ملخص البحث :

Network violations are currently society's major challenge. For networks to be protected against hostile threats, an intrusion detection system (IDS) is important. To create effective IDS, deep learning (DL) is used in various fields, including information security. In this paper, a hybrid deep learning approach is proposed to effectively identify network intrusions using Autoencoder (AE) and Multi-layer perceptron (MLP). We use Autoencoder which can reduce the number of the original attributes based on the number of attributes, we first enter the original data on the Autoencoder and produce new compressed data, then enter it on the MLP classifier. The NSL-KDD dataset is thoroughly evaluated to determine the efficacy of the hybrid AE-MLP model the best outcomes are reached, with an accuracy rate of 87.6% and 81.06% (binary classification and multi-classification). In addition, the proposed hybrid method was compared with various recently proposed DL-based attack detection mechanisms. In terms of performance on the available dataset, it is observed that the proposed model outperformed.

ملخص البحث :

Obviously, the increasing threats to network security, which led to devastating network attacks, have taken a heavy toll on enterprises as a simple firewall cannot prevent complex and changing attacks. Therefore, companies should use intrusion detection systems in combination with other security devices to protect against corporate network security issues. In fact, intrusion detection is a system whose primary function is to protect network security by monitoring traffic, collecting and analyzing information, and then issuing an alert in cases where the output of the analysis represents a threat to network security. Intrusion Detection Systems (IDS) can stop unauthorized activity on a network or operating system, react automatically, stop the intrusion's source in time, record it, and alert the network administrator to ensure maximum system security. The process of detecting attacks using a single algorithm has not proven its worth. Therefore, several algorithms were used together by using ensemble learning. To elaborate, ensemble learning is a wellknown predictive technique that involves training multiple algorithms to treat the same problem, after which the results are combined to produce a single, potent prediction that can provide performance better than that of a single algorithm. The primary goal of this study is to present an overview of the main ensemble techniques that are used to enhance the effectiveness of the intrusion detection system, as well as the research using these methods as published by Elsevier and Springer from 2018 until the time being. The results prove that the two easiest methods within ensemble learning to implement are majority voting and weighted averaging, which provide good results in terms of accuracy. In cases where the base models have a significant variance, the bagging method would be more beneficial, while the boosting method would be used in cases where the basic models are biased, and in order to lower bias by learning different algorithms, the stacking ensemble methods are used.

ملخص البحث :

Breast cancer has been recently considered as one of the broadly spread diseases that causes death among women. Early disease diagnosis is a critical aim in building the treatment policies and is extremely related to safety of patient. Therefore, there is a necessity for computer aided detection (CAD) in order to provide accurate and rapid diagnosis for breast cancer. Recently, many classification models utilizing machine learning approaches have been adopted and modified to diagnose breast cancer disease. Moreover, the performance of each model depends on different compositions such as the number and type of data features and the parameters of model. In order to enhance the performance of classification model, this research proposes a model using modified K-means algorithm to create a new training dataset of breast cancer which can highly improve the performance of support vector machine model. A modified K-means algorithm is also proposed to build a high quality training dataset that contributes significantly to reduce the training time of classifiers, and improve the performance of classifier. The proposed model handles the noise and irregularity in data and produce high quality dataset which represents all the cases of disease. The two recognized datasets Wisconsin Breast Cancer (WBC) and Wisconsin Diagnostic Breast Cancer (WDBC) have been used to examine and appraise the performance of the proposed model. The experimental results show that the proposed model has a significant performance compared to other previous works and with accuracy level of 98.067%, sensitivity of 100%, specificity of 94.811%, precision of 97.011% and finally with area under the curve related to the receiver operating characteristic of 97.406%.

ملخص البحث :

One of the business intelligent solutions that are currently in use is the multi-agent system (MAS). Communication is one of the most important elements in MAS, especially for exchanging large low level data between distributed agents (physically). The agent communication language in Java Agent Development framework has been offered as a secure method for sending data, whereby the data is defined as an object. However, the object cannot be used to send data to another agent in a different machine. Therefore, the aim of this paper was to propose a method for the exchange of large low level data as an object by creating a proxy agent known as a delivery agent, which temporarily imitates the receiver agent. The results showed that the proposed method is able to send large-sized data. The experiments were conducted using 16 datasets ranging from 100,000 to 7 million instances. However, for the proposed method, the RAM and the CPU machine had to be slightly increased for the receiver agent, but the latency time was not significantly different compared to the use of the java socket method (non-agent and less secure). With such results, it was concluded that the proposed method can be used to securely send large data between agents.

