Mohamad Khayat

Dr. Mohamad Khayat

CIT, United Arab Emirates University, Al Ain, United Arab Emirates
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
23 January 2025 in IEEE Access
Verified
Journal Article
Open access
Mohamad KhayatMohamad Khayat
Mohamad Khayat
EBEzedin Barka
Ezedin Barka
MSMohamed Adel Serhani
Mohamed Adel Serhani
Farag SallabiFarag Sallabi
Farag Sallabi
Khaled ShuaibKhaled Shuaib
Khaled Shuaib
HKHeba Moustafa Khater
Heba Moustafa Khater
Organizational cybersecurity relies heavily on security operation centers (SOCs) to protect businesses and institutions from emerging cyber threats. In recent years, the complexity and sophistication of cyber threats have increased, pushing SOCs to their limits. As a result, SOCs struggle to address the evolving threat landscape due to their reliance on isolation technologies and reactive strategies. However, advanced technologies, such as artificial intelligence (AI) and machine learning (ML), have the potential to revolutionize SOCs by enhancing threat identification and response capabilities, as well as predicting and preempting risks. To address these challenges and highlight the full potential of SOC, this study provides a detailed overview through a comprehensive literature review that identifies gaps in existing research and examines the latest technologies used in the SOC environment to help address different operational and technical challenges and bring out their capabilities. Various methods, ranging from automated incident response and behavioral analytics to neural networks and deep learning, have been classified and compared. In addition, an in-depth reference architectural model, which is a blueprint for SOC integrating AI and ML into SOCs, is introduced. The proposed model provides a structured framework for implementation and offers insights into different SOC components and their interactions. Moreover, this systematic review emphasizes the benefits of these technologies for enhancing security operations. Finally, a case study is presented to describe the function of ML-and AI-powered SOC components to achieve optimum security. This paper concludes by discussing additional challenges and future research directions that may help advance the cybersecurity sector and provide insights into improving SOCs.

26 July 2021 in Electronics
Verified
Journal Article
Open access
PDF file
EBEzedin Barka
Ezedin Barka
Sofiane DahmaneSofiane Dahmane
Sofiane Dahmane
Chaker Abdelaziz KerracheChaker Abdelaziz Kerrache
Chaker Abdelaziz Kerrache
Mohamad KhayatMohamad Khayat
Mohamad Khayat
Farag SallabiFarag Sallabi
Farag Sallabi
Healthcare professionals and scholars have emphasized the need for IoT-based remote health monitoring services to track the health of the elderly. Such systems produce a large amount of data, necessitating the security and privacy of that data. On the other hand, Software Defined Networking (SDN) integration could be seen as a good solution to guarantee both flexibility and efficiency of the network which is even more important in the case of healthcare monitoring. Furthermore, Blockchain has recently been proposed as a game-changing tool that can be integrated into the Internet of Things (IoT) to have the optimal level of security and privacy. However, incorporating Blockchain into IoT networks, which rely heavily on patients’ health sensors, is extremely difficult. In this paper, a secure Healthcare Monitoring System (HMS) is proposed with a focus on trust management issues. The architecture seeks to protect multiple healthcare monitoring system components and preserves patient privacy by developing a security interface where separate security modules can be integrated to run side by side to ensure reliable HMS. The security framework architecture we propose takes advantage of the blockchain technology as a secure and timely information back-end. STHM is a proposal that uses Software-Defined Networking (SDN) as the communication medium that allows users to access SDN’s different functional and security technologies and services. Simulation results show that the use of Blockchain for the SDN-based healthcare monitoring can ensure the desired flexibility and security for a very lightweight additional overhead.

30 May 2024 in IEEE Access
Verified
Journal Article
Open access
HKHeba Moustafa Khater
Heba Moustafa Khater
Farag SallabiFarag Sallabi
Farag Sallabi
MSMohamed Adel Serhani
Mohamed Adel Serhani
EBEzedin Barka
Ezedin Barka
Khaled ShuaibKhaled Shuaib
Khaled Shuaib
Mohamad KhayatMohamad Khayat
Mohamad Khayat
Cyber-physical systems (CPS) are recognized for their intelligence as they seamlessly interact with humans, enhancing the physical world through computation, communication, and control. Over the last few years, the evolution of CPS, including IoT components, has significantly impacted many facets of people’s lifestyles. It has been immersed in a wide range of services and applications in various areas, including manufacturing, healthcare, and energy. However, the interrelationship between the cyber and physical worlds gives rise to a multitude of research problems and challenges. In the healthcare field, for instance, CPS introduces complexities related to interoperability, privacy, data security, and real-time data processing with critical implications for the reliability and safety of medical processes. To address these challenges and harness the full potential of CPS in healthcare, this paper, through a comprehensive literature review, aims to discuss cutting-edge CPS technologies and solutions that hold promise for healthcare applications. To this end, we propose a comprehensive architectural model that can serve as a benchmark for implementing CPS in healthcare applications. This model thoroughly details how services, components, and technologies can be integrated to transform massive raw data collected from the physical world into valuable information for an enhanced decision-making process. Finally, a use case on healthcare CPS is presented, outlining its characteristics, the role that different technologies have played in its development, and the major challenges in implementing such systems successfully. This study provides a cohesive understanding of the role CPS can play in empowering healthcare while offering insights into the challenges, and future research trends.

