mlsanityData to 14 Oct 2026

Poison to Detect: Detection of Targeted Overfitting in Federated Learning

arXiv 2509.11974 ↗First posted 15 Sep 2025cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) enables collaborative model training among clients without centralising data, making it a widely adopted privacy-enhancing technology (PET). Despite its privacy benefits, FL remains vulnerable to orchestrator-driven privacy attacks. In this paper, we study an underexplored threat in which a dishonest orchestrator intentionally manipulates the aggregation process to induce targeted overfitting in local models of specific clients. Although prior work focuses on reducing information leakage during training, we emphasise early client-side detection of targeted overfitting, allowing clients to disengage before significant harm occurs. To this end, we propose three detection techniques -- label flipping, backdoor trigger injection, and model fingerprinting -- which enable clients to verify the integrity of the global aggregation. We evaluated our methods across multiple datasets and attack scenarios. In single-client attacks, all three methods detect orchestrator-induced overfitting within 1-2 training rounds with F1 scores up to 0.7. Scalability experiments further show that detection effectiveness is influenced by cohort composition and method parameters. These results demonstrate that client-side integrity testing can provide early, effective, and scalable detection, supporting safer deployment of FL systems.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 32 of its 65 references that are in the map. First posted on arXiv 15 Sep 2025.

Builds on

32 of 65 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2019Advances and Open Problems in Federated Learningcited by 3,046
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  5. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  6. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  7. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  8. 2020Adaptive Federated Optimizationcited by 1,046
  9. 2018How To Backdoor Federated Learningcited by 765
  10. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 711
  11. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 690
  12. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
20 more
  1. 2019Does Learning Require Memorization? A Short Tale about a Long Tailcited by 460
  2. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  3. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 326
  4. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  5. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  6. 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 179
  7. 2022Reconstructing Training Data with Informed Adversariescited by 148
  8. 2022FLDetector: Defending Federated Learning Against Model Poisoning Attacks via Detecting Malicious Clientscited by 125
  9. 2020A Blockchain-based Decentralized Federated Learning Framework with Committee Consensuscited by 84
  10. 2016Data Poisoning Attacks on Factorization-Based Collaborative Filteringcited by 83
  11. 2020BaFFLe: Backdoor detection via Feedback-based Federated Learningcited by 53
  12. 2020Robust Federated Learning with Noisy Labelscited by 40
  13. 2021Federated Learning with Local Differential Privacy: Trade-offs between Privacy, Utility, and Communicationcited by 39
  14. 2024Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerablecited by 25
  15. 2021Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learningcited by 21
  16. 2023On the Over-Memorization During Natural, Robust and Catastrophic Overfittingcited by 20
  17. 2023A Survey on Class Imbalance in Federated Learningcited by 13
  18. 2022Federated Learning Attacks and Defenses: A Surveycited by 12
  19. 2025Deep Learning Model Inversion Attacks and Defenses: A Comprehensive Surveycited by 9
  20. 2025FinP: Fairness-in-Privacy in Federated Learning by Addressing Disparities in Privacy Riskcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning
  2. 2024Defending against Data Poisoning Attacks in Federated Learning via User Elimination
  3. 2025FedNIA: Noise-Induced Activation Analysis for Mitigating Data Poisoning in Federated Learning
  4. 2022Backdoor Defense in Federated Learning Using Differential Testing and Outlier Detection
  5. 2022Identifying Backdoor Attacks in Federated Learning via Anomaly Detection
  6. 2023A Survey on Vulnerability of Federated Learning: A Learning Algorithm Perspective
  7. 2022FL-Defender: Combating Targeted Attacks in Federated Learning
  8. 2026United We Defend: Collaborative Membership Inference Defenses in Federated Learning