mlsanityData to 14 Oct 2026

Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them

arXiv 2401.11723 ↗First posted 22 Jan 2024cs.CR cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

The advent of the Internet of Things (IoT) has brought forth an era of unprecedented connectivity, with an estimated 80 billion smart devices expected to be in operation by the end of 2025. These devices facilitate a multitude of smart applications, enhancing the quality of life and efficiency across various domains. Machine Learning (ML) serves as a crucial technology, not only for analyzing IoT-generated data but also for diverse applications within the IoT ecosystem. For instance, ML finds utility in IoT device recognition, anomaly detection, and even in uncovering malicious activities. This paper embarks on a comprehensive exploration of the security threats arising from ML's integration into various facets of IoT, spanning various attack types including membership inference, adversarial evasion, reconstruction, property inference, model extraction, and poisoning attacks. Unlike previous studies, our work offers a holistic perspective, categorizing threats based on criteria such as adversary models, attack targets, and key security attributes (confidentiality, availability, and integrity). We delve into the underlying techniques of ML attacks in IoT environment, providing a critical evaluation of their mechanisms and impacts. Furthermore, our research thoroughly assesses 65 libraries, both author-contributed and third-party, evaluating their role in safeguarding model and data privacy. We emphasize the availability and usability of these libraries, aiming to arm the community with the necessary tools to bolster their defenses against the evolving threat landscape. Through our comprehensive review and analysis, this paper seeks to contribute to the ongoing discourse on ML-based IoT security, offering valuable insights and practical solutions to secure ML models and data in the rapidly expanding field of artificial intelligence in IoT.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 152 of its 265 references that are in the map. First posted on arXiv 22 Jan 2024.

Builds on

152 of 265 references.

References · 152

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Deep Learning with Differential Privacycited by 2,728
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  8. 2020Extracting Training Data from Large Language Modelscited by 2,189
  9. 2016Adversarial examples in the physical worldcited by 1,769
  10. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  11. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
  12. 2019Deep Leakage from Gradientscited by 1,021
38 more
  1. 2016Adversarial Machine Learning at Scalecited by 936
  2. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  3. 2021Membership Inference Attacks From First Principlescited by 878
  4. 2018The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networkscited by 864
  5. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
  6. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  7. 2016Stealing Machine Learning Models via Prediction APIscited by 619
  8. 2017One pixel attack for fooling deep neural networkscited by 582
  9. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 520
  10. 2018Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networkscited by 519
  11. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  12. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 498
  13. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 493
  14. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  15. 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
  16. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  17. 2017Differentially Private Federated Learning: A Client Level Perspectivecited by 459
  18. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 397
  19. 2020Label-Only Membership Inference Attackscited by 388
  20. 2020iDLG: Improved Deep Leakage from Gradientscited by 382
  21. 2018Analyzing Federated Learning through an Adversarial Lenscited by 351
  22. 2020Weight Poisoning Attacks on Pre-trained Modelscited by 341
  23. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 334
  24. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  25. 2017Adversarial Attacks on Neural Network Policiescited by 320
  26. 2018Knockoff Nets: Stealing Functionality of Black-Box Modelscited by 292
  27. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  28. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  29. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  30. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  31. 2016Safety Verification of Deep Neural Networkscited by 263
  32. 2019Simple Black-box Adversarial Attackscited by 251
  33. 2021Enhanced Membership Inference Attacks against Machine Learning Modelscited by 248
  34. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 246
  35. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 246
  36. 2017Detecting Adversarial Samples from Artifactscited by 245
  37. 2017On Detecting Adversarial Perturbationscited by 232
  38. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 225

50 most cited of 152 All 152 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Robustness Analysis of Machine Learning Models for IoT Intrusion Detection Under Data Poisoning Attacks
  2. 2026Privacy-Preserving Machine Learning for IoT: A Cross-Paradigm Survey and Future Roadmap
  3. 2022Gotham Testbed: a Reproducible IoT Testbed for Security Experiments and Dataset Generation
  4. 2023Edge Learning for 6G-enabled Internet of Things: A Comprehensive Survey of Vulnerabilities, Datasets, and Defenses
  5. 2025LLM-based Multi-class Attack Analysis and Mitigation Framework in IoT/IIoT Networks
  6. 2026Online AutoML: Evaluating Poisoning Attacks on Cost-Utility Adversarial Training Defence Strategy for IoT Networks
  7. 2026Privacy-Preserving Distributed Learning in IoT Systems: A Unified Threat Model and Evaluation Framework
  8. 2022Machine Learning Security against Data Poisoning: Are We There Yet?