Abdullah Ibrahim Alzahrani

Dr. Abdullah Ibrahim Alzahrani

Shaqra University, Riyadh, Ar Riyāḑ, Saudi Arabia
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
30 April 2023 in Sensors
Verified
Journal Article
Open access
PDF file
EAEman Abdullah Aldakheel
Eman Abdullah Aldakheel
MZMohammed Zakariah
Mohammed Zakariah
GGGhada Abdalaziz Gashgari
Ghada Abdalaziz Gashgari
FAFahdah Almarshad
Fahdah Almarshad
AAAbdullah Ibrahim Alzahrani
Abdullah Ibrahim Alzahrani
Organizations and individuals worldwide are becoming increasingly vulnerable to cyberattacks as phishing continues to grow and the number of phishing websites grows. As a result, improved cyber defense necessitates more effective phishing detection (PD). In this paper, we introduce a novel method for detecting phishing sites with high accuracy. Our approach utilizes a Convolution Neural Network (CNN)-based model for precise classification that effectively distinguishes legitimate websites from phishing websites. We evaluate the performance of our model on the PhishTank dataset, which is a widely used dataset for detecting phishing websites based solely on Uniform Resource Locators (URL) features. Our approach presents a unique contribution to the field of phishing detection by achieving high accuracy rates and outperforming previous state-of-the-art models. Experiment results revealed that our proposed method performs well in terms of accuracy and its false-positive rate. We created a real data set by crawling 10,000 phishing URLs from PhishTank and 10,000 legitimate websites and then ran experiments using standard evaluation metrics on the data sets. This approach is founded on integrated and deep learning (DL). The CNN-based model can distinguish phishing websites from legitimate websites with a high degree of accuracy. When binary-categorical loss and the Adam optimizer are used, the accuracy of the k-nearest neighbors (KNN), Natural Language Processing (NLP), Recurrent Neural Network (RNN), and Random Forest (RF) models is 87%, 97.98%, 97.4% and 94.26%, respectively, in contrast to previous publications. Our model outperformed previous works due to several factors, including the use of more layers and larger training sizes, and the extraction of additional features from the PhishTank dataset. Specifically, our proposed model comprises seven layers, starting with the input layer and progressing to the seventh, which incorporates a layer with pooling, convolutional, linear 1 and 2, and linear six layers as the output layers. These design choices contribute to the high accuracy of our model, which achieved a 98.77% accuracy rate.

8 June 2023 in Electronics
Verified
Journal Article
Open access
PDF file
AAAbdullah Ibrahim Alzahrani
Abdullah Ibrahim Alzahrani
SCSajjad Hussain Chauhdary
Sajjad Hussain Chauhdary
AAAbdulrahman A. Alshdadi
Abdulrahman A. Alshdadi
Wastewater management is a mechanism that is used to extract and refine pollutants from wastewater or drainage that can be recycled to the water supply with minimal environmental effects. New methods and techniques are required to ensure safe and smart wastewater management systems in smart cities because of the present deteriorating environmental state. Wireless sensor networks and the Internet of Things (IoT) represent promising wastewater treatment technologies. The elaborated literature survey formulates a conceptual framework with an Internet of Things (IoT)-based wastewater management system in smart cities (IoT-WMS) using blockchain technology. Blockchain technology is now being used to store information to develop an incentive model for encouraging the reuse of wastewater. Concerning the quality and quantity of recycled wastewater, tokens are issued to households/industries in smart cities. Nevertheless, this often encourages tampering with the information from which these tokens are awarded to include certain rewards. Anomaly detector algorithms are used to identify the possible IoT sensor data which has been tampered with by intruders. The model employs IoT sensors together with quality metrics to measure the amount of wastewater produced and reused. The simulation analysis shows that the proposed method achieves a high wastewater recycling rate of 96.3%, an efficiency ratio of 88.7%, a low moisture content ratio of 32.4%, an increased wastewater reuse of 90.8%, and a prediction ratio of 92.5%.

27 September 2023 in IEEE Access
Verified
Journal Article
Open access
FAFahdah Almarshad
Fahdah Almarshad
GGGhada Abdalaziz Gashgari
Ghada Abdalaziz Gashgari
AAAbdullah Ibrahim Alzahrani
Abdullah Ibrahim Alzahrani
Credit card use poses a significant security issue on a global scale, with rule-based algorithms and traditional anomaly detection being two of the most often used methods. However, they are resource-intensive, time-consuming, and erroneous. Given fewer instances than legal payments, the dataset imbalance has become a serious issue. On the other hand, the generative technique is considered an effective way to rebalance the imbalanced class issue, as this technique balances both minority and majority classes before the training. In a more recent period, GAN is considered one of the most popular data generative techniques, as it is used in significant data settings. Hence, the research under study explores a classification system to detect fraudulent credit card transactions that are being trained using the European Cardholders 2013 dataset. It has 30 features, 28 of which are hidden due to sensitive information. Fraud activity accounts for less than 1% of the entire transaction volume of $284807. Additionally, GANs is a generative model based on game theory, in which a generator G and a discriminator D compete with one another. The generator’s goal is to make the discriminator uncertain. Distinguishing between instances from the generator and those from the original dataset is the discriminator’s goal, and we can increase classifiers’ discriminating strength by training GANs on a set of fraudulent credit card transactions. According to the outcome, our model outperformed the earlier experiments with an AUC score of 0.999. Additionally, it creates artificial data using GANs, enabling the production of a sizable volume of high-quality data. In terms of innovation and performance, this technique substantially improves over earlier research.

