RF Fingerprinting-Based IoT Node Authentication Using Mahalanobis Distance Correlation Theory

Nguyen, Dinh Duc Nha; Sood, Keshav; Nosouhi, Mohammad Reza; Xiang, Yong; Gao, Longxiang; Chi, Lianhua

doi:10.1109/lnet.2022.3167665

Cited by 10 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As the sampling frequency of PMU is not synchronous with SCADA data, so it is necessary to unify the two types of data under the same snapshot when combining them [17] . In this paper, the calculation method of optimal buffer length for PMU is used based on Mahalanobis distance [21]- [22] . All PMU measurement points are treated as a whole, so that the buffer length of each PMU measurement point is the same.…”

Section: Bthe Optimal Buffer Length Calculation Methods Based On the ...mentioning

confidence: 99%

Robust State Estimation Method Based on Mahalanobis Distance Under Non-Gauss Noise

Zhang,

Xu,

Xie

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Under non-Gauss noise condition, the performance of traditional state estimation methods based on Gauss measurement noise will be greatly reduced. In order to solve this problem, a robust state estimation method based on Mahalanobis distance under non-Gauss noise is proposed in this paper. First of all, based on the Mahalanobis distance, the calculation method of optimal buffer length for PMU measurements is used, which can unify the SCADA measurements with PMU measurements in the same snapshot. Then, Based on the two-stage processing method, in the first stage, the SCADA measurements are used for filtering by using maximum likelihood estimator to obtain the estimated values, and then the estimated values in the first-stage are combined with PMU measurements as the second-stage measurements for filtering, and finally the final results are obtained. Based on the IEEE-39 buses system and IEEE-118 buses system, under Gaussian noise and non-Gaussian noise, the AEE results of proposed method are very small, and which are all within 10 -3 , numerical tests under different simulation conditions verified the robustness and effectiveness.INDEX TERMS Non-Gauss noise; optimal buffer length; two-stage; maximum likelihood estimator; state estimation.

show abstract

Section: Bthe Optimal Buffer Length Calculation Methods Based On the ...mentioning

confidence: 99%

Robust State Estimation Method Based on Mahalanobis Distance Under Non-Gauss Noise

Zhang,

Xu,

Xie

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Anomaly detection has been addressed using different approaches namely multivariate statistical methods (e.g., Hoteling, Mahalanobis distance) [29], [30], variational autoencoders (VAE) [31], [32], Bayesian neural networks (BNN) [33], [34], ensemble learning [17], [35], among others. An extensive survey of the different methods for anomaly detection is found in [36].…”

Section: Anomaly Detectionmentioning

confidence: 99%

“…Sun et al [29] propose using a confidence region to diagnose heart diseases using a Gaussian mixture model and the Mahalanobis distance. Nguyen et al [30] use the Mahalanobis distance and Chi-square distribution for IoT node authentication by setting a cut-off value in the Chi-square distribution to identify non-legitimate nodes. Cao et al [12] propose using clustering, a sub-region CVA, and Hoteling to identify faults.…”

Section: Anomaly Detectionmentioning

confidence: 99%

Anomaly Detection Using Ensemble Classification and Evidence Theory

et al. 2023

View full text Add to dashboard Cite

Multi-class ensemble classification remains a popular focus of investigation within the research community. The popularization of cloud services has sped up their adoption due to the ease of deploying large-scale machine-learning models. It has also drawn the attention of the industrial sector because of its ability to identify common problems in production. However, there are challenges to conform an ensemble classifier, namely a proper selection and effective training of the pool of classifiers, the definition of a proper architecture for multi-class classification, and uncertainty quantification of the ensemble classifier. The robustness and effectiveness of the ensemble classifier lie in the selection of the pool of classifiers, as well as in the learning process. Hence, the selection and the training procedure of the pool of classifiers play a crucial role. An (ensemble) classifier learns to detect the classes that were used during the supervised training. However, when injecting data with unknown conditions, the trained classifier will intend to predict the classes learned during the training. To this end, the uncertainty of the individual and ensemble classifier could be used to assess the learning capability. We present a novel approach for anomaly detection using ensemble classification and evidence theory. A pool selection strategy is presented to build a solid ensemble classifier. We present an architecture for multi-class ensemble classification and an approach to quantify the uncertainty of the base classifiers and the ensemble classifier. We address the problem of detecting unknown conditions (while feeding out-of-distribution data), presenting a novel approach that monitors the uncertainty of the ensemble classifier using evidence theory. Finally, we use the benchmark Tennessee Eastman to perform experiments to test the ensemble classifier's prediction and anomaly detection capabilities.

show abstract

“…Considering the open nature of wireless vehicular communication, VANETs are susceptible to passive and active attacks such as interception, fabrication, and modification [3]. These attacks can be avoided by authenticating the received message to determine the legitimacy of the sender [4]. Generally, a VANET architecture involves a trusted authority (TA), roadside units (RSUs), and vehicles' wireless communication devices known as "onboard units" (OBUs) [3].…”

Section: Introductionmentioning

confidence: 99%

Efficient Blockchain-Based Group Key Distribution for Secure Authentication in VANETs

et al. 2023

View full text Add to dashboard Cite

This paper proposes a group key distribution scheme using smart contract-based blockchain technology. The smart contract's functions allow for securely distributing the group session key, following the initial legitimacy detection using public key infrastructure-based authentication. For message authentication, we propose a lightweight symmetric key cryptographybased group signature method, supporting the security and privacy requirements of vehicular ad hoc networks (VANETs). Our discussion examined the scheme's robustness against typical adversarial attacks. To evaluate the gas costs associated with smart contract's functions, we implemented it on the Ethereum main network. Finally, comprehensive analyses of computation and communication costs demonstrate the scheme's effectiveness.

show abstract

RF Fingerprinting-Based IoT Node Authentication Using Mahalanobis Distance Correlation Theory

Cited by 10 publications

References 15 publications

Robust State Estimation Method Based on Mahalanobis Distance Under Non-Gauss Noise

Robust State Estimation Method Based on Mahalanobis Distance Under Non-Gauss Noise

Anomaly Detection Using Ensemble Classification and Evidence Theory

Efficient Blockchain-Based Group Key Distribution for Secure Authentication in VANETs

Contact Info

Product

Resources

About