Search

Globally, as the upsurge in dependencies on computer network services, so are the activities of attackers that gain undue access to network resources for selfish interest at the expense of the stakeholders. Attackers threaten integrity, availability, and confidentiality of network resources despite various preventive security measures, hence the need to study ways to detect and minimize attackers’ activities. This paper develops a Network-Based Intrusion Detection System (NBIDS) using the machine learning algorithms capable of detecting and preventing anomaly (attack) network traffic from the Internet, thereby reducing cases of successful network attacks. Gain Ratio and Information Gain are used for features ranking on the UNSW-NB15 benchmark network intrusion dataset. The first fifteen highly ranked features are selected for developing classification models using C4.5 and Naive Bayes (NB), coincidentally the two feature ranking approaches to select the same features but in a different ordering. Empirical results show that the C4.5 algorithm outperformed NB for all simulations based on a different spilled ratio of testing and training sets as it returns the highest accuracy of 90.44% against 75.09% for NB for two-class models on simulation IV. For all the experimental setup, both DT and NB have a constant precision of 91% to 75%, the True Positive value of 90%:75%, and False Positive value of 8.6%:22.8%, respectively. The experiments revealed that accuracy increases as the training ratio increases. The results show that the approach is practicable for real-time network intrusion detection.

Over the years, the vulnerability of the network system has completely revolutionized the security system. Attackers simply exploit these exposures to gain undue access to network resources. It is essential to safeguard network resources with the Intrusion Prevention System (IPS) and Intrusion Detection System (IDS). Hence, to develop an optimized IDS model using ensemble modeling of machine learning technique is paramount. Therefore, this research attempts to build a network IDS using an ensemble of Decision Trees (DT) algorithms to optimize an IDS model. Furthermore, the C4.5 DT classifier used on the University of New South Wales Network-Based 2015 (UNSW-NB15) network data set. Then the ensemble techniques of bagging and AdaBoost are compared during the performance evaluation. The results of this work depict that performance increase as training size increases. Consequently, the results showed that adopting the ensemble model for the C4.5 decision tree classified improved network intrusion classification compared to using the machine learning algorithm in isolation. Moreover, the result also showed an improved classification model for network IDS model. The AdaBoost ensemble model of the C4.5 DT algorithm using partitions of 90% of training and 10% of testing data sets performs the best with 98% accuracy and precision.

Internet has positively changed social, political and economic structures and in many ways obviating geographical boundaries. The enormous contributions of Internet to business transactions coupled with its ease of use has resulted in increased number of internet users and consequently, intruders. It is crucial to safeguard computer resources with the aid of Intrusion Detection Systems (IDS) in addition to Intrusion Prevention Systems. In recent times, enormous network traffic generated in terabytes within couples of seconds are difficult to analyze with the traditional rule-based approach; hence, researchers have to subject data mining techniques to intrusion detection with emphasis on intrusion detection accuracy; relevant feature selection leads to faster and enhanced accurate detection rate. Therefore, this paper presents a light weight IDS based on information gain and Multi-layer perceptron Neural Network. Gain ratio was used in selecting relevant features for attack and normal traffic prior classification using Neural Network. Empirical results from the UNSW-NB15 intrusion detection dataset on thirty selected attributes is a highly ranked decision, thus, the light weight IDS is suitable for real time intrusion detection.

This research designed a multigeneration system that meets the energy requirement of a rural community in Nigeria. This system is powered by the biogas produced from maize silage and chicke...

Aim/Purpose: The wide use of online banking and technological advancement has attracted the interest of malicious and criminal users with a more sophisticated form of attacks. Background: Therefore, banks need to adapt their security systems to effectively stem threats posed by imposters and hackers and to also provide higher security standards that assure customers of a secured environment to perform their financial transactions. Methodology : The use of authentication techniques that include the mutual secure socket layer authentication embedded with some specific features. Contribution: An approach was made through this paper towards providing a more reliable and complete solution for implementing multi-level user authentication in a banking environment. Findings: The use of soft token as the final stage of authentication provides ease of management with no additional hardware requirement. Recommendations for Practitioners : This work is an approach made towards providing a more reliable and complete solution for implementing multi-level user authentication in a banking environment to stem cybercrime. Recommendation for Researchers: With this approach, a reliable system of authentication is being suggested to stem the growing rate of hacking activities in the information technology sector. Impact on Society :This work if adopted will give the entire populace confidence in carrying out online banking without fear of any compromise. Future Research: This work can be adopted to model a real-life scenario.

