In this paper, non-orthogonal multiple access (NOMA) with successive interference cancellation (SIC) technique for downlink channel of next generation wireless network and its security issues are discussed. In NOMA, signals for all user equipment (UEs) are superimposed before transmission and then decoded at each UE implementing SIC. SIC relies on decoding and subtracting the signals in sequence until it reaches its desired signal. The decoding order at each UE, however, must match with the user index in the cancellation sequence. In case of mismatch, UEs will not obtain their signals and re-request their messages from the BS which will further increase the processing time that is already high for a regular SIC receiver. Numerical results show the performance of SIC at the UE side. The time spent for decoding the received signal at the UE with and without user mismatch is discussed. The unusual longer decoding times are further discussed as potential external network threat.

In this work, we emphasize the practical importance of mission-critical wireless sensor networks (WSNs) for structural health monitoring of industrial constructions. Due to its isolated and ad hoc nature, this type of WSN deployments is susceptible to a variety of malicious attacks that may disrupt the underlying crucial systems. Along these lines, we review and implement one such attack, named a broadcast storm, where an attacker is attempting to flood the network by sending numerous broadcast packets. Accordingly, we assemble a live prototype of said scenario with real-world WSN equipment, as well as measure the key operational parameters of the WSN under attack, including packet transmission delays and the corresponding loss ratios. We further develop a simple supportive mathematical model based on widely-adopted methods of queuing theory. It allows for accurate performance assessment as well as for predicting the expected system performance, which has been verified with statistical methods.

Subject of Research.The paper proposes an approach to the use of gradient boosted decision trees algorithm. For this purpose, CatBoost algorithm developed by Yandex is proposed. Its implementation is aimed at the problem solution of OS Linux software identification in order to reduce the number of system vulnerabilities, which occur due to the installation of unauthorized software by automated system users. We consider an approach to the program signatures formation and further training of CatBoostClassifier classifier model. The subsequent recognition task is set for the identified programs that were not previously involved in the model training process. Method. Free CatBoost software was used for implementation of the gradient boosted decision trees algorithm. CatBoostClassifier multi-classification model was created on its basis. The use of this model allows identifying test sample elf-files.Main Results. The training parameters of the classification model are selected. An experiment is carried out to identify elf-files with the use of ten different featuresof emerging signature programs. The results obtained in the new approach are compared with the results of the previously developed method of identification based on the application of the statistical criterion of Chi-square homogeneity at the significance level p = 0.01. Practical Relevance. The results of the study can be recommended to information security specialists for data media audit. The developed approach gives the possibility to identify violations of the established security policy in the processing of confidential information.

The research objective is to construct an adaptive model for modular machine learning structures that improves the processing quality of information sequences. The novelty of the proposed methodology is that it can identify segments of an information sequence obtained using various methods and assign models with the best quality indicator values to subsequences. Classical methods allow tuning of the model to the entire data sample. The improvement consists of the proposed solutions that consider the inverse problem of forming segments of data sequences, such that their properties correspond to the processing model. The proposed methodology was tested on various models and datasets. Segmentation and assignment of regression models with the best characteristics to individual segments allow the reduction of the mean square error (MSE) and mean absolute error (MAE) to 8%. The findings show an opportunity to increase of 5-8% for weak LR, SVM, and GR models, while strong DT, CNN, ANN, ANFIS, and XGBoost models improve by 1-4% in scenarios with limited data. Segmentation enables more efficient training and reduces sensitivity to noise and outliers. The proposed solution allows the selection of segmentation strategies and model combinations considering local data properties. Its application enables the implementation of existing machine learning architectures to improve the quality of training and analysis of information sequences and increase adaptability, scalability, and interpretability.