mlsanityData to 7 Oct 2026

Exploiting Unintended Feature Leakage in Collaborative Learning

arXiv 1805.04049 ↗First posted 10 May 2018cs.CR cs.AIcited by 509

Not on the map. Why?

Cited by 63 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Collaborative machine learning and related techniques such as federated learning allow multiple participants, each with his own training dataset, to build a joint model by training locally and periodically exchanging model updates. We demonstrate that these updates leak unintended information about participants' training data and develop passive and active inference attacks to exploit this leakage. First, we show that an adversarial participant can infer the presence of exact data points -- for example, specific locations -- in others' training data (i.e., membership inference). Then, we show how this adversary can infer properties that hold only for a subset of the training data and are independent of the properties that the joint model aims to capture. For example, he can infer when a specific person first appears in the photos used to train a binary gender classifier. We evaluate our attacks on a variety of tasks, datasets, and learning configurations, analyze their limitations, and discuss possible defenses.

Key facts. Cited by 509 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 113; 2022: 110; 2023: 84; 2024: 97; 2025: 63; 2026: 41.

509 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks From First Principlescited by 839
  2. 2021See through Gradients: Image Batch Recovery via GradInversioncited by 320
  3. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  4. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  5. 2021Adversary Instantiation: Lower Bounds for Differentially Private Machine Learningcited by 193
  6. 2021FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropoutcited by 192
  7. 2023Text Embeddings Reveal (Almost) As Much As Textcited by 189
  8. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 188
  9. 2021Graph Unlearningcited by 129
  10. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
  11. 2021The Distributed Discrete Gaussian Mechanism for Federated Learning with Secure Aggregationcited by 127
  12. 2021When the Curious Abandon Honesty: Federated Learning Is Not Privatecited by 126
38 more
  1. 2023Dataset Distillation: A Comprehensive Reviewcited by 126
  2. 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 125
  3. 2022Zero-Shot Machine Unlearningcited by 125
  4. 2022Privacy for Free: How does Dataset Condensation Help Privacy?cited by 119
  5. 2023Machine Learning for Synthetic Data Generation: A Reviewcited by 118
  6. 2021Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Modelscited by 106
  7. 2021Gradient Inversion with Generative Image Priorcited by 101
  8. 2023Low-Cost High-Power Membership Inference Attackscited by 99
  9. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 94
  10. 2021PPFL: Privacy-preserving Federated Learning with Trusted Execution Environmentscited by 93
  11. 2022Membership Inference Attacks by Exploiting Loss Trajectorycited by 93
  12. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?cited by 90
  13. 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learningcited by 86
  14. 2023Multimodal Federated Learning via Contrastive Representation Ensemblecited by 85
  15. 2021A Study of Face Obfuscation in ImageNetcited by 83
  16. 2021Membership Inference Attack on Graph Neural Networkscited by 81
  17. 2022Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challengescited by 81
  18. 2021Node-Level Membership Inference Attacks Against Graph Neural Networkscited by 80
  19. 2021FedProc: Prototypical Contrastive Federated Learning on Non-IID datacited by 80
  20. 2021ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Modelscited by 79
  21. 2022Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakagecited by 72
  22. 2022Recovering Private Text in Federated Learning of Language Modelscited by 67
  23. 2021Eluding Secure Aggregation in Federated Learning via Model Inconsistencycited by 66
  24. 2021From Distributed Machine Learning to Federated Learning: A Surveycited by 65
  25. 2021Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecturecited by 63
  26. 2021Provably Secure Federated Learning against Malicious Clientscited by 60
  27. 2021Collaborative Federated Learning For Healthcare: Multi-Modal COVID-19 Diagnosis at the Edgecited by 56
  28. 2021Property Inference From Poisoningcited by 56
  29. 2021Decentralized Federated Learning through Proxy Model Sharingcited by 56
  30. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  31. 2022FederatedScope: A Flexible Federated Learning Platform for Heterogeneitycited by 53
  32. 2021Membership Inference Attacks Against Recommender Systemscited by 52
  33. 2022Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Modelscited by 52
  34. 2022GradViT: Gradient Inversion of Vision Transformerscited by 52
  35. 2023FedMultimodal: A Benchmark For Multimodal Federated Learningcited by 51
  36. 2023GIFD: A Generative Gradient Inversion Method with Feature Domain Optimizationcited by 45
  37. 2021Survey: Leakage and Privacy at Inference Timecited by 44
  38. 2021Gradient Disaggregation: Breaking Privacy in Federated Learning by Reconstructing the User Participant Matrixcited by 43

50 most cited of 509 All 509 (JSON)