Mohammad Rasmi AlMousa
@zu.edu.jo
Cybersecurity Department/Faculty of Information Technology
Zarqa University
RESEARCH INTERESTS
Network Security, Digital Forensics, Software Engineering
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Raed Masadeh, Dmaithan Abdelkarim Almajali, Manaf Al-Okaily, Nida AL-Sous, and Mohammad Rasmi Al-Mousa
Growing Science
The recent progress of Financial Information System (FIS) has significantly affected businesses’ sustainable production process. Businesses generally employ FIS to automate their operational procedures and increase their corporate efficiencies through improvement in output quality and sustainability. The performance of FIS has been attributed to its key success criteria. Accordingly, this study examined antecedents of FIS intention to use among Small and Medium-Size Enterprises (SMEs) in Jordan at individual level, with specific focus on the acceptance and use of FIS among accounting department employees. Based on 436 respondents from Jordanian SMEs, results showed an impact of COVID-19 risk, trust, performance expectancy, and perceived severity on the intention to use FIS, whereas effort expectancy and perceived vulnerability showed no impact on the intention to use FIS among Jordanian SMEs.
Ahmad Al-Fandi, Ahmad Toma, Basim Alsayid, Samer Alsadi, Tareq Foqha, Ali Elrashidi, and Mohammad Rasmi Al-Mousa
Springer Nature Switzerland
Mohammad Kaik, Momen Zarour, Faris Sabha, Tawfiq Abu-salah, M. Muntaser-Aldabe, Samer Alsadi, Tareq Foqha, and Mohammad Rasmi Al-Mousa
Springer Nature Switzerland
Abdullah Ziadeh, Heba Zedan, Taima’a Theeb, Waseem Kharoof, Arafat Zedan, Samer Alsadi, Tareq Foqha, and Mohammed Rasmi Al-Mousa
Springer Nature Switzerland
R. Alazaidah, A. Al-Shaikh, M. Al-Mousa, H. Khafajah, G. Samara, M. Alzyoud, N. Al-Shanableh and S. Almatarneh
Natural Sciences Publishing
: Phishing is a cybercrime that is constantly increasing in the recent years due to the increased use of the Internet and its applications. It is one of the most common types of social engineering that aims to disclose or steel users sensitive or personal information. In this paper, two main objectives are considered. The first is to identify the best classifier that can detect phishing among twenty-four different classifiers that represent six learning strategies. The second objective aims to identify the best feature selection method for websites phishing datasets. Using two datasets that are related to Phishing with different characteristics and considering eight evaluation metrics, the results revealed the superiority of RandomForest, FilteredClassifier, and J-48 classifiers in detecting phishing websites. Also, InfoGainAttributeEval method showed the best performance among the four considered feature selection methods.
Saeb Al-Sherideh, Roesnita Ismail, M. Al-Mousa, Khaled E. Al-Qawasmi, Ala'a F. Al-Shaikh, H. Awwad, K. Maabreh and Mohammad Alauthman
Natural Sciences Publishing
: This paper develops a secure model for mobile government (M-G) applications using effective privacy methods and validates the model through semi-structured interviews with eight Jordanian e-government experts. The experts emphasized the importance of M-G applications in enhancing services such as bill payments, civil services, civil defense, and police services. To improve privacy, the experts suggested methods such as strong textual passwords, data encryption, login tracking, SMS login confirmation
Aman R. Anand, V. Srivastav, M. Al-Mousa, A. Paul, S. Thota, R. Anand, K. Srivastav, R. Al-Mousa, Akshoy Mohammad R. Paul and An International
Natural Sciences Publishing
: In this paper, we present a three-dimensional numerical analysis of friction stir welding on an alumunium butt joint. A thin sheet of aluminum marking material was embedded into the 6061-aluminum alloy panel and its rear weld path. The positions after friction stir welding were investigated by metallographic techniques. Looking at the visualized material flow pattern, a three-dimensional model was developed to numerically simulate the temperature profile and plastic effects. The calculated velocity profile for plastic flow in the immediate vicinity of the tool generally agrees with the visualized results. Increasing the tool speed while maintaining a constant tool feed rate increases the material flow near the pin. The shape and size of the predicted weld zone match the experimentally measured ones
Maher Al-Khateeb, Mohammad Rasmi Al-Mousa, Ala’a Saeb Al-Sherideh, Dmaithan Almajali, Mahmoud Asassfeha, and Hayel Khafajeh
Growing Science
Social Engineering (SE) Attacks against information systems continue to pose a potentially devastating impact. Security information systems are becoming increasingly significant as the number of SE incidents rapidly increased and became more aggressive than before. The World Wide Web (WWW) has evolved for information exchange and knowledge-sharing. It enables the sharing of information in a timely, effective, and transparent manner. Identity theft and identity misuse are two sides of cybercrime in which hackers and fraudulent users collect sensitive information from current legal users in order to perform fraud or deceit for financial gain. Malicious links are used as phishing methods, in which malicious links are planted beneath legitimate-looking links. As the number of web pages grows, the number of malicious web pages and the attacks of such become more complex. In this paper, we provide a method for identifying malicious web pages using a crawling and classification approach that helps to support the automatic discovery of the malicious links. The proposed approach can successfully complete the crawling session even if the page requires partial page refreshment and authentication credentials. The evaluation of the proposed approach shows a higher accuracy compared to an existing approach with an overall accuracy of 72% in three custom applications. Moreover, the proposed approach will calculate the significance and the impact severances of each link on the website and it better differentiates malicious web pages and normal links. The results of the proposed approach will also help in providing a set of recommendations which can increase the awareness level of the end-users, website administrators on how to better deal with these types of SE attacks.
