Error-Robust Distributed Denial of Service Attack Detection Based on an Average Common Feature Extraction Technique.

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.

Optimally tuned functionals improving the description of optical and electronic properties of the phthalocyanine molecule.

By means of Density functional theory and time-dependent density functional theory calculations, we present a comprehensive investigation on the influence of different functional schemes on electronic and optical properties of the phthalocyanine molecule. By carrying out our own tuning on the OT-LC-BLYP/6-31G(d,p) functional, we show that such a procedure is fundamental to accurately match experimental results. We compare our results to several others available in the literature, including the B3LYP/6-31+G(d,p) set, which is commonly portrayed as the best combination in order to obtain a good description of the band gap. The results obtained here present not only significant improvement of the optical properties from the conventional BLYP, but we can also objectively report an improvement of our tuned functional when compared to the current benchmark of the literature as far as optical properties are concerned. Particularly, by means of this approach, it was possible to achieve a good agreement between the theoretical and experimental optical gap as well as of the positioning of the main peaks in the absorption spectrum. Our results thus suggest that correcting the long-range term on exchange term of the Coulomb operator, by means of a tuning procedure, is a good option to accurately describe properties of the phthalocyanine molecule.