Multi-Binary Classifiers Using Optimal Feature Selection for Memory-Saving Intrusion Detection Systems

With the rise of remote work and the digital industry,advanced cyberattacks have become more diverse and complex in terms of attack types and characteristics,rendering them difficult to detect with conventional intrusion detection methods.Signature-based intrusion detection methods can be used to detect attacks;however,they cannot detect new malware.Endpoint detection and response(EDR)tools are attracting attention as a means of detecting attacks on endpoints in real-time to overcome the limitations of signature-based intrusion detection techniques.However,EDR tools are restricted by the continuous generation of unnecessary logs,resulting in poor detection performance and memory efficiency.Machine learning-based intrusion detection techniques for responding to advanced cyberattacks are memory intensive,using numerous features;they lack optimal feature selection for each attack type.To overcome these limitations,this study proposes a memory-efficient intrusion detection approach incorporating multi-binary classifiers using optimal feature selection.The proposed model detects multiple types of malicious attacks using parallel binary classifiers with optimal features for each attack type.The experimental results showed a 2.95%accuracy improvement and an 88.05%memory reduction using only six features compared to a model with 18 features.Furthermore,compared to a conventional multi-classification model with simple feature selection based on permutation importance,the accuracy improved by 11.67%and the memory usage decreased by 44.87%.The proposed scheme demonstrates that effective intrusion detection is achievable with minimal features,making it suitable for memory-limited mobile and Internet of Things devices.

Hemodynamic Response Detection Using Integrated EEG-fNIRS-VPA for BCI

For BCI systems,it is important to have an accurate and less complex architecture to control a device with enhanced accuracy.In this paper,a novel methodology for more accurate detection of the hemodynamic response has been developed using a multimodal brain-computer interface(BCI).An integrated classifier has been developed for achieving better classification accuracy using two modalities.An integrated EEG-fNIRS-based vector-phase analysis(VPA)has been conducted.An open-source dataset collected at the TechnischeUniversit鋞Berlin,including simultaneous electroencephalography(EEG)and functional near-infrared spectroscopy(fNIRS)signals of 26 healthy participants during n-back tests,has been used for this research.Instrumental and physiological noise removal has been done using preprocessing techniques followed by individually detecting activity in both modalities.With resting state threshold circle,VPA has been used to detect a hemodynamic response in fNIRS signals,whereas phase plots for EEG signals have been constructed using Hilbert Transform to detect the activity in each trial.Multiple threshold circles are drawn in the vector plane,where each circle is drawn after task completion in each trial of EEG signal.Finally,both processes are integrated into one vector-phase plot to get combined detection of hemodynamic response for activity.Results of this study illustrate that the combined EEG-fNIRS VPA yields considerably higher average classification accuracy,that is 91.35%,as compared to other classifiers such as support vector machine(SVM),convolutional neural networks(CNN),deep neural networks(DNN)and VPA(with dual-threshold circles)with classification accuracies 82%,89%,87%and 86%respectively.Outcomes of this research demonstrate that improved classification performance can be feasibly achieved using multimodal VPA for EEG-fNIRS hybrid data.

The History, Trend, Types, and Mitigation of Distributed Denial of Service Attacks

Over time, the world has transformed digitally and there is total dependence on the internet. Many more gadgets are continuously interconnected in the internet ecosystem. This fact has made the Internet a global information source for every being. Despite all this, attacker knowledge by cybercriminals has advanced and resulted in different attack methodologies on the internet and its data stores. This paper will discuss the origin and significance of Denial of Service (DoS) and Distributed Denial of Service (DDoS). These kinds of attacks remain the most effective methods used by the bad guys to cause substantial damage in terms of operational, reputational, and financial damage to organizations globally. These kinds of attacks have hindered network performance and availability. The victim’s network is flooded with massive illegal traffic hence, denying genuine traffic from passing through for authorized users. The paper will explore detection mechanisms, and mitigation techniques for this network threat.

Aeroengine Fault Diagnosis Method Based on Optimized Supervised Kohonen Network

To diagnose the aeroengine faults accurately,the supervised Kohonen(S-Kohonen)network is proposed for fault diagnosis.Via adding the output layer behind competitive layer,the network was modified from the unsupervised structure to the supervised structure.Meanwhile,the hybrid particle swarm optimization(H-PSO)was used to optimize the connection weights,after using adaptive inheritance mode(AIM)based on the elite strategy,and adaptive detecting response mechanism(ADRM),HPSO could guide the particles adaptively jumping out of the local solution space,and ensure obtaining the global optimal solution with higher probability.So the optimized S-Kohonen network could overcome the problems of non-identifiability for recognizing the unknown samples,and the non-uniqueness for classification results existing in traditional Kohonen(T-Kohonen)network.The comparison study on the GE90 engine borescope image texture feature recognition is carried out,the research results show that:the optimized S-Kohonen network has a strong ability of practical application in the classification fault diagnosis;the classification accuracy is higher than the common neural network model.

An Attack Modeling Based on Colored Petri Net

A color petri net (CPN) based attack modeling approach is addressed. Compared with graph-based modeling, CPN based attack model is flexible enough to model Internet intrusions, because of their static and dynamic features. The processes and rules of building CPN based attack model from attack tree are also presented. In order to evaluate the risk of intrusion, some cost elements are added to CPN based attack modeling. This extended model is useful in intrusion detection and risk evaluation. Experiences show that it is easy to exploit CPN based attack modeling approach to provide the controlling functions, such as intrusion response and intrusion defense. A case study given in this paper shows that CPN based attack model has many unique characters which attack tree model hasn’t.

Electromagneto-mechanical fields of giant magnetostrictive/piezoelectric laminates under concentrated load

This paper presents the nonlinear electromagneto-mechanical behavior of magnetostrictive/piezoelectric laminates under three-point bending both numerically and experimentally.The laminates are fabricated using thin Terfenol-D and PZT layers.The three-point bending test was conducted on the Terfenol-D/PZT laminates,and the displacement,induced magnetic field and induced voltage due to mechanical loads were measured.Three-dimensional finite element analysis was also carried out,and the electromagneto-mechanical fields in the laminates were predicted by introducing a second-order magnetoelastic constant for Terfenol-D.Comparison was then made between simulation and experiment.