ملخص البحث :

Most steganography methods suffer from many problems that effect on their efficiency and performance. Some of these are the capacity of cover media, the distortion of cover media, and etc. In this paper we are proposed a new method to hide audio file (WAV format) in image (BMP format) that overcomes most of these problems. Also the proposed method aims to meet most the requirements of any steganography system (like capacity, security and undetectability). It depends on finding the similarity between the embedded data blocks and others in the cover-image. It can be used as a powerful tool to get a high capacity data embedding and a less distortion stego-image, where the PSNR for the stego-image is large.

ملخص البحث :

Currently, most IT organizations are inclined towards a cloud computing environment because of its distributed and scalable nature. However, its flexible and open architecture is receiving lots of attention from potential intruders for cyber threats. Here, Intrusion Detection System (IDS) plays a significant role in monitoring malicious activities in cloud-based systems. The state of the art of this paper is to systematically review the existing methods for detecting intrusions based upon various techniques, such as data mining, machine learning, and deep learning methods. Recently, deep learning techniques have gained momentum in the intrusion detection domain, and several IDS approaches are provided in the literature using various deep learning techniques to deal with privacy concerns and security threats. For this purpose, the article focuses on the deep IDS approaches and investigates how deep learning networks are employed by different approaches in various steps of the intrusion detection process to achieve better results. Then, it provided a comparison of the deep learning approaches and the shallow machine learning methods. Also, it describes datasets that are most used in IDS.

ملخص البحث :

In general, multidimensional data (mobile application for example) contain a large number of unnecessary information. Web app users find it difficult to get the information needed quickly and effectively due to the sheer volume of data (big data produced per second). In this paper, we tend to study the data mining in web personalization using blended deep learning model. So, one of the effective solutions to this problem is web personalization. As well as, explore how this model helps to analyze and estimate the huge amounts of operations. Providing personalized recommendations to improve reliability depends on the web application using useful information in the web application. The results of this research are important for the training and testing of large data sets for a map of deep mixed learning based on the model of back-spread neural network. The HADOOP framework is using to perform a number of experiments in a different environment with a learning rate between -1 and +1. Also, using the number of techniques to evaluate the number of parameters, true positive cases are represent and fall into positive cases in this example to evaluate the proposed model.

ملخص البحث :

The growing volume of data on the computer network led to increasing the challenges for intrusion detection systems to deal with high dimensions that contain irrelevant and redundant features. This consumes time and difficulty in detecting the attack correctly, with increasing false alarms rate. This problem can be solved by applying dimensionality reduction. In this paper, a wrapper feature selection model based on Differential Evolution technique is proposed for intrusion detection systems. It reduces the number of features by finding the minimum number of features without effecting on the performance of the system. The main idea is to select some features from 41 features of NSL-KDD datasets using Differential Evolution and evaluate these features by computing the accuracy using Extreme Learning Machine. Differential Evolution is continued until obtaining the minimum number of features that satisfy a high accuracy. The results have shown a better detection rate with reduced false alarm rate in five and binary classification. The proposed system achieved an accuracy of 80.15 % and 87.53 for five and binary classification respectively with a reduction in training and testing time.

ملخص البحث :

In recent years, deep learning techniques have achieved significant results in several fields, like computer vision, speech recognition, bioinformatics, medical image analysis, and natural language processing. On the other hand, deep learning for intrusion detection has been widely used, particularly the implementation of convolutional neural networks (CNN), multilayer perceptron (MLP), and autoencoders (AE) to classify normal and abnormal. In this article, we propose a multi-level deep learning approach (MuDeLA) for intrusion detection systems (IDS). The MuDeLA is based on CNN and MLP to enhance the performance of detecting attacks in the IDS. The MuDeLA is evaluated by using various well-known benchmark datasets like KDDCup’99, NSL-KDD, and UNSW-NB15 in order to expand the comparison with different related work results. The outcomes show that the proposed MuDeLA achieves high efficiency for multiclass classification compared with the other methods, where the accuracy reaches 95.55% for KDDCup’99, 88.12% for NSL-KDD, and 90.52% for UNSW-NB15.