mlsanityData to 7 Oct 2026

Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap

arXiv 2603.13570 ↗First posted 13 Mar 2026cs.LG cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

The rapid proliferation of the Internet of Things has intensified demand for robust privacy-preserving machine learning mechanisms to safeguard sensitive data generated by large-scale, heterogeneous, and resource-constrained devices. Unlike centralized environments, IoT ecosystems are inherently decentralized, bandwidth-limited, and latency-sensitive, exposing privacy risks across sensing, communication, and distributed training pipelines. These characteristics render conventional anonymization and centralized protection strategies insufficient for practical deployments. This survey presents a comprehensive IoT-centric, cross-paradigm analysis of privacy-preserving machine learning. We introduce a structured taxonomy spanning perturbation-based mechanisms such as differential privacy, distributed paradigms such as federated learning, cryptographic approaches including homomorphic encryption and secure multiparty computation, and generative synthesis techniques based on generative adversarial networks. For each paradigm, we examine formal privacy guarantees, computational and communication complexity, scalability under heterogeneous device participation, and resilience against threats including membership inference, model inversion, gradient leakage, and adversarial manipulation. We further analyze deployment constraints in wireless IoT environments, highlighting trade-offs between privacy, communication overhead, model convergence, and system efficiency within next-generation mobile architectures. We also consolidate evaluation methodologies, summarize representative datasets and open-source frameworks, and identify open challenges including hybrid privacy integration, energy-aware learning, privacy-preserving large language models, and quantum-resilient machine learning.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 89 of its 258 references that are in the map. First posted on arXiv 13 Mar 2026.

Builds on

89 of 258 references.

References · 89

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  6. 2019Advances and Open Problems in Federated Learningcited by 3,021
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2016Deep Learning with Differential Privacycited by 2,682
  9. 2017Improved Training of Wasserstein GANscited by 2,223
  10. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  11. 2020Extracting Training Data from Large Language Modelscited by 2,144
  12. 2019Deep Leakage from Gradientscited by 1,004
38 more
  1. 2021Membership Inference Attacks From First Principlescited by 839
  2. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  3. 2019Modeling Tabular data using Conditional GANcited by 695
  4. 2023Time-LLM: Time Series Forecasting by Reprogramming Large Language Modelscited by 680
  5. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  6. 2016Federated Optimization: Distributed Machine Learning for On-Device Intelligencecited by 558
  7. 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 528
  8. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  9. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 451
  10. 2020Flower: A Friendly Federated Learning Research Frameworkcited by 449
  11. 2020Reliable Fidelity and Diversity Metrics for Generative Modelscited by 425
  12. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 375
  13. 2020iDLG: Improved Deep Leakage from Gradientscited by 367
  14. 2017Real-valued (Medical) Time Series Generation with Recurrent Conditional GANscited by 329
  15. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  16. 2020SplitFed: When Federated Learning Meets Split Learningcited by 308
  17. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  18. 2014RAPPOR: Randomized Aggregatable Privacy-Preserving Ordinal Responsecited by 262
  19. 2019Can You Really Backdoor Federated Learning?cited by 250
  20. 2021Federated Learning for Internet of Things: A Comprehensive Surveycited by 247
  21. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  22. 2018Machine Learning with Membership Privacy using Adversarial Regularizationcited by 177
  23. 2018PRADA: Protecting against DNN Model Stealing Attackscited by 159
  24. 2017A Survey on Homomorphic Encryption Schemes: Theory and Implementationcited by 154
  25. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 150
  26. 2020A Survey of Privacy Attacks in Machine Learningcited by 143
  27. 2019Reconstruction and Membership Inference Attacks against Generative Modelscited by 122
  28. 2020DP-CGAN: Differentially Private Synthetic Data and Label Generationcited by 118
  29. 2019Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learningcited by 117
  30. 2019Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbationscited by 115
  31. 2023Large Models for Time Series and Spatio-Temporal Data: A Survey and Outlookcited by 109
  32. 2023Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibrationcited by 90
  33. 2020FedGAN: Federated Generative Adversarial Networks for Distributed Datacited by 89
  34. 2018Privacy Preserving Machine Learning: Threats and Solutionscited by 78
  35. 2020Local and Central Differential Privacy for Robustness and Privacy in Federated Learningcited by 72
  36. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  37. 2020DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environmentscited by 57
  38. 2018Privacy-preserving Predictioncited by 48

50 most cited of 89 All 89 (JSON)

Built on by

Not cited yet.