Baharudin Osman

The Internet of Things (IoT) is a rapidly growing field that connects various devices and systems to the internet, enabling them to communicate and share data. However, this increased connectivity also makes IoT networks vulnerable to various types of attacks, one of which is the wormhole attack. A wormhole attack is a type of security threat in which an attacker creates a tunnel between two or more nodes in an IoT network, allowing the attacker to intercept, modify or inject malicious packets into the network. This can lead to serious security issues such as unauthorized access, data leakage and network disruption. The problem of wormhole attack detection in IoT networks is a crucial issue that must be addressed. Traditional security methods, such as firewalls and intrusion detection systems, may not be effective in detecting and preventing wormhole attacks, as these attacks are difficult to detect due to the stealthy nature of the attacker. Therefore, there is a need for new and more advanced methods for wormhole attack detection in IoT networks, such as deep learning approaches. The goal of this paper is to use a deep learning approach to detect wormhole attacks in IoT networks and to compare the performance of this approach with traditional machine learning methods. This research paper presents a deep learning approach for wormhole attack detection in Internet of Things (IoT) networks using Long Short-Term Memory (LSTM) model. The proposed method is compared with traditional machine learning techniques which are Decision Tree, and Naive Bayes. The performance of the proposed approach is evaluated using a malware dataset for predicting the type of wormhole attack (WHR). The evaluation metrics used in this study include accuracy, F1 score, precision, recall and confusion matrix. The implementation of the proposed approach is performed using Python programming and the Anaconda Navigator (Spyder notebook) tool. The results show that the proposed LSTM-based approach outperforms traditional machine learning techniques in terms of accuracy and F1 score which is 99% while Decision Tree Model accuracy is 94% and Naïve Bayes Model scores 93%, the output results of this paper demonstrating the effectiveness of deep learning in wormhole attack detection in IoT networks.

Technology and online systems were enhancing the way people work. An online system for evaluating practicum students is vital as the number of students participating in practicum sessions each semester continues to grow. The traditional method of manual evaluation can be time-consuming and tedious for supervisors, and maintaining and organising student evaluation data can also be a challenge for the university. To overcome these issues, this study aims to create an online evaluation system named "Online Practicum Evaluation Management System". This system will enable supervisors to evaluate students quickly and easily based on the specific rubric without needing to be paper-based. Additionally, the system will provide a secure and organised platform for storing and accessing student evaluation data. This solution aims to enhance the overall efficiency and effectiveness of the practicum program. Rapid Application Developments (RAD) has been used in developing this system. There are four steps in the RAD methodology: requirements gathering, user design, construction, and cutover. Interviews and content analysis were first used to gather the functional requirements. The collected requirements were then used to create a prototype and put through a recorded usability study. The evaluation indicated that OPEMS is practical and straightforward to operate. A majority of respondents are pleased with the system's features. Researchers and developers in this field can use the study as a blueprint for creating similar designs or improving the performance of existing ones. Therefore, the proposed Online Practicum Evaluation Management System will be a more practical, well-organized, faster, reliable, and accurate means of processing the current conventional method of evaluating practicum students.

Data communication over the Internet has increased significantly, resulting in high data traffic and concerns over data security. Information sent over the Internet always gets the attention of intruders, which causes the effort to increase the security of sensitive data and the need to prevent leakage. Steganography is one of the techniques to protect the confidentiality of data that can be accomplished by hiding secret information within the medium of text, images, audio, and video. Hiding a secret message using text steganography can be done on character properties such as size, colour, style, etc. Colour- based steganography has always raised suspicions about the generated stego text, which is a major issue in this study. Therefore, the Red, Green, and Blue (RGB) colour technique and the Second Quotient Remainder Theorem (SQRT) were introduced in this study to perform the hiding process. RGB (0,0,0) to RGB (15,15,15) colours were used for the hiding process to avoid colour suspicion. In addition, the pseudorandom number generator (PRNG) was also used to generate dynamic hidden messages with Homophonic table generation. The results showed that the secret message can be represented dynamically and has increased the hiding capacity to 77.4%. Other than that, the selected colour has successfully avoided the suspicion of the generated stego text. Hence, the results suggested that SQRT could be employed as a method in text steganography for securing information.