Blind Physical Layer Authentication over Fading Wireless Channels through Machine Learning

Senigagliesi, Linda; Cintioni, Lorenzo; Baldi, Marco; Gambi, Ennio

doi:10.1109/wifs47025.2019.9035105

Cited by 5 publications

(5 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, there is no limit for combining the available information in the interest of creating helpful datasets. Having said that, the datasets built on the basis of channel measurements are commonly used as the input data, e.g., see [22], [24], [25].…”

Section: A Traditional Datamentioning

confidence: 99%

“…As a further development, the authors of [23] suggest using estimated channel matrices for generating features and then compare four different ML algorithms, i.e., the k-NN, SVM, decision tree and bagged tree, in terms of their accuracy and prediction time. Similar to [73], the training data considered in [25] contains only a single class under the assumption that there is no knowledge concerning any of the potential adversary. Also assuming that the prior knowledge of the CSI of illegitimate devices is unavailable, Du et al [169] utilize a CART decision tree for designing an authenticator that is trained on CSI-based datasets for differentiating legitimate devices from illegitimate ones.…”

Section: The Application Of ML In Phy Securitymentioning

confidence: 99%

“…The authenticator in [169] was shown to reduce the dimension of the original datasets into lower-dimensional data for employment in industrial environments. In [25], single-class nearest neighbour classification is performed on the single-class data for finding both high-and low-density regions, thereby creating a predictive model for authentication. The authors of [27] propose a logistic regression model for authentication and estimate the coefficients of the model by using the popular Frank-Wolfe algorithm.…”

Section: The Application Of ML In Phy Securitymentioning

confidence: 99%

See 2 more Smart Citations

Physical Layer Authentication and Security Design in the Machine Learning Era

Hoang,

Vahid,

Tuan

et al. 2024

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

Security at the physical layer (PHY) is a salient research topic in wireless systems, and machine learning (ML) is emerging as a powerful tool for providing new data-driven security solutions. Therefore, the application of ML techniques to the PHY security is of crucial importance in the landscape of more and more data-driven wireless services. In this context, we first summarize the family of bespoke ML algorithms that are eminently suitable for wireless security. Then, we review the recent progress in ML-aided PHY security, where the term "PHY security" is classified into two different types: i) PHY authentication and ii) secure PHY transmission. Moreover, we treat NNs as special types of ML and present how to deal with PHY security optimization problems using NNs. Finally, we identify some major challenges and opportunities in tackling PHY security challenges by applying carefully tailored ML tools.

show abstract

Section: A Traditional Datamentioning

confidence: 99%

Section: The Application Of ML In Phy Securitymentioning

confidence: 99%

Section: The Application Of ML In Phy Securitymentioning

confidence: 99%

See 1 more Smart Citation

Physical Layer Authentication and Security Design in the Machine Learning Era

Hoang,

Vahid,

Tuan

et al. 2024

IEEE Commun. Surv. Tutorials

View full text Add to dashboard Cite

show abstract

“…As a further development, the authors of [19] suggest using estimated channel matrices for generating features and then compare four different ML algorithms, i.e., the k-NN, SVM, decision tree and bagged tree, in terms of their accuracy and prediction time. Similar to [71], the training data considered in [21] contains only a single class under the assumption that there is no knowledge concerning any of the potential eavesdropper. In [21], single-class nearest neighbour classification is performed on the single-class data for finding both high-and low-density regions, thereby creating a predictive model for authentication.…”

Section: B Recent Advances and Future Directionsmentioning

confidence: 99%

“…Similar to [71], the training data considered in [21] contains only a single class under the assumption that there is no knowledge concerning any of the potential eavesdropper. In [21], single-class nearest neighbour classification is performed on the single-class data for finding both high-and low-density regions, thereby creating a predictive model for authentication. The authors of [23] propose a logistic regression model for authentication and estimate the coefficients of the model by using the popular Frank-Wolfe algorithm.…”

Section: B Recent Advances and Future Directionsmentioning

confidence: 99%

Physical Layer Security: Detection of Active Eavesdropping Attacks by Support Vector Machines

et al. 2021

View full text Add to dashboard Cite

Security at the physical layer (PHY) is a salient research topic in wireless systems, and machine learning (ML) is emerging as a powerful tool for providing new data-driven security solutions. Therefore, the application of ML techniques to the PHY security is of crucial importance in the landscape of more and more data-driven wireless services. In this context, we first summarize the family of bespoke ML algorithms that are eminently suitable for wireless security. Then, we review the recent progress in ML-aided PHY security, where the term "PHY security" is classified into two different types: i) PHY authentication and ii) secure PHY transmission. Moreover, we treat neural networks as special types of ML and present how to deal with PHY security optimization problems using neural networks. Finally, we identify some major challenges and opportunities in tackling PHY security challenges by applying carefully tailored ML tools.

show abstract