Covert Channels Detection with Supported Vector Machine and Hyperbolic Hopfield Neural Network

A mechanism that is intended to expose information against a security violation in a network is the use of network covert channel and it is difficult to detect information about data loss like location of loss using network covert channel. To identify the covert channel were the data pattern missing over the sharing of resources in networks. Several mechanisms are used to identify a large variation of covert channels. However, those mechanisms have more limitation like speed of detection, detection accuracy etc. In this paper, a new machine learning approaches called “Support Vector Machine and Hyperbolic Hopfield Neural Network” to overcome the drawbacks of existing methods. This approach is supported to classifying the different covert channels with data packets which is shared in networks and its supports to identifying the location of data loss or data pattern mismatched. Finally, the proposed methods properly detected covert channels with high accuracy and less detection high speed shared a network resources in effective manner.

Download Full-text

Random Forest Regressor-Based Approach for Detecting Fault Location and Duration in Power Systems

Sensors ◽

10.3390/s22020458 ◽

2022 ◽

Vol 22 (2) ◽

pp. 458

Author(s):

Zakaria El Mrabet ◽

Niroop Sugunaraj ◽

Prakash Ranganathan ◽

Shrirang Abhyankar

Keyword(s):

Neural Network ◽

Random Forest ◽

Power Systems ◽

Real Time ◽

Fault Location ◽

State Of The Art ◽

Economic Consequences ◽

Support Vector ◽

Detection Accuracy ◽

Data Driven Approach

Power system failures or outages due to short-circuits or “faults” can result in long service interruptions leading to significant socio-economic consequences. It is critical for electrical utilities to quickly ascertain fault characteristics, including location, type, and duration, to reduce the service time of an outage. Existing fault detection mechanisms (relays and digital fault recorders) are slow to communicate the fault characteristics upstream to the substations and control centers for action to be taken quickly. Fortunately, due to availability of high-resolution phasor measurement units (PMUs), more event-driven solutions can be captured in real time. In this paper, we propose a data-driven approach for determining fault characteristics using samples of fault trajectories. A random forest regressor (RFR)-based model is used to detect real-time fault location and its duration simultaneously. This model is based on combining multiple uncorrelated trees with state-of-the-art boosting and aggregating techniques in order to obtain robust generalizations and greater accuracy without overfitting or underfitting. Four cases were studied to evaluate the performance of RFR: 1. Detecting fault location (case 1), 2. Predicting fault duration (case 2), 3. Handling missing data (case 3), and 4. Identifying fault location and length in a real-time streaming environment (case 4). A comparative analysis was conducted between the RFR algorithm and state-of-the-art models, including deep neural network, Hoeffding tree, neural network, support vector machine, decision tree, naive Bayesian, and K-nearest neighborhood. Experiments revealed that RFR consistently outperformed the other models in detection accuracy, prediction error, and processing time.

Download Full-text

A Survey of Key Technologies for Constructing Network Covert Channel

Security and Communication Networks ◽

10.1155/2020/8892896 ◽

2020 ◽

Vol 2020 ◽

pp. 1-20

Author(s):

Jing Tian ◽

Gang Xiong ◽

Zhen Li ◽

Gaopeng Gou

Keyword(s):

Communication Technology ◽

Network Architecture ◽

The Internet ◽

Covert Channel ◽

Free Access ◽

Transmission Network ◽

Information Channel ◽

Covert Channels ◽

Key Technologies ◽

Network Covert Channel

In order to protect user privacy or guarantee free access to the Internet, the network covert channel has become a hot research topic. It refers to an information channel in which the messages are covertly transmitted under the network environment. In recent years, many new construction schemes of network covert channels are proposed. But at the same time, network covert channel has also received the attention of censors, leading to many attacks. The network covert channel refers to an information channel in which the messages are covertly transmitted under the network environment. Many users exploit the network covert channel to protect privacy or guarantee free access to the Internet. Previous construction schemes of the network covert channel are based on information steganography, which can be divided into CTCs and CSCs. In recent years, there are some covert channels constructed by changing the transmission network architecture. On the other side, some research work promises that the characteristics of emerging network may better fit the construction of the network covert channel. In addition, the covert channel can also be constructed by changing the transmission network architecture. The proxy and anonymity communication technology implement this construction scheme. In this paper, we divide the key technologies for constructing network covert channels into two aspects: communication content level (based on information steganography) and transmission network level (based on proxy and anonymity communication technology). We give an comprehensively summary about covert channels at each level. We also introduce work for the three new types of network covert channels (covert channels based on streaming media, covert channels based on blockchain, and covert channels based on IPv6). In addition, we present the attacks against the network covert channel, including elimination, limitation, and detection. Finally, the challenge and future research trend in this field are discussed.