Shrouq Al-Daja, Ala'Alyabrodi, Mohammad Rasmi Al-Mousa, Abdullah Al-Qammaz, Kholod Naser Olimat, Hamza M Olemat, and Mohammad Sh Daoud
IEEE
As the prevalence of sophisticated network attacks continues to rise, enhancing conventional intrusion detection systems (IDS) methods presents a significant challenge. Machine learning (ML)-based anomaly detection and cybersecurity analytics have been widely used in research and development projects related to network IDS. This study explores a set of classifiers on specific domain is a cybersecurity. A significant aspect of this study involves data preparation, including a selection of important features to enhance detection accuracy. Additionally, the study introduces the Synthetic Minority Over-sampling Technique (SMOTE) to address the challenge of classifying imbalanced data. The primary aim of this study is to evaluate various classifiers, such as Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), and Multi-layer perceptron (MLP) neural network. The experiments involve different feature groups distributed at percentages of 25%, 50%, 75%, and 100%. The evaluation is conducted from the perspectives of evaluation measurements, time consumption, and space utilization. The experimental findings highlight that RF outperforms the other classifiers, achieving an accuracy of 0.96778, precision of 0.73007, recall of 0.74087, F1 score of 0.73184, and G-mean of 0.22136.
The goal of this research is to review the researcher's different attempts with respect to new and emerging technology in malware detection techniques based on machine learning approaches over smartphones. The aim is to evaluate and benchmark these techniques, identify the current landscape of research in this area, and construct a cohesive taxonomy. The available options and gaps will be analyzed to provide valuable insights for researchers regarding the technological environments within this research area. A deep analysis review was conducted to identify studies addressing smartphone security based on machine learning approaches in order to identify all related articles. The outcomes of the last classification scheme of these articles were categorized into types of detection: dynamic analysis, static analysis, hybrid analysis, and uniform resource locator (URL) analysis. The evaluation criteria used in malware detection techniques, with respect to machine learning approaches for smartphones, include accuracy, precision rates (including true positive, false positive, true negative, false negative), training time, f-measure, detection time, area under the curve, true positive, true negative, false positive, false negative, and error rate. Additionally, our classification covers the main machine learning techniques used in the reviewed studies. The taxonomy includes three distinct layers, each reflecting one aspect of the analysis. We also reviewed the details of various types of malicious and benign datasets used within malware detection. Furthermore, open issues and challenges were identified in terms of evaluation and benchmarking, which jeopardize the utilization of this technology. We have described a new recommendation pathway solution that aims to enhance the measurement process of smartphone security applications.
Suha Afaneh, Mohammad Rasmi Al-Mousa, Hilal Shrif Al-hamid, Bara'h Suliman AL-Awasa, Mohammad Alia, Hani Almimi, and Ahmad A Alkhatib
IEEE
Agile and DevOps methodologies are becoming increasingly popular in software development, as they offer many benefits to software development teams and the organizations they work for. Agile methods depend on speed in development, repetition, and an increase in focus on the main characteristics and functions of the system. The DevOps approach aims at continuous integration, continuous delivery, continuous improvement, and faster feedback. Security is a critical component of Agile and DevOps methodologies. Integrating security into the development process from the outset can help to reduce the risk of security vulnerabilities, improve collaboration between development and security teams, enable rapid response to security incidents, increase automation, and ensure compliance with regulatory requirements. In conclusion, security has challenges in agile and DevOps approaches, so this paper discusses the most important challenges of combining ensuring security and continuous development.
