LTE Device Identification Based on RF Fingerprint with Multi-Channel Convolutional Neural Network

Yin, Pengcheng; Peng, Linning; Zhang, Junqing; Liu, Ming; Fu, Hua; Hu, Aiqun

doi:10.1109/globecom46510.2021.9685067

Cited by 28 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [21], the multi-channel DCTF-based CNN demonstrated outstanding performance for LTE terminals. This inspired us to apply it to the 5G terminals.…”

Section: Multi-channel Dctf-based Cnn Structurementioning

confidence: 99%

“…These features are unique, persistent and resistant to cloning or tampering attempts, which can be considered the "fingerprint" of a device [2,9]. The research on RFF identification has covered a number of wireless communication systems, such as GSM [10], Wi-Fi [11][12][13][14][15], LoRa [16,17], ZigBee [2,18,19], RFID [20], LTE [21,22] and IEEE 802.11ad [23].…”

Section: Introductionmentioning

confidence: 99%

“…The authors of [10] classified the DCTFs of global system for mobile communications (GSM) phones using a CNN. The DCTF of a long-term evolution (LTE) mobile terminal was studied in [21], where the DCTF of a physical random access channel (PRACH) preamble was identified. In this work, the DCTF is divided into transient parts and steady state parts, and then a multi-channel CNN is used with each channel treated a part of the DCTF.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Radio Frequency Fingerprint Identification for 5G Mobile Devices Using DCTF and Deep Learning

Fu,

Dong,

Yin

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

The fifth-generation (5G) mobile cellular network is vulnerable to various security threats. Radio frequency fingerprint (RFF) identification is an emerging physical layer authentication technique which can be used to detect spoofing and distributed denial of service attacks. In this paper, the performance of RFF identification is studied for 5G mobile phones. The differential constellation trace figure (DCTF) is extracted from the physical random access channel (PRACH) preamble. When the database of all 64 PRACH preambles is available at the gNodeB (gNB), an index-based DCTF identification scheme is proposed, and the classification accuracy reaches 92.78% with a signal-to-noise ratio of 25 dB. Moreover, due to the randomness in the selection of preamble sequences in the random access procedure, when only a portion of the preamble sequences can be trained, a group-based DCTF identification scheme is proposed. The preamble sequences generated from the same root value are grouped together, and the untrained sequences can be identified based on the trained sequences within the same group. The classification accuracy of the group-based scheme is 89.59%. An experimental system has been set up using six 5G mobile phones of three models. The 5G gNB is implemented on the OpenAirInterface platform.

show abstract

“…In [21], the multi-channel DCTF-based CNN demonstrated outstanding performance for LTE terminals. This inspired us to apply it to the 5G terminals.…”

Section: Multi-channel Dctf-based Cnn Structurementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Radio Frequency Fingerprint Identification for 5G Mobile Devices Using DCTF and Deep Learning

Fu,

Dong,

Yin

et al. 2023

Entropy

Self Cite

View full text Add to dashboard Cite

show abstract

“…In [22], an efficient SEI method based on Complex Valued Neural Network (CVNN) and network compression is proposed, which can reduce the complexity and size of the model under the condition of ensuring the recognition accuracy, the complexity is 10%~30% of CVNN. In [23], a new multi-channel neural network for long-term evolution terminal identification is proposed, the DCTF they use is extracted from random access preamble for synchronization, this network uses multiple downsampling transformations to automatically perform multi-scale feature extraction and classification, thus eliminating the need for manual extraction of features, experiments were carried out in Line Of Sight(LOS) and Non LOS (NLOS) scenes to classify ZigBee devices. The classification accuracy rate was 97% in LOS scenes with SNR=30 dB or so.…”

Section: B Neural Network Classifiermentioning

confidence: 99%

Specific Emitter Identification of Frequency Hopping Signals Based on Feature Extraction and Deep Residual Network

Xie

Yang

et al. 2022

IEEE Access

View full text Add to dashboard Cite

In the modern war with complex and changeable electromagnetic environment, Specific Emitter Identification (SEI) is an important and difficult problem, which is of great significance in obtaining intelligence information, identifying ourselves or foe, and specifying combat plans. In order to solve the problems of low accuracy, poor robustness and difficulty in extracting effective individual features of frequency hopping (FH) radio set, this paper studies the generation of PSK signal constellation to proposes a radio frequency fingerprint(RFF) based on constellation. We also improved the existing RFF extraction method, combined with the deep learning recognition method based on the Deep Residual Network (ResNet), to achieve effective feature fusion. By comparing different input methods, we found that the recognition accuracy is improved, and reaches 96.16% in the outfield experiments of 15 FH radio sets. In addition, we also designed a ResNet structure to compare the recognition accuracy under different signal-to-noise ratio(SNR), different network structure, different number of individuals, different modulation methods and different recognition algorithms, which proved the superiority of our method.

show abstract

“…I N the era of fifth generation (5G) communications and beyond, wireless technology plays a key role in our everyday life [1]. However, the broadcast nature of wireless transmission makes device authentication challenging [2]. In particular, the spoofing attack caused by pseudo base station (BS) seriously disrupts the management of legitimate wireless Yilun Sun and Hongyi Luo are with the School of Cyber Science and Engineering, Southeast University, Nanjing 210096, China (e-mail: sunyilun@seu.edu.cn; hongyiluo@seu.edu.cn).…”

Section: Introductionmentioning

confidence: 99%

Location-Invariant Radio Frequency Fingerprint for Base Station Recognition

Sun

Luo

et al. 2023

IEEE Wireless Commun. Lett.

Self Cite

View full text Add to dashboard Cite

Pseudo base station (BS) is an illegal radio device that exploits the security vulnerabilities of fifth generation (5G) communications and then implements corresponding network attacks, such as spoofing attack. These malicious actions cause security and privacy threats and hinder the wide deployment of wireless access networks. To address these problems, efficient BS identification mechanisms are necessary. Radio frequency fingerprinting (RFF) and channel fingerprinting are potential solutions. Unfortunately, existing solutions are limited to be applicable to scenarios where the locations of pseudo BSs are fixed, while the emerging challenges brought by movable pseudo BSs can hardly be addressed by mature wireless security mechanisms. In this letter, we propose a signal echoing protocol (SEP) to reduce the influence on wireless channels and construct the locationinvariant RFF. When BS and user equipment (UE) communicate using SEP, UE can accurately estimate the channel to recognize different BSs. Numerical results demonstrate that the proposed scheme can reach a high classification accuracy for ten BSs, by 95.2% at the signal-noise ratio (SNR) of 25 dB.

show abstract

LTE Device Identification Based on RF Fingerprint with Multi-Channel Convolutional Neural Network

Cited by 28 publications

References 16 publications

Radio Frequency Fingerprint Identification for 5G Mobile Devices Using DCTF and Deep Learning

Radio Frequency Fingerprint Identification for 5G Mobile Devices Using DCTF and Deep Learning

Specific Emitter Identification of Frequency Hopping Signals Based on Feature Extraction and Deep Residual Network

Location-Invariant Radio Frequency Fingerprint for Base Station Recognition

Contact Info

Product

Resources

About