Research on the Internet of Things Device Recognition Based on RF-Fingerprinting

Tu, Ya; Zhang, Zhen; Li, Yibing; Wang, Chao; Xiao, Yao

doi:10.1109/access.2019.2904657

Cited by 45 publications

(11 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their experiment shows that frequencydomain features are more reliable than time-domain features. In [80] and [81], the time-domain statistical metrics and wavelet features of transmitters' turn-on transient signals are transformed into devices' RF fingerprints. Finally, it is notable that the authors in [82] capture the turn-on transient signal of Bluetooth devices and extract 13 time-frequency domain features (via Hibert-Huang spectrum) to construct devices' fingerprints.…”

Section: B Feature-based Statistical Learning For Specific Device Ide...mentioning

confidence: 99%

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

Liu

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

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. Noncryptographic 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.

show abstract

Section: B Feature-based Statistical Learning For Specific Device Ide...mentioning

confidence: 99%

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

Liu

Wang

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…G. Huang extracted amplifier nonlinearity characteristics [14] caused by power amplifier imperfections [15]. Some researchers use multiple features, which are cultivated from received signals [16] or robust principle component analyzed (RPCA) features [17] to improve accuracy. However, it must be pointed out that the performances of these hand-extracted features based methods are limited.…”

Section: A Device Identificationmentioning

confidence: 99%

Deep Open Set Identification for RF Devices

Wang¹,

Liu²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Artificial intelligence (AI) based device identification improves the security of the internet of things (IoT), and accelerates the authentication process. However, existing approaches rely on the assumption that we can learn all the classes from the training set, namely, closed-set classification. To overcome the closed-set limitation, we propose a novel open set RF device identification method to classify unseen classes in the testing set. First, we design a specific convolution neural network (CNN) with a short-time Fourier transforming (STFT) preprocessing module, which efficiently recognizes the differences of feature maps learned from various RF device signals. Then to generate a representation of known class bounds, we model the peripheral samples' distribution and revise CNN's output according to the extreme value theory (EVT). Finally, we estimate the probability map of the open-set via the OpenMax function.We conduct experiments on sampled data and voice signal sets, considering various pre-processing schemes, network structures, distance metrics, tail sizes, and openness degrees. The simulation results show the superiority of the proposed method in terms of robustness and accuracy.

show abstract

“…This image is called the constellation diagram. In the constellation diagram, although each sampling point is disturbed by noise, it will produce random disturbance [31]- [33]. However, if each signal sample is large, a large number of random samples will reflect the statistical characteristics of radio frequency signals on the constellation diagram.…”

Section: Contour Stella Imagementioning

confidence: 99%

Specific Emitter Identification Techniques for the Internet of Things

Sa¹,

Lang

Wang³

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Specific Emitter Identification (SEI) detects the individual emitter according its varied signal characteristics. The method operates in the physical layer of the internet and can effectively improve the security of the Internet of Things (IoT). Generally, SEI identifies the uniqueness of the transmitting platform by using the unintentional modulation information of the emitter such as radar, which has ''fingerprint'' characteristics. Existing SEI methods are based on hand-crafted features to distinguish different emitters. In this paper, traditional feature extraction methods are studied and a new recognition method is proposed. To determine the effectiveness of the method, the output signals of eight amplifiers are collected as the research object. The power spectrum characteristics and adjacent channel power ratio (ACPR) of the signal are then extracted and eight amplifiers are distinguished. Finally, the quadrature-phase signals are converted into pictures, and convolutional neural networks are used to automatically extract features for classification and recognition. The results show that the recognition rate of converting signals into pictures can reach 95%, when SNR is 20dB. INDEX TERMS Specific emitter identification, IoT, power amplifier.

show abstract

Research on the Internet of Things Device Recognition Based on RF-Fingerprinting

Cited by 45 publications

References 28 publications

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

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

Deep Open Set Identification for RF Devices

Specific Emitter Identification Techniques for the Internet of Things

Contact Info

Product

Resources

About