Download Full-text

An Intelligent Classification Model for Surface Defects on Cement Concrete Bridges

Applied Sciences ◽

10.3390/app10030972 ◽

2020 ◽

Vol 10 (3) ◽

pp. 972 ◽

Cited By ~ 2

Author(s):

Jinsong Zhu ◽

Jinbo Song

Keyword(s):

Neural Network ◽

Surface Defects ◽

Concrete Bridges ◽

Classification Model ◽

Jiangxi Province ◽

Support Vector ◽

Detection Accuracy ◽

Cement Concrete ◽

Softmax Classifier ◽

Road Inspection

This paper mainly improves the visual geometry group network-16 (VGG-16), which is a classic convolutional neural network (CNN), to classify the surface defects on cement concrete bridges in an accurate manner. Specifically, the number of fully connected layers was reduced by one, and the Softmax classifier was replaced with a Softmax classification layer with seven defect tags. The weight parameters of convolutional and pooling layers were shared in the pre-trained model, and the rectified linear unit (ReLU) function was taken as the activation function. The original images were collected by a road inspection vehicle driving across bridges on national and provincial highways in Jiangxi Province, China. The images on surface defects of cement concrete bridges were selected, and divided into a training set and a test set, and preprocessed through morphology-based weight adaptive denoising. To verify its performance, the improved VGG-16 was compared with traditional shallow neural networks (NNs) like the backpropagation neural network (BPNN), support vector machine (SVM), and deep CNNs like AlexNet, GoogLeNet, and ResNet on the same sample dataset of surface defects on cement concrete bridges. Judging by mean detection accuracy and top-5 accuracy, our model outperformed all the contrastive methods, and accurately differentiated between images with seven classes of defects such as normal, cracks, fracturing, plate fracturing, corner rupturing, edge/corner exfoliation, skeleton exposure, and repairs. The results indicate that our model can effectively extract the multi-layer features from surface defect images, which highlights the edges and textures. The research findings shed important new light on the detection of surface defects and classification of defect images.

Download Full-text

Simultaneous evolutionary neural network based automated video based facial expression analysis

International Journal of Engineering & Technology ◽

10.14419/ijet.v7i1.1.9211 ◽

2017 ◽

Vol 7 (1.1) ◽

pp. 125

Author(s):

S. Jeyalaksshmi ◽

S. Prasanna

Keyword(s):

Neural Network ◽

Facial Expression ◽

Facial Expressions ◽

Real Life ◽

Support Vector ◽

Detection Accuracy ◽

Physical Fatigue ◽

Adaboost Algorithm ◽

Evolutionary Neural Network ◽

Fatigue Detection

In real life scenario, facial expressions and emotions are nothing but responses to the external and internal events of human being. In Human Computer Interaction (HCI), recognition of end user’s expressions and emotions from the video streaming plays very important role. In such systems it is required to track the dynamic changes in human face movements quickly in order to deliver the required response system. In real time applications, this Facial Expression Recognition (FER) is very helpful like physical fatigue detection based on facial detection and expressions such as driver fatigue detection in order to prevent the accidents on road. Face expression based physical fatigue analysis or detection is out of scope of this work, but this work proposed a Simultaneous Evolutionary Neural Network (SENN) classification scheme is proposed for recognising human emotion or expression. In this work, at first, automatically detects and tracks facial landmarks in videos, and face is detected by using enhanced adaboost algorithm with haar features. Then, in order to describe facial expression modifications, geometric features are taken out and the Local Binary Pattern (LBP) is extracted to improve the detection accuracy and it has a much lower-dimensional size. With the aim of examining the temporal facial expression modifications, we apply SENN probabilistic classifiers, which examine the facial expressions in individual frames, and after that promulgate the likelihoods during the course of the video to take the temporal features of facial expressions such as glad, sad, anger, and fear feelings. The experimental results show that the performance of proposed SENN scheme is attained better results compared than existing recognition schemes like Time-Delay Neural Network with Support Vector Regression (TDNN-SVR) and SVR.