Ala'a Al-Shaikh, Ameen Shaheen, Mohammed Rasmi Al-Mousa, Khaled Alqawasmi, Ala'a Saeb Al Sherideh, and Hebatullah Khattab
International Association of Online Engineering (IAOE)
Mobile devices are playing an important role in our daily lives. Nowadays, mobile devices are not only phones to call and text, but they are also smart devices that enable users to do almost any task that could be done on a regular PC. At the heart of the design of smartphones, there lies the processor to which almost all the development in the smartphone arena is attributed. Recently, ARM processors are among the most prominent processors used in mobile devices, smartphones, and embedded systems. This paper conducts an experimental comparative study of ARM 64-bit processors in terms of performance and their effect on power consumption, CPU temperature, and battery temperature. We use a number of well-known benchmarks to evaluate those characteristics of three smartphones, namely, Snapdragon 778G+, Exynos 1280 and HiSilicon Kirin 980. Those smartphones are all equipped with ARM 64-bit processors. Our results reveal that none of the three-selected smartphones was the best in all characteristics; each has superiority amongst others in certain characteristics and is dominated by others in other characteristics.
Alaa Saeb Al-Sherideh, Khaled Maabreh, Majdi Maabreh, Mohammad Rasmi Al Mousa, and Mahmoud Asassfeh
The Science and Information Organization
Yahya Qusay AL-Sammarraie, Khaled AL-Qawasmi, Mohammad Rasmi AL-Mousa, and Sameh F. Desouky
IEEE
social media are fantastic tools for public communication. Social media has become an integral part of our everyday lives, and an increasing number of individuals use it for marketing and communication. Social networking enables you to demonstrate your skills and knowledge without leaving home. Companies exert significant efforts to make social media more controlled and valuable while avoiding negative repercussions. They accomplish this with artificial intelligence (AI), which enables them to develop unique applications and algorithms. It can eliminate inappropriate information or spam automatically, for instance. The description and hashtags that grab the reader's attention are among the most critical aspects of a social media post's success. Typically, individuals generate multiple captions and hashtags before selecting the optimal content for a post. Occasionally, they employ content writers, which requires time, effort, and money. The suggested method makes correct captions and hashtags using conventional neural networks (CNN) trained on image datasets containing captions
Pouya Khomand, Malihe Sabeti, Reza Boostani, Ehsan Moradi, Mahmoud Odeh, and Mohammad Rasmi AL-Mousa
IEEE
Skeletal bone age assessment (SBAA) is very important for both sides of parents and physicians to evaluate the irregular growth of children. SBAA process is carried out by radiologists who visually inspect the radiology image of the left hand according to the Greulich and Pyle (GP) or the Tanner-Whitehouse 2 (TW2) methods. However, human eyes have their own limitations and therefore the visual inspection procedure by radiologist involves a degree of error and also intra personal variability. To address these drawbacks, a deep learning-based approach is proposed here to precisely act on these X-ray images. The employed database contains 1391 X-ray left-hand image from Los Angeles children's hospital and 200 left hand x-ray image from different age and gender from Iranian children from Namazi hospital of Shiraz. Our results demonstrate the efficiency of proposed model (mean absolute error of 0.89) in this field.
Mooad Al-Shalout, Khalid Mansour, Khaled E. Al-Qawasmi, and Mohammad Rasmi
IEEE
One of Jordan's most significant agricultural crops is the date palm tree. The high level of interest in date palm farming is a result of the crop's superior economic viability when compared to other agricultural crops; Jordan's annual investments in this sector are expected to be more than $500 million. Recently, the Jordanian ministry of agriculture reported that many trees are vulnerable to damage because of several diseases related to date palms. In this study, the convolutional neural network (CNN) and support vector machine (SVM) algorithms are used to detect and classify date palm diseases. Four common diseases are considered in this paper: bacterial blight, brown spots, leaf smut, and white scales. The palm farms in the northern Jordan Valley, Kaggle, the National Center for Agricultural Research, and other sources provided the dataset used in this study. The experimental results show that CNN is effective mechanism for detecting and classifying Date Palm disease especially when large dataset is used in training the algorithm.
