Generative Adversarial Network for Wireless Physical Layer Authentication

Version	Summary	Created by	Modification	Content Size	Created at	Operation
1		Reemah Mohammed Alhebshi	--	1193	2024-01-23 19:24:06	\|
2	layout	Camila Xu	Meta information modification	1193	2024-01-24 01:53:59	\|

This entry is adapted from the peer-reviewed paper 10.3390/s24020641

Wireless physical layer authentication has emerged as a promising approach to wireless security. The topic of wireless node classification and recognition has experienced significant advancements due to the rapid development of deep learning techniques. Ubiquitous technologies are experiencing significant growth, characterized by the development of several innovative systems, including smart vehicles, smart homes, smart cities and intelligent applications in industries and healthcare.

generative adversarial networks wireless physical layer authentication convolutional neural network

1. Introduction

Ubiquitous technologies are experiencing significant growth, characterized by the development of several innovative systems, including smart vehicles, smart homes, smart cities and intelligent applications in industries and healthcare. Emerging ubiquitous technologies, such as the Internet of Things (IoT), are significantly increasing the number of devices used. Furthermore, the German online platform Statista Inc. expects 17 billion IoT devices to be actively deployed by 2030 ^[1].

Due to the openness of wireless networks, practically every wireless-receiving device within a given range can receive signals, which creates serious network security issues because both authorized and unauthorized users can use the communication channel. However, the preservation of integrity, confidentiality and availability presents significant challenges in the context of wireless networks ^[2]. As a result of the broadcasting nature of wireless communications, authentication is a crucial problem ^[3]. To prevent malicious users and only allow authorized users to access a wireless network, device identity authentication is essential ^[4].

To effectively address these challenges, it is important to employ robust and highly efficient techniques to mitigate the risk of device impersonation. These techniques must be stable, regardless of environmental conditions or device movements. Wireless physical layer authentication (WPLA) is a promising approach that offers a comprehensive framework for addressing security concerns in wireless communication. It is an approach for identifying wireless transmitters by analyzing the physical layer features of transmissions ^[5].

With the continual development of artificial intelligence (AI) technologies, machine learning (ML) and deep learning (DL) have grown to influence various aspects of people’s daily lives. With great results in numerous challenging cognitive experiments, DL computing has steadily risen to become the most used computational approach for ML. Significantly, DL has surpassed other well-known ML approaches in several fields due to its superior data analysis capabilities and accuracy.

Due to DL’s excellent classification capabilities, deep neural networks (DNNs) perform exceptionally well for WPLA. Baldini et al. ^[6] used convolutional neural network (CNN) and recurrence plot techniques to develop classification approaches for the physical layer authentication challenge. To identify different devices by utilizing distinctive radio frequency fingerprints (RFFs), Aminuddin et al. ^[7] presented a methodology based on a CNN to secure wireless transmissions in wireless local area networks. Liao et al. ^[8] adopted DNNs, CNNs and convolutional preprocessing neural networks to perform physical layer authentication in industrial wireless sensor networks. Furthermore, some research has examined the relationship between the number of hidden layers and authentication rate and has discovered that authentication rate improves as the number of hidden layers increases. In contrast, Ma et al. ^[9] used long short-term memory as an effective classifier to determine authorized and unauthorized users and increase detection efficiency and accuracy through simulations under varied channel conditions.

