Recent outbreaks of pandemics have deepened the adoption and use of IT-based systems. This development has led to an exponential increase in cyberattacks caused by malware. Current approaches ...(static, dynamic and hybrid) for detecting malware still exhibit low efficiency when subjected to sophisticated malware. This work used an ensemble technique consisting of Deep Convolutional Neural Network and Deep Generative Adversarial Neural Network (Mal-Detect) to analyse, detect, and categorise malware. The proposed Mal-Detect first converts both malware and benign file binaries into RGB binary images. New malware images are then generated using a deep generative adversarial neural network from original malware samples. The generated malware images with original malware and benign files images are pre-processed and trained with Deep Convolutional Neural Networks to extract important features from the dataset. The effectiveness of Mal-Detect was evaluated against three benchmark datasets; MaleVis, Mallmg and Virushare. The results of the evaluation showed that Mal-Detect outperforms other state of art techniques with an accuracy of 99.8% and an average accuracy of 96.77% on all malware datasets tested. These results showed that Mal-Detect can be deployed for detecting all categories of malware.
Rail track breakages represent broken structures consisting of rail track on the railroad. The traditional methods for detecting this problem have proven unproductive. The safe operation of rail ...transportation needs to be frequently monitored because of the level of trust people have in it and to ensure adequate maintenance strategy and protection of human lives and properties. This paper presents an automatic deep learning method using an improved fully Convolutional Neural Network (FCN) model based on
-Net architecture to detect and segment cracks on rail track images. An approach to evaluating the extent of damage on rail tracks is also proposed to aid efficient rail track maintenance. The model performance is evaluated using precision, recall, F1-Score, and Mean Intersection over Union (MIoU). The results obtained from the extensive analysis show
-Net capability to extract meaningful features for accurate crack detection and segmentation.
The study proposes a fuzzy-based control of admission of customers in a queue network with two stations in tandem. Each of the stations has individual arrival streams which may either be accepted or ...rejected. Class i arrivals occur in a Poisson stream with constant rate λi, i = 1, 2. Successive services in each station j are independent and exponentially distributed, with mean 1/µj in station j, j =1, 2, irrespective of the customer’s class. The objective of the study is to decide an optimal admission policy based on the state of the queue such that profit is maximized. The state of the system is described by (z1, z2), where zi is the number of customers in station i, and i = 1, 2. The tool adopted is a fuzzy process which determines this policy using the fuzzy input values, s and λ giving a corresponding decision, dec. which is either a ‘1’ or ‘0’ representing ‘Admit’ or ‘Reject’ respectively. The membership functions of arrivals were defined and implemented using fuzzy rules to derive a fuzzy output of decision which either ‘Admit’ or ‘Reject’ an arrival. Numerical results show a considerable improvement in the control of customers’ admission and it was concluded that the proposed method is efficient in the control of customers’ admission in queue network.
Phishing attacks have become the most effective means of gaining unauthorized access to confidential information in the cyberspace. Unfortunately, many Internet users cannot identify phishing ...strategies and fall victim to these attacks. This work presents a mobile game-based learning called PHISHGEM for enhancing the awareness of phishing attacks. PHISHGEM educates users on five (5) major types of phishing techniques, namely, URL Manipulation, Email Spoofing, Website Cloning, Smishing and Social Media Attacks. The users of the game will identify phishing attacks in a wide range of real-life scenarios using a mobile application. The functionalities of the game were run on JAVA programming language, XML (Extensible Markup Language) was used to create the layout and Android studio IDE Version 4.1 was used to run the program. A user study with 100 participants was conducted to determine the effectiveness of PHISHGEM. Three (3) prominent factors such as the playability, usability and users' learning outcome were used for the evaluation of the game. The study analysis revealed that PHISHGEM attained a 98% Awareness Level, a Perceived Ease of Use of 94% and a New Knowledge Acquired of 94%. Also, the Perceived Effectiveness of the game and Users' Experience were given positive responses of 90% and 89%, respectively.
Distributed Denial of Service (DDoS) attacks are the foremost security concerns on the Internet. DDoS attacks and a similar occurrence called Flash Event (FE) signify anomalies in the normal network ...traffic, requiring intelligent interventions. This study presents the design and implementation of an intelligent model for the detection of application-layer DDoS attacks and the prevention of service degradations during FE. A Multi-Layer Perceptron (MLP) classifier was used for detecting DDoS attacks on application servers. The FE management system consists of asynchronous processing of requests on a First-In, First-Out (FIFO) basis. A demo application was set up wherein HTTP flood attack was launched and a Flash Event was simulated. The experimental results clearly show that the MLP classifier in comparison with other machine learning classifiers performs best in terms of speed and accuracy. Also, the evaluation of the FE management system shows a great reduction in service degradation. This reflects that the designed model is capable of averting service unavailability on the web.
A natural language architecture SODIYA, ADESINA SIMON
Journal of computing and information technology,
2007, Volume:
15, Issue:
1
Journal Article, Paper
Peer reviewed
Open access
Natural languages are the latest generation of programming languages, which require processing real human natural expressions. Over the years, several groups or researchers have trying to develop ...widely accepted natural language languages based on artificial intelligence (AI). But no true natural language has been developed. The goal of this work is to design a natural language preprocessing architecture that identifies and accepts programming instructions or sentences in their natural forms and generate equivalent codes in the base high level language. The new programming language platform developed called H++, translates and processes real human natural expressions. Using Visual Basic 6.0 as the base high level programming language, the implementation resulted in an interactive and easy to use natural language platform.
Since Intrusion Detection System (IDS) has become necessary security tool for detecting attacks on computer network and resources, it is therefore essential to improve on previous designs. In past, ...many mobile agent-based IDSs have been designed, but there still exists some drawbacks. Some of these drawbacks are low detection efficiency, high false alarm rate and agent security. A multi-level and secured IDS architecture that is based on mobile agent is presented on this work to correct these drawbacks. Implementing the new design using JAVA shows a better performance over previous designs.
The goal of co st-sensitive response system is to ensure that response cost does not outweigh the intrusion cost. In order to ensure this, some cost-sensitive response models have been developed. ...Some of these models do not consider the effectiveness of previous actions and lack standard approach for estimating associated cost. In this work, we present a model for assessing cost of responses based on three factors, the cost of damage caused by the intrusion, the cost of automatic response to an intrusion and the operational cost. The proposed approach provides consistent basis for response assessment across different systems and environment. In addition, the performance analysis indicates that automated responses systems using this cost metric COSIRS, when deployed can responds quickly enough to thwart active attacks in real time using optimal responses. The results of evaluation show that the design has better performance over existing ones.
Intrusion Detection Systems (IDS) is defined as a component that analyses system and user operations in computer and network systems in search of activities considered undesirable from security ...perspectives. Applying mobile agent (MA) to intrusion detection design is a recent development and it is aimed at effective intrusion detection in distributed environment. From the literature, it is clear that most MA-based IDS that are available are not quite effective because then-time to detection is high and detect limited intrusions. This paper proposes a way of classifying a typical IDS and then strategically reviews the existing mobile agent-based IDSs focusing on each of the categories of the classification, for example architecture, mode of data collection, the techniques for analysis, and the security of these intelligent codes. Their strengths and problems are stated wherever applicable. Furthermore, suggested ways of improving on current MA-IDS designs are presented in order to achieve an efficient mobile agent-based IDS for future security of distributed network.