Alireza Kazemi, Reza Boostani, Mahmoud Odeh, and Mohammad Rasmi AL-Mousa
IEEE
Support Vector Machine (SVM) is originally a binary large-margin classifier emerged from the concept of structural risk minimization. Multiple solutions such as one-versus-one and one-versus-all have been proposed for creating multi-class SVM using elementary binary SVMs. Also multiple solutions have been proposed for SVM model selection, adjusting margin-parameter C and the Gaussian kernel variance. Here, an improved classifier named SVM-SVM is proposed for multi-class problems which increases accuracy and decreases dependency to margin-parameter selection. SVM-SVM adopts two K-class one-vs-one SVMs in a cascaded two-layer structure. In the first layer, input features are fed to one-vs-one SVM with non-linear kernels. We introduce this layer as a large-margin non-linear feature transform that maps input feature space to a discriminative K*(K-1)/2 dimensional space. To assess our hierarchical classifier, some datasets from the UCI repository are evaluated. Standard one-vs-one SVM and one-vs-one fuzzy SVM are used as reference classifiers in experiments. Results show significant improvements of our proposed method in terms of test accuracy and robustness to the model (margin and kernel) parameters in comparison with the reference classifiers. Our observations suggest that a multi-layer (deep) SVM structures can gain the same benefits as is seen in the deep neural nets (DNNs).
Fahimeh Jamshidian Tehrani, Behrooz Nasihatkon, Khaled Al-Qawasmi, Mohammad Rasmi Al-Mousa, and Reza Boostani
IEEE
This study aims at designing an efficient combinatorial classifier, which fuses linear discriminant analysis (LDA) and kernel support vector machine (SVM) classifiers. The proposed method is called kernel SVM-LDA which benefits from global property of LDA, simultaneous with localized capability of SVM along with mapping ability of RBF kernel to project input data into a more separable high dimensional space. To assess the proposed scheme, Kernel SVM-LDA was applied to some standard datasets derived from UCI database and then compared to standard LDA and kernel SVM classifiers. Kernel SVM-LDA was also employed in cue-based brain computer interface to classify the left and right imagery movements. The results indicate that the introduced method is more superior to that of LDA and kernel SVM because it surpasses the counterparts in terms of robustness, complexity and performance.
Ghassan Samara, Mohammed Bhaa Eid, Mohammad Aljaidi, Sattam Almatarneh, Mohammad Rasmi, Raed Alazaideh, and Yasser Al-Lahham
IEEE
Recently, the Vehicular Ad Hoc Network, or VANET, has emerged as the most essential topic for researchers and the automobile industry to discuss in order to enhance the level of safety enjoyed by road users. Users of VANET need to be able to access both safety-related and non-safety-related apps. In this paper, we offer sixteen different kinds of attacks, as well as potential defenses against them.
Mohammad Rasmi Al-Mousa, Qutaiba Al-Zaqebah, Ala'a Saeb Al-Sherideh, Mohammed Al-Ghanim, Ghassan Samara, Sattam Al-Matarneh, and Mahmoud Asassfeh
IEEE
The examination of digital forensic evidence is a science highlighting the main areas of progress in forensic science. Various social media sites (SNS) providing e-mail services, messages, pictures, and videos have brought about a huge explosion in development. In recent times, Digital Forensics has expanded to be used in all institutions and companies, especially financial companies, pharmaceutical companies, and investment companies. With this electronic development, criminal activities have dramatically increased to obtain and steal data for personal or international interests or the so-called data theft. Therefore, the biggest challenge lies in protecting this information from theft and searching for digital forensic evidence so that the digital evidence is correct and sound from a forensic point of view. Against this, this paper provides a detailed review of the most important Android applications in digital forensics to attain, retrieve, and compare information altogether.
Ala Mughaid, Ahmed Al-Arjan, M. Rasmi and Shadi Alzu'bi
Communication methods in the world are constantly evolving, this means that the amounts of data sent through open networks are in populated quantities, so there must be means to protect that data sent, and this could be done by information protection systems by encryption and coding of the data in order to protect the content of that data sent. The main aim of encrypting and encoding data is to protect the integrity of the data, and also to ensure the confidentiality of the data source, this is done through the use of algorithms for encryption and encoding the data, with the aim of changing its content using those algorithms and returning its original content with the same algorithms used to encrypt it, through a symmetric secret key for encryption and decryption. In this paper, the researcher highlights the weakness of the basic RC4 algorithm, which lies in the stability of the key used in scheduling the key, as a prelude to generating the stream keys used in serial byte encryption, so the RC4-Pr algorithm was modified by adding an additional permutation function by performing a key permutation operation to produce a different key in each 16-bytes (128-bits) cipher round.