mlsanityData to 14 Oct 2026

United We Defend: Collaborative Membership Inference Defenses in Federated Learning

arXiv 2601.06866 ↗First posted 11 Jan 2026cs.CRcited by 1

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

Abstract (arXiv)

Membership inference attacks (MIAs), which determine whether a specific data point was included in the training set of a target model, have posed severe threats in federated learning (FL). Unfortunately, existing MIA defenses, typically applied independently to each client in FL, are ineffective against powerful trajectory-based MIAs that exploit temporal information throughout the training process to infer membership status. In this paper, we investigate a new FL defense scenario driven by heterogeneous privacy needs and privacy-utility trade-offs, where only a subset of clients are defended, as well as a collaborative defense mode where clients cooperate to mitigate membership privacy leakage. To this end, we introduce CoFedMID, a collaborative defense framework against MIAs in FL, which limits local model memorization of training samples and, through a defender coalition, enhances privacy protection and model utility. Specifically, CoFedMID consists of three modules: a class-guided partition module for selective local training samples, a utility-aware compensation module to recycle contributive samples and prevent their overconfidence, and an aggregation-neutral perturbation module that injects noise for cancellation at the coalition level into client updates. Extensive experiments on three datasets show that our defense framework significantly reduces the performance of seven MIAs while incurring only a small utility loss. These results are consistently verified across various defense settings.

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 50 of its 80 references that are in the map. First posted on arXiv 11 Jan 2026.

Builds on

50 of 80 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Find a Scapegoat: Poisoning Membership Inference Attack and Defense to Federated Learning1 Jul
  2. 2024Membership Inference Attacks and Defenses in Federated Learning: A Survey9 Dec
  3. 2024FedMIA: An Effective Membership Inference Attack Exploiting "All for One" Principle in Federated Learning9 Feb
  4. 2022Subject Membership Inference Attacks in Federated Learning7 Jun

Other references · 46

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  4. 2016Deep Learning with Differential Privacycited by 2,728
  5. 2015Learning Deep Features for Discriminative Localizationcited by 2,436
  6. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  7. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  8. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  9. 2019Federated Learning: Challenges, Methods, and Future Directionscited by 1,538
  10. 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,475
  11. 2018Federated Learning with Non-IID Datacited by 1,108
  12. 2021Membership Inference Attacks From First Principlescited by 878
34 more
  1. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  2. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 851
  3. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  4. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  5. 2020Label-Only Membership Inference Attackscited by 388
  6. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 328
  7. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  8. 2018Distributed learning of deep neural network over multiple agentscited by 279
  9. 2017Automated Curriculum Learning for Neural Networkscited by 257
  10. 2022Unlocking High-Accuracy Differentially Private Image Classification through Scalecited by 224
  11. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 197
  12. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 186
  13. 2017Machine Learning Models that Remember Too Muchcited by 169
  14. 2020Membership Leakage in Label-Only Exposurescited by 168
  15. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 78
  16. 2019Overlearning Reveals Sensitive Attributescited by 76
  17. 2022Membership Inference Attacks Against Text-to-image Generation Modelscited by 69
  18. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecturecited by 67
  19. 2022TAN Without a Burn: Scaling Laws of DP-SGDcited by 52
  20. 2024Membership Inference Attacks Against In-Context Learningcited by 43
  21. 2022RelaxLoss: Defending Membership Inference Attacks without Losing Utilitycited by 37
  22. 2024Evaluations of Machine Learning Privacy Defenses are Misleadingcited by 36
  23. 2021Source Inference Attacks in Federated Learningcited by 34
  24. 2023Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Predictioncited by 29
  25. 2020Memorizing without overfitting: Bias, variance, and interpolation in over-parameterized modelscited by 27
  26. 2024SeqMIA: Sequential-Metric Based Membership Inference Attackcited by 23
  27. 2023On the Over-Memorization During Natural, Robust and Catastrophic Overfittingcited by 20
  28. 2020An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learningcited by 19
  29. 2019Effects of Differential Privacy and Data Skewness on Membership Inference Vulnerabilitycited by 17
  30. 2021Collaboration Equilibrium in Federated Learningcited by 16
  31. 2023FedPass: Privacy-Preserving Vertical Federated Deep Learning with Adaptive Obfuscationcited by 10
  32. 2024Cross-silo Federated Learning with Record-level Personalized Differential Privacycited by 9
  33. 2022Towards Sparsified Federated Neuroimaging Models via Weight Pruningcited by 4
  34. 2024Learning Versatile Skills with Curriculum Maskingcited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026FISGuard: Defending Against Membership Inference via Fixed Input Subspacescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Res-MIA: A Training-Free Resolution-Based Membership Inference Attack on Federated Learning Models
  2. 2023MIA-BAD: An Approach for Enhancing Membership Inference Attack and its Mitigation with Federated Learning
  3. 2023Active Membership Inference Attack under Local Differential Privacy in Federated Learning
  4. 2024Membership Information Leakage in Federated Contrastive Learning
  5. 2022Perfectly Accurate Membership Inference by a Dishonest Central Server in Federated Learning
  6. 2025FedBAP: Backdoor Defense via Benign Adversarial Perturbation in Federated Learning
  7. 2026Leveraging Soft Prompts for Privacy Attacks in Federated Prompt Tuning
  8. 2023A Survey of What to Share in Federated Learning: Perspectives on Model Utility, Privacy Leakage, and Communication Efficiency