2. Generative Adversarial Network-Based Data Augmentation for Enhancing Wireless Physical Layer Authentication

Davaslioglu and Sagduyu ^[10] introduced a new approach to spectrum augmentation using GANs. This approach effectively handles the inherent difficulties of applying ML classifiers in the cognitive radio domain. Generative adversarial learning is implemented to obtain and generate synthetic data samples, enhancing classifier accuracy via training data augmentation. Additionally, they demonstrated that the inclusion of high-fidelity training data in the retraining process of the classifier leads to improved accuracy in spectrum sensing. This improvement is comparable to the hypothetical scenario, where extra real data are available within the same spectrum environment. Gong et al. ^[11] proposed a framework for identifying specific emitters utilizing the InfoGAN approach. To enhance the quality of GANs, the proposed framework contains two additional inputs. The proposed framework involves the creation of an artificial RFF vector. This vector is generated using the histograms of bispectral information extracted from received signals. This synthetic RFF vector aims to improve the distinction between individual elements. Additionally, a structured multimodal latent vector is utilized. This latent vector incorporates prior knowledge of fading channel distributions and was designed to align with the characteristics of received signals. The proposed framework demonstrated an assessment score of 87% for the GAN generator. Truong and Yanushkevich ^[12] proposed an approach for synthesizing radar signals using GANs. Their research explored the application of GANs in the domain of one-dimensional radar signal data generation and augmentation, which has yet to be thoroughly studied. The approach intends to replicate simplified real scenarios in which suspects endeavor to obscure highly reflective objects underneath multiple layers of clothing. Training samples are used to train GANs to generate samples that closely match the training data distribution. This approach has presented encouraging outcomes in synthesizing indiscernible radar signal samples from training samples.

In the same context, Roy et al. ^[13] provided complete band spectrum simulations and emulation examples using GANs that are sufficiently realistic. In addition, they considered the need for signal synthesis to validate and show that such an approach was feasible, improve the algorithmic approach and quantify and prove its efficiency with current signal sets. Tang et al. ^[14] addressed the issue of limited labeled data. They looked into the potential of using GANs to effectively generate images to expand original datasets through data augmentation. The findings of this experiment suggest that the GAN-based data augmentation framework used in this study can potentially enhance CNN classification performance, resulting in accuracy improvement ranging from 0.1–6%. Castelli et al. ^[15] investigated using GANs to generate synthetic telecommunication data about Wi-Fi signal quality. Vanilla GANs and Wasserstein GAN architectures were employed in this study. According to the results of their experiment, both models can generate synthetic data whose distribution matches that of actual data. Additionally, they demonstrated that an ML classifier showed a limited ability to differentiate between actual and generated data, thus providing further evidence of the resilience of the GAN-based model.

Furthermore, He et al. ^[16] introduced a communication signal enhancement model to address environmental changes. They developed a model utilizing GANs, which includes an encoding–decoding structure based on convolutional layers. This model’s primary objective is to mitigate noise and interference in signals expeditiously. The experimental findings confirm that the proposed model provides greater efficacy in enhancing communication signals. Zhou et al. ^[17] developed a generic adversarial framework called the wireless signal enhancement GAN for wireless signal enhancement. Ablation studies were employed to demonstrate the value of each part of the objective’s function. Unlike the signal enhancement method, which learns noise distribution and interference characteristics and then removes them from the original signals, this generator learns the characteristics of signals in an adversarial manner. Patel et al. ^[18] suggested a data augmentation approach involving the utilization of conditional GANs for automatic modulation classification. Their objective was to utilize conditional GANs to produce high-quality labeled data using just a small quantity of initial data. This approach addresses the significant expenses and difficulties faced in acquiring wireless datasets. Through experimentation using an open-source dataset, they demonstrated that the suggested data augmentation approach can significantly enhance the performance of automatic modulation classification models.

