mlsanityData to 14 Oct 2026

Machine Learning for the Detection and Identification of Internet of Things (IoT) Devices: A Survey

arXiv 2101.10181 ↗First posted 25 Jan 2021cs.CR cs.AI cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

The Internet of Things (IoT) is becoming an indispensable part of everyday life, enabling a variety of emerging services and applications. However, the presence of rogue IoT devices has exposed the IoT to untold risks with severe consequences. The first step in securing the IoT is detecting rogue IoT devices and identifying legitimate ones. Conventional approaches use cryptographic mechanisms to authenticate and verify legitimate devices' identities. However, cryptographic protocols are not available in many systems. Meanwhile, these methods are less effective when legitimate devices can be exploited or encryption keys are disclosed. Therefore, non-cryptographic IoT device identification and rogue device detection become efficient solutions to secure existing systems and will provide additional protection to systems with cryptographic protocols. Non-cryptographic approaches require more effort and are not yet adequately investigated. In this paper, we provide a comprehensive survey on machine learning technologies for the identification of IoT devices along with the detection of compromised or falsified ones from the viewpoint of passive surveillance agents or network operators. We classify the IoT device identification and detection into four categories: device-specific pattern recognition, Deep Learning enabled device identification, unsupervised device identification, and abnormal device detection. Meanwhile, we discuss various ML-related enabling technologies for this purpose. These enabling technologies include learning algorithms, feature engineering on network traffic traces and wireless signals, continual learning, and abnormality detection.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 51 of its 235 references that are in the map. First posted on arXiv 25 Jan 2021.

Builds on

51 of 235 references.

