Deep learning based RF fingerprinting for device identification and wireless security

Abstract

RF fingerprinting is an emerging technology for identifying hardware-specific features of wireless transmitters and may find important applications in wireless security. In this study, the authors present a new RF fingerprinting scheme using deep neural networks. In particular, a long short-term memory based recurrent neural network is proposed and used for automatically identifying hardware-specific features and classifying transmitters. Experimental studies using identical RF transmitters showed very high detection accuracy in the presence of strong noise (signal-to-noise ratio as low as −12 dB) and demonstrated the effectiveness of the proposed scheme.Introduction: 'RF fingerprinting' generally refers to the process of identifying the unique characteristics of a wireless transmitter hardware imposed on the transmitted signals. RF fingerprinting can be used to effectively prevent node impersonation, in which legitimate security credentials are obtained by an adversary to compromise the security [1].Many hardware-dependent features have been explored for RF fingerprinting. These features exist due to variations in the manufacture process of wireless transmitters. These variations are small enough to meet the requirements of communication standards but allow for unique device-dependent features to be identified. Examples of such features include the turn-on transient phase of the signals [2, 3], power amplifier imperfections [4,5], magnitude and phase errors, I/Q dc offset [6], carrier frequency differences, phase offset, and second-order cyclostationary features [7], clock offset [8].Existing fingerprinting algorithms include white-list based algorithms and unsupervised learning based algorithms. The former requires legitimate devices to register and training a prior to setup a database for their feature space. The latter does not require such prior knowledge, and as such does not differentiate legitimate features from illegitimate ones. Both methods are useful in detecting and identifying spoofing. However, all existing works on RF fingerprinting depend on a set of human engineered features from various layers of the protocol stack [1]. In this work, we will demonstrate that deep neural networks can be used to effectively implement device identification with high accuracy through automatic learning of device-dependent RF fingerprints. In contrast to existing works, the proposed approach does not require human intervention in defining what features should be used in the RF fingerprinting process.

DSLN: Securing Internet of Things Through RF Fingerprint Recognition in Low-SNR Settings

“…(2) Short-term invariance: Unlike human beings who can remain their fingerprint features invariant throughout their lives, the components of wireless devices will inevitably face aging, and long-term use will lead the actual fingerprint features to be different from those registered in the fingerprint feature database. However, the aging of components takes a long time, so its impact on RF fingerprint features during a short period is relatively low [21]. The study in [21] shows that the RF fingerprint features extracted by a wireless network can remain unchanged within 5 months, and the device recognition rate is quite stable.…”

“…However, the aging of components takes a long time, so its impact on RF fingerprint features during a short period is relatively low [21]. The study in [21] shows that the RF fingerprint features extracted by a wireless network can remain unchanged within 5 months, and the device recognition rate is quite stable.…”

Radio Frequency Fingerprint Identification Based on Multi-Intervals Differential Constellation Trace Figures

“…But when faced with a large number of devices, such as large-scale wireless sensor networks, machine learning methods usually cannot achieve a high identification accuracy. As a very effective end-to-end learning method, deep learning has also been widely used in the RFF field recently [11,12,13]. Convolutional neural networks (CNN) is translation invariant and can learn spatial hierarchies of patterns [14,15].…”

Discriminative adversarial networks for specific emitter identification

“…In recent years, deep learning becomes increasingly attractive in SEI. Classical neural networks, such as long short-term memory [4] and convolutional neural networks (CNN) [5,6], have been investigated to extract features.…”