Aim/Purpose: Medical images are very sensitive data that can be transferred to medical laboratories, professionals, and specialist for referral cases or consultation. Strict security measures must be utilized to keep these data secured in computer networks when transferred to another party. On a daily basis, unauthorized users derive ways to gain access to sensitive patient medical information. Background: One of the best ways to which medical image could be kept secured is through the use of quantum cryptography Methodology : Applying the principles of quantum mechanics to cryptography has led to a remarkable new dimension in secured network communication infrastructure. This enables two legitimate users to produce a shared secret random bit string, which can be used as a key in cryptographic applications, such as message encryption and authentication. Contribution: This paper can make it possible for the healthcare and medical professions to construct cryptographic communication systems to keep patients’ transferred data safe and secured. Findings: This work has been able to provide a way for two authorized users who are in different locations to securely establish a secret network key and to detect if eavesdropping (a fraudulent or disruption in the network) has occurred Recommendations for Practitioners: This security mechanism is recommended for healthcare providers and practitioners to ensure the privacy of patients’ medical information. Recommendation for Researchers: This paper opens a new chapter in secured medical records Impact on Society Quantum key distribution promises network security based on the fundamental laws of quantum mechanics by solving the problems of secret-key cryptography . Future Research: The use of post-quantum cryptography can be further researched.

Smart-grid is the adoption of better control, monitoring and remote sensing in power systems while micro-grid is an advance approach to integrate energy resources in the power distribution system. These two technologies have developed over the years and have proven to be a reliable and secured approach in power system. In this paper, the potential utilization of smart micro-grid to solve the power supply challenge in Nigeria is explored. The used of wind and solar PV for electricity generation for 12 different cities in Nigeria is also analyzed. Nigeria’s renewable energy and fossil fuel potential are enormous but the country is faced with epileptic power supply challenge. Only 60% of Nigerians have access to electricity and most of these citizens (55%) reside in the urban areas. The paper presents the prospect of smart micro-grid as an immediate solution to the current challenges in Nigeria power sector.

The major principle of multicast communication is that each data packet sent from one source must reach all the receivers exactly as it originates from the source without any modification on the way. For information to be authentic there is the need to ensure that the information is from where they claim to come from and that security requirements are put in place. In multicast applications, when there are packet losses, the authenticity of the packet will not be verifiable by the receiver, making authentication impossible. In view of this, there is a need to develop an authentication scheme with lower communication cost and one that can be verifiable when packet loss is high. Thus, this research work developed a multicast authentication scheme that makes verification possible when there is packet loss and minimizes the size of the communication overhead. The research simulates a network environment using C sharp programming language and was tested with different messages to a number of receivers. The program was implemented in two phases: the sender’s end and the receiver’s end. The results show that amortization technique assists in reconstruction of the packet and make verification possible even when there are high losses of packets.

The most common way of ensuring confidentiality of data or documents by individuals, governments, and institutions such as banks, hospitals, and other commercial enterprises is by consigning their secrets to a computer system. But this has not solved the problems of upholding security, instead they are more compounded due to the fact that secrets sharing is generally desired but only in a tightly controlled manner. This could be resolved by the introduction of a secured shared processing system. Secured shared processing system is a system that comprises of several computers whereby one stands as a secured, trusted system while the other systems are connected to it. The system do not divide up a memory or a clock; the computers only communicate with each other by exchanging messages over a communication channel; and each computer has its own memory and operates on its own operating system. This is achieved with the aid of Cryptographic mechanisms in which EI Gamal model was adopted as a Public-key cryptography scheme which will be applied on a workstation distributed System.

An Empirical Investigation of Users’ Knowledge of Electronic Waste based on Technology Awareness Model Improper Electronics Waste (E-Waste) management is an endemic problem that characterizes developing countries including Nigeria. It is a known fact that improper waste disposal impinges on environmental health. This paper focuses on studying the level of users’ awareness of hazardous effect of obsolete and refurbished electronics on both the environment and human in Ondo State, South West, Nigeria. The survey instrument employed involved a total of 367 questionnaires within the study area. Technology Awareness Model (TAM) and Principal Component Analysis were employed to evaluate the multivariate data. The result of this study shows that they are not aware of the hazardous effects of e-wastes on individual and environmental health.