Online Learning Aided Adaptive Multiple Attribute-Based Physical Layer Authentication in Dynamic Environments

Yin, Xinyu; Fang, Xiaojie; Zhang, Ning; Yang, Peng; Sha, Xuejun; Qiu, Jinghui

doi:10.1109/tnse.2020.3013232

Cited by 9 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some efforts have been made to predict estimates for selecting channel attributes. An authenticator is used to monitor and save extracted features [37,38]. In previous research [39,40], a data-adaptive matrix in a deep learning structure was suggested for tracking changing attributes over time.…”

Section: Prior Art and Motivationmentioning

confidence: 99%

Intelligent Security Authentication for Connected and Autonomous Vehicles: Attacks and Defenses

Qiu,

Yu,

Jiang

et al. 2024

Electronics

View full text Add to dashboard Cite

The emergence of integrated positioning, communication, and sensing technologies has paved the way for a surge in connected and autonomous vehicles. The control system has been successful in reliable and fast transmission. However, practical applications face security risks, especially data tampering and spoofing attacks. To improve the resilience of the system against potential attacks, we attempt to leverage a generative adversarial network learning-assisted authentication framework (GAF). In addition to proposing a new method for validating vehicles, we also introduce a new architectural innovation in the generator–discriminator pair to achieve improved results. The generator sub-network is constructed using an advanced convolutional neural network, whereas the discriminator is designed to leverage global and local information to determine whether a signal is real or fake. On this basis, we propose a signal enhancement-based authentication method, a deep convolutional generative adversarial network (DCGAN). Experimental results using the National Institute of Standards and Technology (NIST) dataset show that the proposed method is effective in denoising and improving the detection performance.

show abstract

Section: Prior Art and Motivationmentioning

confidence: 99%

Intelligent Security Authentication for Connected and Autonomous Vehicles: Attacks and Defenses

Qiu,

Yu,

Jiang

et al. 2024

Electronics

View full text Add to dashboard Cite

show abstract

“…The authors in [25] present a learning algorithm for dynamic selection of physical layer attributes for PLS. Attributes are selected using authentication performance history of each attribute.…”

Section: Related Workmentioning

confidence: 99%

IRS-Assisted Physical Layer Security for 5G Enabled Industrial Internet of Things

et al. 2023

View full text Add to dashboard Cite

5G is a key enabler of Industrial Internet of Things (IIoT) that provides seamless connectivity between machines, sensors and computing servers. Security and privacy are major concerns for 5G enabled IIoT. Physical Layer Security (PLS) is a promising technique that can enhance the security of 5G enabled IIoT. In this paper, we present an IRS-assisted PLS scheme for 5G enabled IIoT that improves the weighted secrecy sum-rate (WSSR) of the industrial wireless network, where eavesdroppers are present around the facility. The key idea is to jointly optimize active and passive beamforming vectors to increase the secrecy rate at the user. To maximize WSSR, we use the stable matching algorithm that optimally assigns IRSs for secure data sharing between industrial units. Simulation results show that the proposed scheme enhances the WSSR performance by 40% and minimum secrecy rate by 25% as compared to the random and maximum weight matching schemes, respectively.

show abstract

“…However, the thresholds for the hypothesis test in [15] and [18] may not be always available in dynamic IoV environment. Consequently, several works exploiting the internal features of the CSI through ML approaches have been proposed [19], [20], [21], [22]. Both Yin et al [19] and Fang et al [20] utilized multiple physical layers attributes jointly to provide robust ML-based authentication in the IoV environment.…”

Section: A Developments and Limitations Of The Existing Plamentioning

confidence: 99%

“…Consequently, several works exploiting the internal features of the CSI through ML approaches have been proposed [19], [20], [21], [22]. Both Yin et al [19] and Fang et al [20] utilized multiple physical layers attributes jointly to provide robust ML-based authentication in the IoV environment. In [19], the attributes are chosen according to their past authentication performance while in [20], a kernel fusion machine is designed to deal with the multiple attributes without requiring the previous knowledge of their statistical properties.…”

Section: A Developments and Limitations Of The Existing Plamentioning

confidence: 99%

“…Both Yin et al [19] and Fang et al [20] utilized multiple physical layers attributes jointly to provide robust ML-based authentication in the IoV environment. In [19], the attributes are chosen according to their past authentication performance while in [20], a kernel fusion machine is designed to deal with the multiple attributes without requiring the previous knowledge of their statistical properties. Moreover, Chen et al [21] proposed a convolutional neural network-based authentication and data augmentation approach named triple pool network (TP-Net) for an edge computing system.…”

Section: A Developments and Limitations Of The Existing Plamentioning

confidence: 99%

See 1 more Smart Citation

Physical Layer Authentication in the Internet of Vehicles based on Signal Propagation Attribute Prediction

Umar¹,

Wang²,

Liu³

et al. 2023

J-NaNA

View full text Add to dashboard Cite

Physical layer authentication (PLA) has emerged as a promising alternative to complex cryptographic-based authentication schemes, especially for the Internet of Vehicles (IoV) scenarios with resource-limited onboard units (OBUs). However, the existing PLA schemes securing the IoV against GPS location spoofing/falsification attacks consider only insider attackers. Moreover, they cannot be used by mobile vehicles to validate GPS locations. To address these issues, this paper proposes a PLA scheme based on the Gaussian process (GP) path loss prediction, where channel state information (CSI) is used to track the variation of the channel characteristics and predict the next legitimate path loss (PL) of the signal from a transmitter for authentication. The key ideas in the proposed scheme are to first establish a mapping between the historical CSI attributes and PL features of the transmitter’s signal and use this mapping to predict the next PL, which is then used to cross-verify the transmitter’s reported location information. Extensive simulation experiments are conducted using generated radio channel characteristics from the quasideterministic radio channel generator (QuaDRiGa) to demonstrate the effectiveness of the proposed approach. The results of the experiments show that our system efficiently addressed the limitations of the existing works and improves the authentication performance in IoV environments.

show abstract

Online Learning Aided Adaptive Multiple Attribute-Based Physical Layer Authentication in Dynamic Environments

Cited by 9 publications

References 29 publications

Intelligent Security Authentication for Connected and Autonomous Vehicles: Attacks and Defenses

Intelligent Security Authentication for Connected and Autonomous Vehicles: Attacks and Defenses

IRS-Assisted Physical Layer Security for 5G Enabled Industrial Internet of Things

Physical Layer Authentication in the Internet of Vehicles based on Signal Propagation Attribute Prediction

Contact Info

Product

Resources

About