References

Vailshery, L.S. Number of IoT Connected Devices Worldwide 2019–2030, by Vertical. Available online: https://www.statista.com/statistics/1194682/iot-connected-devices-vertically (accessed on 1 August 2023).
Zou, Y.; Zhu, J.; Wang, X.; Hanzo, L. A Survey on Wireless Security: Technical Challenges, Recent Advances, and Future Trends. Proc. IEEE 2016, 104, 1727–1765.
Xie, N.; Li, Z.; Tan, H. A Survey of Physical-Layer Authentication in Wireless Communications. IEEE Commun. Surv. Tutor. 2021, 23, 282–310.
Peng, L.; Hu, A.; Zhang, J.; Jiang, Y.; Yu, J.; Yan, Y. Design of a Hybrid RF Fingerprint Extraction and Device Classification Scheme. IEEE Internet Things J. 2019, 6, 349–360.
Wang, Q.; Li, H.; Zhao, D.; Chen, Z.; Ye, S.; Cai, J. Deep Neural Networks for CSI-Based Authentication. IEEE Access 2019, 7, 123026–123034.
Baldini, G.; Giuliani, R.; Dimc, F. Physical layer authentication of Internet of Things wireless devices using Convolutional Neural Networks and Recurrence Plots. Internet Technol. Lett. 2018, 2, e81.
Aminuddin, N.S.; Habaebi, M.H.; Yusoff, S.H.; Islam, M.R. Securing Wireless Communication Using RF Fingerprinting. In Proceedings of the 8th International Conference on Computer and Communication Engineering (ICCCE), Kuala Lumpur, Malaysia, 22–23 June 2021; pp. 63–67.
Liao, R.-F.; Wen, H.; Wu, J.; Pan, F.; Xu, A.; Jiang, Y.; Xie, F.; Cao, M. Deep-Learning-Based Physical Layer Authentication for Industrial Wireless Sensor Networks. Sensors 2019, 19, 2440.
Ma, T.; Hu, F.; Ma, M. A LSTM-Based Channel Fingerprinting Method for Intrusion Detection. In Proceedings of the IEEE 5th International Conference on Cryptography, Security and Privacy (CSP), Zhuhai, China, 8–10 January 2021; pp. 113–116.
Davaslioglu, K.; Sagduyu, Y.E. Generative Adversarial Learning for Spectrum Sensing. In Proceedings of the IEEE International Conference on Communications (ICC), Kansas City, MO, USA, 20–24 May 2018; pp. 1–6.
Gong, J.; Xu, X.; Lei, Y. Unsupervised Specific Emitter Identification Method Using Radio-Frequency Fingerprint Embedded InfoGAN. IEEE Trans. Inf. Forensics Sec. 2020, 15, 2898–2913.
Truong, T.; Yanushkevich, S. Generative Adversarial Network for Radar Signal Synthesis. In Proceedings of the International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary, 14–19 July 2019; Volume 15, pp. 1–7.
Roy, T.; O’Shea, T.; West, N. Generative Adversarial Radio Spectrum Networks. In Proceedings of the ACM Workshop on Wireless Security and Machine Learning (WiseML 2019), Miami, FL, USA, 14 May 2019; Association for Computing Machinery: New York, NY, USA, 2019; pp. 12–15.
Tang, B.; Tu, Y.; Zhang, Z.; Lin, Y. Digital Signal Modulation Classification with Data Augmentation Using Generative Adversarial Nets in Cognitive Radio Networks. IEEE Access 2018, 6, 15713–15722.
Castelli, M.; Manzoni, L.; Espindola, T.; Popovič, A.; De Lorenzo, A. Generative adversarial networks for generating synthetic features for Wi-Fi signal quality. PLoS ONE 2021, 16, e0260308.
He, S.; Zhu, L.; Yao, C.; Wang, L.; Qin, Z. A Novel Approach Based on Generative Adversarial Network for Signal Enhancement in Wireless Communications. Wirel. Commun. Mob. Comput. 2022, 8, 8008460.
Zhou, X.; Sun, Z.; Wu, H. Wireless signal enhancement based on generative adversarial networks. Ad Hoc Netw. 2020, 103, 1570–8705.
Mansi, P.; Xuyu, W.; Shiwen, M. Data augmentation with conditional GAN for automatic modulation classification. In Proceedings of the 2nd ACM Workshop on Wireless Security and Machine Learning (WiseML ’20), Linz, Austria, 13 July 2020; Association for Computing Machinery: New York, NY, USA, 2020; pp. 31–36.

© Text is available under the terms and conditions of the Creative Commons Attribution (CC BY) license; additional terms may apply. By using this site, you agree to the Terms and Conditions and Privacy Policy.

Upload a video for this entry

Information

Subjects: Computer Science, Cybernetics

Contributors MDPI registered users' name will be linked to their SciProfiles pages. To register with us, please refer to https://encyclopedia.pub/register :

Lamia Alhoraibi

Daniyal Alghazzawi

Reemah Alhebshi

View Times: 96

Update Date: 24 Jan 2024

Table of Contents

Video Upload Options

Confirm

1. Introduction

2. Generative Adversarial Network-Based Data Augmentation for Enhancing Wireless Physical Layer Authentication

References