Download Full-text

Real Time Security Assessment of the Power System Using a Hybrid Support Vector Machine and Multilayer Perceptron Neural Network Algorithms

Sustainability ◽

10.3390/su11133586 ◽

2019 ◽

Vol 11 (13) ◽

pp. 3586 ◽

Cited By ~ 4

Author(s):

Oyeniyi Akeem Alimi ◽

Khmaies Ouahada ◽

Adnan M. Abu-Mahfouz

Keyword(s):

Neural Network ◽

Support Vector Machine ◽

Power System ◽

Real Time ◽

Multilayer Perceptron ◽

Hybrid Algorithm ◽

Test System ◽

Support Vector ◽

Detection Accuracy ◽

Bus System

In today’s grid, the technological based cyber-physical systems have continued to be plagued with cyberattacks and intrusions. Any intrusive action on the power system’s Optimal Power Flow (OPF) modules can cause a series of operational instabilities, failures, and financial losses. Real time intrusion detection has become a major challenge for the power community and energy stakeholders. Current conventional methods have continued to exhibit shortfalls in tackling these security issues. In order to address this security issue, this paper proposes a hybrid Support Vector Machine and Multilayer Perceptron Neural Network (SVMNN) algorithm that involves the combination of Support Vector Machine (SVM) and multilayer perceptron neural network (MPLNN) algorithms for predicting and detecting cyber intrusion attacks into power system networks. In this paper, a modified version of the IEEE Garver 6-bus test system and a 24-bus system were used as case studies. The IEEE Garver 6-bus test system was used to describe the attack scenarios, whereas load flow analysis was conducted on real time data of a modified Nigerian 24-bus system to generate the bus voltage dataset that considered several cyberattack events for the hybrid algorithm. Sising various performance metricion and load/generator injections, en included in the manuscriptmulation results showed the relevant influences of cyberattacks on power systems in terms of voltage, power, and current flows. To demonstrate the performance of the proposed hybrid SVMNN algorithm, the results are compared with other models in related studies. The results demonstrated that the hybrid algorithm achieved a detection accuracy of 99.6%, which is better than recently proposed schemes.

Download Full-text

Fault Detection in Wireless Sensor Networks through the Random Forest Classifier

Sensors ◽

10.3390/s19071568 ◽

2019 ◽

Vol 19 (7) ◽

pp. 1568 ◽

Cited By ~ 20

Author(s):

Zainib Noshad ◽

Nadeem Javaid ◽

Tanzila Saba ◽

Zahid Wadud ◽

Muhammad Saleem ◽

...

Keyword(s):

Neural Network ◽

Wireless Sensor Networks ◽

Sensor Networks ◽

Random Forest ◽

Fault Detection ◽

Stochastic Gradient Descent ◽

Wireless Sensor ◽

Support Vector ◽

Data Loss ◽

Daunting Task

Wireless Sensor Networks (WSNs) are vulnerable to faults because of their deployment in unpredictable and hazardous environments. This makes WSN prone to failures such as software, hardware, and communication failures. Due to the sensor’s limited resources and diverse deployment fields, fault detection in WSNs has become a daunting task. To solve this problem, Support Vector Machine (SVM), Convolutional Neural Network (CNN), Stochastic Gradient Descent (SGD), Multilayer Perceptron (MLP), Random Forest (RF), and Probabilistic Neural Network (PNN) classifiers are used for classification of gain, offset, spike, data loss, out of bounds, and stuck-at faults at the sensor level. Out of six faults, two of them are induced in the datasets, i.e., spike and data loss faults. The results are compared on the basis of their Detection Accuracy (DA), True Positive Rate (TPR), Matthews Correlation Coefficients (MCC), and F1-score. In this paper, a comparative analysis is performed among the classifiers mentioned previously on real-world datasets. Simulations show that the RF algorithm secures a better fault detection rate than the rest of the classifiers.

Download Full-text

Research on Construction Methods for Network Covert Channels Based on HTTP

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.220-223.2528 ◽

2012 ◽

Vol 220-223 ◽

pp. 2528-2533

Author(s):

Ran Zhang ◽

Yong Gan ◽

Yi Feng Yin

Keyword(s):

Network Traffic ◽

Covert Channel ◽

Construction Technology ◽

Traffic Data ◽

Covert Channels ◽

Secret Data ◽

Construction Methods ◽

Working Principle ◽

Network Covert Channel

Network covert channel is a steganography technology that uses network traffic data as a carrier to transfer the secret data. This paper analyzes the working principle of network covert channels, and summarizes the commonly used construction technology of network covert channels. Then it analyzes the characteristics of the HTTP header lines and gives some methods of constructing network covert channels with these characteristics. Network covert channels based on the HTTP header lines are simple, flexible, and difficult to be detected and shielded.

