by 2
  6. 2024Federated Learning in Genetics: Extended Analysis of Accuracy, Performance and Privacy Trade-offscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Evaluating Differential Privacy Against Membership Inference in Federated Learning: Insights from the NIST Genomics Red Team Challengecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025An Efficient Gradient-Based Inference Attack for Federated Learning
  2. 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning
  3. 2023Source Inference Attacks: Beyond Membership Inference Attacks in Federated Learning
  4. 2024FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning
  5. 2025Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
  6. 2023Privacy and Accuracy Implications of Model Complexity and Integration in Heterogeneous Federated Learning
  7. 2026Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning Models
  8. 2023Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning