mlsanityData to 7 Oct 2026

A Survey of Privacy Attacks in Machine Learning

arXiv 2007.07646 ↗First posted 15 Jul 2020cs.CR cs.LGcited by 143

Not on the map. Why?

Cited by 27 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

As machine learning becomes more widely used, the need to study its implications in security and privacy becomes more urgent. Although the body of work in privacy has been steadily growing over the past few years, research on the privacy aspects of machine learning has received less focus than the security aspects. Our contribution in this research is an analysis of more than 40 papers related to privacy attacks against machine learning that have been published during the past seven years. We propose an attack taxonomy, together with a threat model that allows the categorization of different attacks based on the adversarial knowledge, and the assets under attack. An initial exploration of the causes of privacy leaks is presented, as well as a detailed analysis of the different attacks. Finally, we present an overview of the most commonly proposed defenses and a discussion of the open problems and future directions identified during our analysis.

Key facts. Cited by 143 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 23; 2023: 25; 2024: 34; 2025: 32; 2026: 20.

143 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  2. 2023Large Language Model Alignment: A Surveycited by 241
  3. 2021FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learningcited by 140
  4. 2023ProPILE: Probing Privacy Leakage in Large Language Modelscited by 127
  5. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  6. 2021Trustworthy AI: A Computational Perspectivecited by 93
  7. 2023Membership Inference Attacks against Synthetic Data through Overfitting Detectioncited by 66
  8. 2023Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competitioncited by 65
  9. 2022Label-Only Model Inversion Attacks via Boundary Repulsioncited by 56
  10. 2022SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learningcited by 47
  11. 2023Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreakscited by 45
  12. 2021Survey: Leakage and Privacy at Inference Timecited by 44
38 more
  1. 2024Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)cited by 44
  2. 2022Gradient Obfuscation Gives a False Sense of Security in Federated Learningcited by 37
  3. 2023Reinforcement Learning-Based Black-Box Model Inversion Attackscited by 33
  4. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  5. 2022On the Privacy Risks of Algorithmic Recoursecited by 32
  6. 2021FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorizationcited by 31
  7. 2022Bilateral Dependency Optimization: Defending Against Model-inversion Attackscited by 30
  8. 2023Identifying and Mitigating Privacy Risks Stemming from Language Models: A Surveycited by 30
  9. 2023Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Datacited by 29
  10. 2022Model Inversion Attacks against Graph Neural Networkscited by 26
  11. 2022Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerabilitycited by 25
  12. 2023A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applicationscited by 22
  13. 2022The privacy issue of counterfactual explanations: explanation linkage attackscited by 20
  14. 2023Gaussian Membership Inference Privacycited by 20
  15. 2021Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model's Complexitycited by 19
  16. 2024Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Imagescited by 18
  17. 2024Poison-splat: Computation Cost Attack on 3D Gaussian Splattingcited by 17
  18. 2025Rethinking Data Protection in the (Generative) Artificial Intelligence Eracited by 17
  19. 2023Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillationcited by 14
  20. 2022Differentially Private Counterfactuals via Functional Mechanismcited by 13
  21. 2022Machine Learning with Confidential Computing: A Systematization of Knowledgecited by 13
  22. 2022Towards Lightweight Black-Box Attacks against Deep Neural Networkscited by 13
  23. 2024The Federation Strikes Back: A Survey of Federated Learning Privacy Attacks, Defenses, Applications, and Policy Landscapecited by 13
  24. 2023Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Surveycited by 12
  25. 2024Trained Random Forests Completely Reveal your Datasetcited by 11
  26. 2024Model Inversion Attacks: A Survey of Approaches and Countermeasurescited by 11
  27. 2025Membership Inference Attacks as Privacy Tools: Reliability, Disparity and Ensemblecited by 11
  28. 2022Exploiting Fairness to Enhance Sensitive Attributes Reconstructioncited by 10
  29. 2025Robustness and Cybersecurity in the EU Artificial Intelligence Actcited by 10
  30. 2021Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategiescited by 9
  31. 2024Noise-Aware Algorithm for Heterogeneous Differentially Private Federated Learningcited by 9
  32. 2024Imperio: Language-Guided Backdoor Attacks for Arbitrary Model Controlcited by 8
  33. 2024Improving Robustness to Model Inversion Attacks via Sparse Coding Architecturescited by 8
  34. 2024TUNI: A Textual Unimodal Detector for Identity Inference in CLIP Modelscited by 8
  35. 2023Probabilistic Dataset Reconstruction from Interpretable Modelscited by 7
  36. 2024Cross-silo Federated Learning with Record-level Personalized Differential Privacycited by 7
  37. 2024The Data Minimization Principle in Machine Learningcited by 7
  38. 2025RealHarm: A Collection of Real-World Language Model Application Failurescited by 7

50 most cited of 143 All 143 (JSON)