As cyber-attacks become remarkably sophisticated, effective Intrusion Detection Systems (IDSs) are needed to monitor computer resources and to provide alerts regarding unusual or suspicious behavior. Despite using several machine learning (ML) and data mining methods to achieve high effectiveness, these systems have not proven ideal. Current intrusion detection algorithms suffer from high dimensionality, redundancy, meaningless data, high error rate, false alarm rate, and false-negative rate. This paper proposes a novel Ensemble Learning (EL) algorithm-based network IDS model. The efficient feature selection is attained via a hybrid of Correlation Feature Selection coupled with Forest Panelized Attributes (CFS–FPA). The improved intrusion detection involves exploiting AdaBoosting and bagging ensemble learning algorithms to modify four classifiers: Support Vector Machine, Random Forest, Naïve Bayes, and K-Nearest Neighbor. These four enhanced classifiers have been applied first as AdaBoosting and then as bagging, using the aggregation technique through the voting average technique. To provide better benchmarking, both binary and multi-class classification forms are used to evaluate the model. The experimental results of applying the model to CICIDS2017 dataset achieved promising results of 99.7%accuracy, a 0.053 false-negative rate, and a 0.004 false alarm rate. This system will be effective for information technology-based organizations, as it is expected to provide a high level of symmetry between information security and detection of attacks and malicious intrusion.

No abstract

The current wireless communication system in Iraq faces several challenges during users’ handoff, especially with the fast growth of users and demands. This is also a global issue; therefore, quality of service (QoS) measures have rapidly become more important and developed over the years. The complexity of communication between diverse applications and underlying QoS architectures leads to these deployment problems, which decreases the utility of QoS provisioning. This paper studies different QoS aggregation mechanisms in order to improve the overall operational efficiency of the multi-homed node. The main QoS mechanisms, i.e., IntServ, DiffServ, best-effort, and IntServ-DiffServ were investigated and compared thoroughly. Furthermore, it focuses on the multi-homed network that aims to develop a scalable system with better performance, reliability, and optimized communication networks. In this paper, multi-homed network enhancements are carried out with the comparable site and host multi-homing. The results show how the IntServ-DiffServ has achieved the best overall performance compared to the other mechanisms as it combines the advantages of the IntServ and DiffServ mechanisms. Another important finding was that the multi-homing managed to keep the communication going on the multi-homed node, whereas the site-multi-homing gave a better overall end-to-end latency over the host-multi-homing.

From a security perspective, the research of the jeopardized wireless communications and its expected ultra-densified ubiquitous wireless networks urge the development of a robust intrusion detection system (IDS) with powerful capabilities which could not be sufficiently provided by the existing conventional systems. IDSs are still insufficient against continuous renewable unknown attacks on the wireless communication networks, especially with the new highly vulnerable networks, leading to low accuracy and detection rate with high (false-negative, and false-positive) rates. To this end, this paper proposed a novel anomaly detection in communication networks by using an ensemble learning (EL) algorithm-based anomaly detection in communication networks (ADCNs). EL-ADCNs consist of four main stages; the first stage is the preprocessing steps. The feature selection method is the second stage. It adopts the proposed hybrid method using correlation with the random forest algorithm of ensemble learning (CFS-RF). It reduces dimensionality and retrieves the best subset feature of all the three datasets (NSL_KDD, UNSW_NB2015, and CIC_IDS2017) separately. The third stage is using hybrid EL algorithms to detect intrusions. It involves modifying two classifiers (i.e., random forest RF, and support vector machine SVM) to apply them as adaboosting and bagging EL Algorithms; using the voting average technique as the aggregation process. The final stage is testing the proposal using binary and multi-class classification forms. The experimental results of applying (30, 35, and 40) features of the proposed system to the three datasets achieved the best results of NSL_KDD are 99.6% accuracy with a 0.004 false-alarm rate, a 99.1% accuracy with a 0.008 false-alarm rate for UNSW_NB2015, and a 99.4% accuracy with a 0.0012 false-alarm rate for CIC_IDS2017.

The document indexing process aims to store documents in a manner that facilitates the process of retrieving specific documents efficiently in terms of accuracy and time complexity. Many information retrieval systems encounter security issues and execution time to retrieve relevant documents. In addition, these systems lead to ample storage. Therefore, it requires combining confidentiality with the indexed document, and a separate process is performed to encrypt the documents. Hence, a new indexing structure named tree browser (TB) was proposed in this paper to be applied to index files of the large document set in an encrypted manner. This method represents the keywords in a variable-length binary format before being stored in the index. This binary format provides additional encryption to the information stored and reduces the index size. The proposed method (TB) is applied to the WebKB dataset. This dataset is related to web page documents (semi-structured documents). The experimental results demonstrated that the storage size is reduced by using TB-tree to 48.5 MB, while the traditional index is 307 MB.