12 May 2025 in IEEE Access
Verified
Journal Article
Open access
Mohamad KhayatMohamad Khayat
Mohamad Khayat
EBEzedin Barka
Ezedin Barka
MSMohamed Adel Serhani
Mohamed Adel Serhani
Farag SallabiFarag Sallabi
Farag Sallabi
Khaled ShuaibKhaled Shuaib
Khaled Shuaib
HKHeba Moustafa Khater
Heba Moustafa Khater
Intrusion detection in Internet of Things (IoT) networks is essential to identify and mitigate security breaches and unauthorized access to connected devices. As IoT devices continue to advance, securing interconnected systems against malicious attacks is essential to ensure data privacy, system integrity, and user safety. However, traditional intrusion detection systems (IDSs) often struggle to adapt to novel and evolving threats. Developing a system that can autonomously learn and enhance intrusion detection capabilities to effectively identify and mitigate emerging threats is challenging. To address this issue, we propose a reinforcement learning (RL)–based approach for enhancing cybersecurity in IoT networks. First, various preprocessing techniques such as handling missing values, outliers, and min-max scaling normalization were applied. Then, domain-specific features related to network traffic patterns, including packet size distribution, packet count, and packet rate, were extracted. Statistical measures, including mean, variance, and entropy, were calculated from these features to determine temporal and spatial variations in the network data. Moreover, deep learning models, including long short-term memory networks and convolutional neural networks (CNNs), were used to automatically extract high-level features from raw data such as network logs or sensor readings. The extracted feature sets were concatenated within a feature fusion layer that enabled efficient dimensionality reduction via principal component analysis. A hybrid optimization approach was also introduced for feature selection using green anaconda optimization and the chaotic learning osprey optimization algorithm. Furthermore, an RL-based IDS (RL-IDS) that incorporates RNNs and autoencoders with a deep Q-network was proposed to enhance threat detection. Experimental outcomes emphasize the superiority of the method, obtaining 99.45% accuracy with 70% training data and 99.80% with 80%. Precision and F-measure are 99.99% and 99.89%, respectively, outperforming current models like CNN, DNN, LSTM, and GAN-DRL, while efficiently reducing false positives and false negatives.

3 February 2025 in IEEE Access
Verified
Journal Article
Open access
Mohamad KhayatMohamad Khayat
Mohamad Khayat
EBEzedin Barka
Ezedin Barka
MSMohamed Adel Serhani
Mohamed Adel Serhani
Farag SallabiFarag Sallabi
Farag Sallabi
Khaled ShuaibKhaled Shuaib
Khaled Shuaib
HKHeba Moustafa Khater
Heba Moustafa Khater
As the field of cybersecurity has experienced continual changes, up-to-date techniques have become increasingly necessary to analyze and defend against threats. Furthermore, the current methods consistently produce false alarms and sometimes completely miss real threats. This paper proposes an approach that integrates secure blockchain technology with data preprocessing, deep learning, and reinforcement learning to enhance threat detection and response capabilities. To secure the exchange of threat intelligence information, a safe blockchain network is used, which comprises Byzantine Fault Tolerance for high data integrity and Zero-Knowledge Proofs for access control. All relevant information is cleaned and standardized prior to analysis. Subsequently, graph convolutional neural networks with autoencoders are trained on large unlabeled sets of threat data to automatically label various types of threats, with the system employing fuzzy logic to rank and score possible threats. Furthermore, we implemented a feedback loop that incorporates reinforcement learning, thereby improving model performance over time according to guidance provided by cybersecurity specialists.

26 August 2025 in IEEE Open Journal of the Communications Society
Verified
Journal Article
Open access
Mohamad KhayatMohamad Khayat
Mohamad Khayat
EBEzedin Barka
Ezedin Barka
MSMohamed Adel Serhani
Mohamed Adel Serhani
Farag SallabiFarag Sallabi
Farag Sallabi
Khaled ShuaibKhaled Shuaib
Khaled Shuaib
HKHeba Moustafa Khater
Heba Moustafa Khater
The emergence of new and more sophisticated threats in cybersecurity has necessitated the improvement of security information and event management (SIEM) systems. The previous versions of these security models faced numerous challenges, such as high false-positive and false-negative rates, resulting in extensive unnecessary alerts or failure to identify real threats. This study discusses the use of attention-based models for improving the performance of SIEM systems via an ensemble deep learning framework. To this end, several types of neural networks, such as long short-term memory networks, convolutional neural networks, and bidirectional recurrent neural networks, were used in this framework. The resulting model could assess temporal patterns and significant characteristics from network data. To reduce processing complexity and improve detection accuracy, an attention mechanism was used to let the model focus on the most relevant parts of the input data. Additionally, alert prioritization was integrated using fuzzy logic to rank threats based on factors such as the confidence level, impact, and frequency of alerts, ensuring the more efficient handling of potential intrusions. An optimized ensemble strategy was developed that incorporated different optimization methods to achieve high precision and speed, making the model more robust against contemporary cybersecurity challenges. Experiment results show that the new approach performs much better than other existing models. By splitting the training data into 70% and 30%, the model achieved an accuracy of 98.52%, precision of 99.40%, F-measure of 97.08% and a false negative rate (FNR) of only 1.14%. When the training data was split into 80% and 20%, the model improved its accuracy to 99.28%, precision to 99.46%, F-measure to 98.67% and had a false positive rate (FPR) of just 0.1%. Experiments revealed that the proposed model successfully detected and effectively prioritized intrusions more effectively than other models while maintaining higher accuracy rates and lower false alarm levels.