References · 51

  1. 2016Overcoming catastrophic forgetting in neural networkscited by 4,787
  2. 2015Learning both Weights and Connections for Efficient Neural Networkscited by 2,031
  3. 2018DARTS: Differentiable Architecture Searchcited by 1,798
  4. 2018Continual Lifelong Learning with Neural Networks: A Reviewcited by 1,330
  5. 2017Continual Learning with Deep Generative Replaycited by 1,158
  6. 2018MnasNet: Platform-Aware Neural Architecture Search for Mobilecited by 943
  7. 2017Lifelong Learning with Dynamically Expandable Networkscited by 694
  8. 2015Towards Open Set Deep Networkscited by 538
  9. 2017Progressive Neural Architecture Searchcited by 487
  10. 2018A Survey on Deep Transfer Learningcited by 419
  11. 2019NAS-Bench-101: Towards Reproducible Neural Architecture Searchcited by 344
  12. 2016Designing Neural Network Architectures using Reinforcement Learningcited by 279
38 more
  1. 2019Searching for A Robust Neural Architecture in Four GPU Hourscited by 260
  2. 2016Dynamic Network Surgery for Efficient DNNscited by 233
  3. 2019Progressive Differentiable Architecture Search: Bridging the Depth Gap between Search and Evaluationcited by 230
  4. 2016Deep Predictive Coding Networks for Video Prediction and Unsupervised Learningcited by 204
  5. 2016Learning the Number of Neurons in Deep Networkscited by 69
  6. 2018N-BaIoT: Network-based Detection of IoT Botnet Attacks Using Deep Autoencoderscited by 67
  7. 2016AdaNet: Adaptive Structural Learning of Artificial Neural Networkscited by 54
  8. 2018A Survey of Machine and Deep Learning Methods for Internet of Things (IoT) Securitycited by 42
  9. 2016IoT Sentinel: Automated Device-Type Identification for Security Enforcement in IoTcited by 30
  10. 2019Deep Learning for RF Signal Classification in Unknown and Dynamic Spectrum Environmentscited by 28
  11. 2018ORACLE: Optimized Radio clAssification through Convolutional neuraL nEtworkscited by 27
  12. 2019Towards Automated Machine Learning: Evaluation and Comparison of AutoML Approaches and Toolscited by 25
  13. 2019Generative Adversarial Network for Wireless Signal Spoofingcited by 21
  14. 2019Evolutionary Neural AutoML for Deep Learningcited by 20
  15. 2018Distributed Anomaly Detection using Autoencoder Neural Networks in WSN for IoTcited by 16
  16. 2019DeepRadioID: Real-Time Channel-Resilient Optimization of Deep Learning-based Radio Fingerprinting Algorithmscited by 12
  17. 2019Security of the Internet of Things: Vulnerabilities, Attacks and Countermeasurescited by 12
  18. 2017Machine Learning Approach to RF Transmitter Identificationcited by 11
  19. 2020Counter-Unmanned Aircraft System(s) (C-UAS): State of the Art, Challenges and Future Trendscited by 11
  20. 2015Wireless Physical-Layer Identification: Modeling and Validationcited by 10
  21. 2020Zero-Bias Deep Learning for Accurate Identification of Internet of Things (IoT) Devicescited by 10
  22. 2017Detection of Unauthorized IoT Devices Using Machine Learning Techniquescited by 8
  23. 2018RF-PUF: Enhancing IoT Security through Authentication of Wireless Nodes using In-situ Machine Learningcited by 7
  24. 2019Transmitter Classification With Supervised Deep Learningcited by 7
  25. 2019Complex-valued neural networks for machine learning on non-stationary physical datacited by 7
  26. 2019Micro Air Vehicle Link (MAVLink) in a Nutshell: A Surveycited by 7
  27. 2018SAIFE: Unsupervised Wireless Spectrum Anomaly Detection with Interpretable Featurescited by 6
  28. 2020IoT Device Identification Using Deep Learningcited by 6
  29. 2016Detecting Unseen Falls from Wearable Devices using Channel-wise Ensemble of Autoencoderscited by 5
  30. 2018Deep Predictive Coding Neural Network for RF Anomaly Detection in Wireless Networkscited by 5
  31. 2019Verifying and Monitoring IoTs Network Behavior using MUD Profilescited by 5
  32. 2019Robust Wireless Fingerprinting via Complex-Valued Neural Networkscited by 5
  33. 2017Wi-Fi CSI based Behavior Recognition: From Signals, Actions to Activitiescited by 4
  34. 2018Deep Learning Based Transmitter Identification using Power Amplifier Nonlinearitycited by 4
  35. 2019Radio Frequency Fingerprint Identification Based on Denoising Autoencoderscited by 4
  36. 2020IoT Behavioral Monitoring via Network Traffic Analysiscited by 4
  37. 2019FID: Function Modeling-based Data-Independent and Channel-Robust Physical-Layer Identificationcited by 3
  38. 2019Deep Complex Networks for Protocol-Agnostic Radio Frequency Device Fingerprinting in the Wildcited by 3

50 most cited of 51 All 51 (JSON)

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 3; 2023: 1; 2024: 1; 2025: 2.

9 papers.

  1. 2021Class-Incremental Learning for Wireless Device Identification in IoTcited by 9
  2. 2021Zero-bias Deep Neural Network for Quickest RF Signal Surveillancecited by 2
  3. 2023NoiseCAM: Explainable AI for the Boundary Between Noise and Adversarial Attackscited by 2
  4. 2022Adversarial attacks and defenses on ML- and hardware-based IoT device fingerprinting and identificationcited by 1
  5. 2025What's on My Network? Using Large Language Models to Identify Real-World IoT Devices at Scalecited by 1
  6. 2022Efficient Adaptive Federated Optimization of Federated Learning for IoTcited by 0
  7. 2022A Lightweight Transmission Parameter Selection Scheme Using Reinforcement Learning for LoRaWANcited by 0
  8. 2024Leveraging Machine Learning for Accurate IoT Device Identification in Dynamic Wireless Contextscited by 0
  9. 2025Smart Surveillance: Identifying IoT Device Behaviours using ML-Powered Traffic Analysiscited by 0