mlsanityData to 7 Oct 2026

State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey

arXiv 2404.16847 ↗First posted 25 Feb 2024cs.CR cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

This paper examines the evolving landscape of machine learning (ML) and its profound impact across various sectors, with a special focus on the emerging field of Privacy-preserving Machine Learning (PPML). As ML applications become increasingly integral to industries like telecommunications, financial technology, and surveillance, they raise significant privacy concerns, necessitating the development of PPML strategies. The paper highlights the unique challenges in safeguarding privacy within ML frameworks, which stem from the diverse capabilities of potential adversaries, including their ability to infer sensitive information from model outputs or training data. We delve into the spectrum of threat models that characterize adversarial intentions, ranging from membership and attribute inference to data reconstruction. The paper emphasizes the importance of maintaining the confidentiality and integrity of training data, outlining current research efforts that focus on refining training data to minimize privacy-sensitive information and enhancing data processing techniques to uphold privacy. Through a comprehensive analysis of privacy leakage risks and countermeasures in both centralized and collaborative learning settings, this paper aims to provide a thorough understanding of effective strategies for protecting ML training data against privacy intrusions. It explores the balance between data privacy and model utility, shedding light on privacy-preserving techniques that leverage cryptographic methods, Differential Privacy, and Trusted Execution Environments. The discussion extends to the application of these techniques in sensitive domains, underscoring the critical role of PPML in ensuring the privacy and security of ML systems.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 32 of its 79 references that are in the map. First posted on arXiv 25 Feb 2024.

Builds on

32 of 79 references.

References · 32

  1. 2016Deep Learning with Differential Privacycited by 2,682
  2. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  3. 2019Deep Leakage from Gradientscited by 1,004
  4. 2021Membership Inference Attacks From First Principlescited by 839
  5. 2016Semi-supervised Knowledge Transfer for Deep Learning from Private Training Datacited by 347
  6. 2023Analyzing Leakage of Personally Identifiable Information in Language Modelscited by 278
  7. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  8. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 237
  9. 2019R'enyi Differential Privacy of the Sampled Gaussian Mechanismcited by 199
  10. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 168
  11. 2020A Survey of Privacy Attacks in Machine Learningcited by 143
  12. 2022Reconstructing Training Data with Informed Adversariescited by 143
20 more
  1. 2016Concentrated Differential Privacycited by 139
  2. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
  3. 2020GS-WGAN: A Gradient-Sanitized Approach for Learning Differentially Private Generatorscited by 117
  4. 2019Generative Models for Effective ML on Private, Decentralized Datasetscited by 85
  5. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  6. 2019Differentially Private Model Publishing for Deep Learningcited by 69
  7. 2018Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applicationscited by 67
  8. 2018AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine Learningcited by 58
  9. 2021Property Inference From Poisoningcited by 56
  10. 2017DeepSecure: Scalable Provably-Secure Deep Learningcited by 48
  11. 2022SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learningcited by 47
  12. 2022Are Your Sensitive Attributes Private? Novel Model Inversion Attribute Inference Attacks on Classification Modelscited by 42
  13. 2018Chiron: Privacy-preserving Machine Learning as a Servicecited by 38
  14. 2020BLAZE: Blazing Fast Privacy-Preserving Machine Learningcited by 32
  15. 2023Scale-MIA: A Scalable Model Inversion Attack against Secure Federated Learning via Latent Space Reconstructioncited by 18
  16. 2019Privacy for Free: Communication-Efficient Learning with Differential Privacy Using Sketchescited by 17
  17. 2019Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environmentscited by 17
  18. 2023Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillationcited by 14
  19. 2018Confidential Inference via Ternary Model Partitioningcited by 5
  20. 2021Decentralized Spectrum Access System: Vision, Challenges, and a Blockchain Solutioncited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 2.

5 papers.

  1. 2024Privacy-Preserving Large Language Models: Mechanisms, Applications, and Future Directionscited by 5
  2. 2024Accelerating Sparse Graph Neural Networks with Tensor Core Optimizationcited by 1
  3. 2025Enabling Trustworthy Federated Learning via Remote Attestation for Mitigating Byzantine Threatscited by 0
  4. 2026PriMod4AI: Lifecycle-Aware Privacy Threat Modeling for AI Systems using LLMcited by 0
  5. 2026POPS: Recovering Unlearned Multi-Modality Knowledge in MLLMs with Prompt-Optimized Parameter Shakingcited by 0