In recent years, advanced threats against Cyber–Physical Systems (CPSs), such as Distributed Denial of Service (DDoS) attacks, are increasing. Furthermore, traditional machine learning-based intrusion detection systems (IDSs) often fail to efficiently detect such attacks when corrupted datasets are used for IDS training. To face these challenges, this paper proposes a novel error-robust multidimensional technique for DDoS attack detection. By applying the well-known Higher Order Singular Value Decomposition (HOSVD), initially, the average value of the common features among instances is filtered out from the dataset. Next, the filtered data are forwarded to machine learning classification algorithms in which traffic information is classified as a legitimate or a DDoS attack. In terms of results, the proposed scheme outperforms traditional low-rank approximation techniques, presenting an accuracy of $98.94\%$, detection rate of $97.70\%$ and false alarm rate of $4.35\%$ for a dataset corruption level of $30\%$ with a random forest algorithm applied for classification. In addition, for error-free conditions, it is found that the proposed approach outperforms other related works, showing accuracy, detection rate and false alarm rate of $99.87\%$, $99.86\%$ and $0.16\%$, respectively, for the gradient boosting classifier.

Distributed Denial of Service (DDoS) attacks are one of the most challenging security threats, since a single victim is attacked by several compromised malicious nodes. As a consequence, legitimate end users can be prevented to access network resources. This letter proposes a noise-robust multilayer perceptron (MLP) architecture for DDoS attack detection trained with corrupted data. In the proposed approach, the average value of the common features among dataset instances is iteratively filtered out by applying Higher Order Singular Value Decomposition (HOSVD) based techniques. The effectiveness of the proposed architecture is validated through comparison with state-of-the-art methods.

This paper proposes a scheme for secure telecommunication based on chaotic oscillators and Lyapunov theory. The presence of internal and external disturbances to increase the robustness of the method is considered in Lyapunov design. Another advantage of the proposed approach lies in that only one control input is required for synchronization of the master system with the slave system, making it relatively easy for application. Additionally, implementation via analog circuits of the proposed model is performed to validate the theoretical analysis.

Safety-critical applications (SCA), such as autonomous driving, and liability critical applications (LCA), such as fisheries management, require a robust positioning system in demanding signal environments with coherent multipath. In this context, antenna array based Global Navigation Satellite Systems (GNSS) receivers with array signal processing schemes allow the spatial separation of line-of-sight (LOS) from multipath components. In this paper, we propose a Procrustes estimation and Khatri-Rao factorization (ProKRaft) filtering approach to separate the direction of arrival (DoA) and complex amplitude factor matrices, which are then used to filter the correlated code for each impinging component. Our scheme outperforms the Higher-Order Singular Value Decomposition (HOSVD) based eigenfilter approach, and the direction of arrival and Khatri-Rao (DoA/KRF) approaches, which are the state-of-the-art tensor based scheme for delay estimation.

Array signal processing schemes can provide accurate estimates for the number of received signal components and their direction of arrival (DoA) at a sensor array. This paper proposes a high resolution framework with multipath mitigation for detecting and locating a signal emitter randomly positioned within a region of interest. First our proposed framework detects the signal of interest and provides the number of line-of-sight (LOS) plus non-line-of-sight (NLOS) components by applying model order selection schemes. Next our approach mitigates the multipaths by exploiting the signal structure and estimating the DoA of each component. Finally, our framework triangulates the estimated DoAs providing the source position. Simulation results are compared to the well known time of arrival (ToA) and DoA based positioning systems illustrating the effectiveness of the proposed framework.