Download Full-text

Neural Network Algorithm for Stabilizing Mechanized Systems

WSEAS TRANSACTIONS ON APPLIED AND THEORETICAL MECHANICS ◽

10.37394/232011.2022.17.3 ◽

2022 ◽

Vol 17 ◽

pp. 15-20

Author(s):

Elena G. Shmakova ◽

Olga A. Filoretova ◽

Olga M. Nikolaeva ◽

Denis P. Vasilkin

Keyword(s):

Neural Network ◽

Experimental Model ◽

High Speed ◽

Experimental Studies ◽

Small Diameter ◽

Hopfield Neural Network ◽

Neural Network Approach ◽

Rolling System ◽

Proportional Integral ◽

Mechanized System

The article describes an experimental model of stabilization of a mechanized system. The following are shown: a skate; an element of the program code; an algorithm for stabilizing a proportional-integral-differential controller (PID). The experimental model uses the calculation and adjustment of the regulator according to the Ziegler-Nichols method. For the case of applying the neural network approach to the search for equilibrium, the Hopfield neural network is used. The technology of calculating the balancing of the values of the coefficients: proportional, integral, differential components are described. The design of the rolling system is described. The experimental model is designed to identify the balancing range of the rolling system of small-diameter balls. The experimental module balances the ball at a distance of 4.5 to 7 cm (SW-range). The shortcomings of the experimental model of stabilization of the mechanized system are revealed. The analysis of experimental studies of spacecraft stabilization is carried out. It is determined that it is advisable to use the mathematical tools of the sixth-order Butterworth polynomial in the training of a neural network. Complex neural network calculations make it possible to calculate the stabilization coefficients of the spacecraft when the coordinate system does not coincide with the axes of inertia. An overview of the authors ' research on the use of intelligent quality control systems for the production of medicines is given. An overview of neural network solutions for stabilizing the turning angle of high-speed cars is given. The expediency of selecting the stabilization coefficients of a proportional-integral-differential regulator by a trained neural network for various rolling ranges is proved.

Download Full-text

Research on Optimal CDMA Multiuser Detection Based on Stochastic Hopfield Neural Network

Recent Patents on Computer Science ◽

10.2174/2213275912666181210103742 ◽

2019 ◽

Vol 12 (3) ◽

pp. 233-240

Author(s):

Tongke Fan

Keyword(s):

Neural Network ◽

Local Convergence ◽

High Speed ◽

Hopfield Neural Network ◽

Communication Model ◽

State Variables ◽

Stochastic Disturbance ◽

Detection Techniques ◽

The Neural Network ◽

Searching Ability

Background: Most of the common multi-user detection techniques have the shortcomings of large computation and slow operation. For Hopfield neural networks, there are some problems such as high-speed searching ability and parallel processing, but there are local convergence problems. Objective: The stochastic Hopfield neural network avoids local convergence by introducing noise into the state variables and then achieves the optimal detection. Methods: Based on the study of CDMA communication model, this paper presents and models the problem of multi-user detection. Then a new stochastic Hopfield neural network is obtained by introducing a stochastic disturbance into the traditional Hopfield neural network. Finally, the problem of CDMA multi-user detection is simulated. Conclusion: The results show that the introduction of stochastic disturbance into Hopfield neural network can help the neural network to jump out of the local minimum, thus achieving the minimum and improving the performance of the neural network.

Download Full-text

Research on Fault Detection for Three Types of Wind Turbine Subsystems Using Machine Learning

Energies ◽

10.3390/en13020460 ◽

2020 ◽

Vol 13 (2) ◽

pp. 460 ◽

Cited By ~ 1

Author(s):

Zuojun Liu ◽

Cheng Xiao ◽

Tieling Zhang ◽

Xu Zhang

Keyword(s):

Neural Network ◽

Support Vector Machine ◽

Fault Detection ◽

Convolutional Neural Network ◽

Wind Turbine ◽

Cost Effective ◽

Support Vector ◽

Detection Accuracy ◽

Machine Method ◽

Scada System

In wind power generation, one aim of wind turbine control is to maintain it in a safe operational status while achieving cost-effective operation. The purpose of this paper is to investigate new techniques for wind turbine fault detection based on supervisory control and data acquisition (SCADA) system data in order to avoid unscheduled shutdowns. The proposed method starts with analyzing and determining the fault indicators corresponding to a failure mode. Three main system failures including generator failure, converter failure and pitch system failure are studied. First, the indicators data corresponding to each of the three key failures are extracted from the SCADA system, and the radar charts are generated. Secondly, the convolutional neural network with ResNet50 as the backbone network is selected, and the fault model is trained using the radar charts to detect the fault and calculate the detection evaluation indices. Thirdly, the support vector machine classifier is trained using the support vector machine method to achieve fault detection. In order to show the effectiveness of the proposed radar chart-based methods, support vector regression analysis is also employed to build the fault detection model. By analyzing and comparing the fault detection accuracy among these three methods, it is found that the fault detection accuracy by the models developed using the convolutional neural network is obviously higher than the other two methods applied given the same data condition. Therefore, the newly proposed method for wind turbine fault detection is proved to be more effective.

Download Full-text