3 December 2022 in Electronics
Verified
Journal Article
Open access
PDF file
AAAbdullah Ibrahim Alzahrani
Abdullah Ibrahim Alzahrani
AAAmal Alrasheed
Amal Alrasheed
AKAmel Ksibi
Amel Ksibi
MAManel Farouk ayadi
Manel Farouk ayadi
MAMashael Asiri
Mashael Asiri
MZMohammed Zakariah
Mohammed Zakariah
Devices which are part of the Internet of Things (IoT) have strong connections; they generate and consume data, which necessitates data transfer among various devices. Smart gadgets collect sensitive information, perform critical tasks, make decisions based on indicator information, and connect and interact with one another quickly. Securing this sensitive data is one of the most vital challenges. A Network Intrusion Detection System (IDS) is often used to identify and eliminate malicious packets before they can enter a network. This operation must be done at the fog node because the Internet of Things devices are naturally low-power and do not require significant computational resources. In this same context, we offer a novel intrusion detection model capable of deployment at the fog nodes to detect the undesired traffic towards the IoT devices by leveraging features from the UNSW-NB15 dataset. Before continuing with the training of the models, correlation-based feature extraction is done to weed out the extra information contained within the data. This helps in the development of a model that has a low overall computational load. The Tab transformer model is proposed to perform well on the existing dataset and outperforms the traditional Machine Learning ML models developed as well as the previous efforts made on the same dataset. The Tab transformer model was designed only to be capable of handling continuous data. As a result, the proposed model obtained a performance of 98.35% when it came to classifying normal traffic data from abnormal traffic data. However, the model’s performance for predicting attacks involving multiple classes achieved an accuracy of 97.22%. The problem with imbalanced data appears to cause issues with the performance of the underrepresented classes. However, the evaluation results that were given indicated that the proposed model opened new avenues of research on detecting anomalies in fog nodes.

13 December 2022 in Diagnostics
Verified
Journal Article
Open access
PDF file
AAAmal Alrasheed
Amal Alrasheed
AKAmel Ksibi
Amel Ksibi
MAManel Farouk ayadi
Manel Farouk ayadi
AAAbdullah Ibrahim Alzahrani
Abdullah Ibrahim Alzahrani
MZMohammed Zakariah
Mohammed Zakariah
NHNada Ali Hakami
Nada Ali Hakami
Skin cancer is one of the most severe forms of the disease, and it can spread to other parts of the body if not detected early. Therefore, diagnosing and treating skin cancer patients at an early stage is crucial. Since a manual skin cancer diagnosis is both time-consuming and expensive, an incorrect diagnosis is made due to the high similarity between the various skin cancers. Improved categorization of multiclass skin cancers requires the development of automated diagnostic systems. Herein, we propose a fully automatic method for classifying several skin cancers by fine-tuning the deep learning models VGG16, ResNet50, and ResNet101. Prior to model creation, the training dataset should undergo data augmentation using traditional image transformation techniques and Generative Adversarial Networks (GANs) to prevent class imbalance issues that may lead to model overfitting. In this study, we investigate the feasibility of creating dermoscopic images that have a realistic appearance using Conditional Generative Adversarial Network (CGAN) techniques. Thereafter, the traditional augmentation methods are used to augment our existing training set to improve the performance of pre-trained deep models on the skin cancer classification task. This improved performance is then compared to the models developed using the unbalanced dataset. In addition, we formed an ensemble of finely tuned transfer learning models, which we trained on balanced and unbalanced datasets. These models were used to make predictions about the data. With appropriate data augmentation, the proposed models attained an accuracy of 92% for VGG16, 92% for ResNet50, and 92.25% for ResNet101, respectively. The ensemble of these models increased the accuracy to 93.5%. A comprehensive discussion on the performance of the models concluded that using this method possibly leads to enhanced performance in skin cancer categorization compared to the efforts made in the past.

9 November 2023 in IEEE Access
Verified
Journal Article
Open access
FAFahdah Almarshad
Fahdah Almarshad
MZMohammed Zakariah
Mohammed Zakariah
GGGhada Abdalaziz Gashgari
Ghada Abdalaziz Gashgari
EAEman Abdullah Aldakheel
Eman Abdullah Aldakheel
AAAbdullah Ibrahim Alzahrani
Abdullah Ibrahim Alzahrani
Android malware security tools that can swiftly identify and categorize various malware classes to create rapid response strategies have been trendy in recent years. Although many application fields have demonstrated the usefulness of implementing Machine Learning and deep learning methods to provide automation and self-learning services, the scarcity of data for malware samples has been cited as a hurdle in creating efficient deep learning-based solutions. In this paper, a one-shot learning-based Siamese neural network is proposed to overcome this issue, as it can both identify malware assaults and categorize malware into multiple categories. The Drebin dataset, which is divided into benign and harmful components, is used in our suggested methodology. The efficiency of the suggested strategy is evaluated through a database dataset made up of 9476 goodware applications and 5560 Android malware apps. The five critical phases of its implementation are pre-processing, data partitioning, model architecture, training, and assessment. In both the training and testing phases, Siamese networks are trained to rank sample similarity, and the accuracy is determined using N-way one-shot tasks. According to the experiment’s findings, our Siamese Shot model fared better than the other standard approaches, obtaining an accuracy of 98.9%. Additionally, the most well-liked platforms are Keras and TensorFlow.