Mohammad Arafah
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mohammad Arafah has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Ahmad Aladawi
Loughborough University, UK
6 shared publications Asma Adnane
3 shared publications- Louay Karadsheh
University of Petra, Jordan
3 shared publications - Mohammad Alauthman
University of Petra, Jordan
3 shared publications - Abedal-Kareem Al-Banna
University of Petra, Jordan
2 shared publications - Faisal Aburub
University of Petra
2 shared publications
Latest Publications
- Open Access
- 1 December 2026
- Published by KEAI Publishing in International Journal of Cognitive Computing in Engineering
- Vol. 7, 376-388
Enhancing web of things security using Harris hawks optimization with reinforcement learning
- 1 December 2026
- Published by KEAI Publishing in International Journal of Cognitive Computing in Engineering
- Vol. 7, 376-388
Open AccessEnhancing web of things security using Harris hawks optimization with reinforcement learning
- 18 September 2025
- Published by IGI Global Scientific Publishing
- p. 281-314
Reinforcement Learning for Adaptive Healthcare
The chapter explores the conditioning of Deep Q Networks (DQNs) and computational intelligence for changing the healthcare decision making. We study the role of reinforcement learning for sequential optimization of clinical decisions in different kinds of healthcare domains. Innovations regarding application of DQNs in complex medical environments as well as the theoretical foundations of DQNs are presented. This paper shows how these technologies transform clinical decision supporting systems, predictive analytics, disease diagnosis, personalized treatment optimization as well as IoT-enabled patient monitoring. Demonstrating wide spread implementation in settings of chronic disease management, critical care and diagnostic pathways results in very substantial improvements of clinical outcomes over traditional approaches.
- 18 September 2025
- Published by IGI Global Scientific Publishing
- p. 281-314
Reinforcement Learning for Adaptive Healthcare
The chapter explores the conditioning of Deep Q Networks (DQNs) and computational intelligence for changing the healthcare decision making. We study the role of reinforcement learning for sequential optimization of clinical decisions in different kinds of healthcare domains. Innovations regarding application of DQNs in complex medical environments as well as the theoretical foundations of DQNs are presented. This paper shows how these technologies transform clinical decision supporting systems, predictive analytics, disease diagnosis, personalized treatment optimization as well as IoT-enabled patient monitoring. Demonstrating wide spread implementation in settings of chronic disease management, critical care and diagnostic pathways results in very substantial improvements of clinical outcomes over traditional approaches.
- 12 September 2025
- Published by IGI Global Scientific Publishing
- p. 1-30
AI and Machine Learning Integration in Modern Business Intelligence
In this chapter, the author goes on to describe how artificial intelligence (AI) and machine learning (ML) technologies are integrated into current business intelligence (BI) architectures to improve their operational efficiency. As business intelligence systems become more and more widely recognized for their strategic value of making decisions based on data, those systems are evolving to add in the advanced analytical capabilities. This chapter discusses such architectural concerns, implementation challenges and emerging best practices to be thought about while embedding AI and ML effectively into BI ecosystems. Focusing on the empirical research and industry case studies, we analyze how those technologies change the instance of operational intelligence by making it possible to predict, automate and discover of new underlying patterns by complex business data.
- 12 September 2025
- Published by IGI Global Scientific Publishing
- p. 1-30
AI and Machine Learning Integration in Modern Business Intelligence
In this chapter, the author goes on to describe how artificial intelligence (AI) and machine learning (ML) technologies are integrated into current business intelligence (BI) architectures to improve their operational efficiency. As business intelligence systems become more and more widely recognized for their strategic value of making decisions based on data, those systems are evolving to add in the advanced analytical capabilities. This chapter discusses such architectural concerns, implementation challenges and emerging best practices to be thought about while embedding AI and ML effectively into BI ecosystems. Focusing on the empirical research and industry case studies, we analyze how those technologies change the instance of operational intelligence by making it possible to predict, automate and discover of new underlying patterns by complex business data.
- 18 July 2025
- Published by IGI Global Scientific Publishing
- p. 1-30
Children in Digital Spaces Safety, Privacy, and Protection in the Age of AI
In this chapter, I examine the extraordinary changes in the digital media brought to us by the artificial intelligence technologies, examining at once both the phenomenal indeed unprecedented opportunities they open up, and the huge ethical challenges they arise with. The chapter also serves a crucial role in examining the challenges related to privacy, misinformation, addiction and the protection of the most vulnerable users, especially children, in such processes of creation, curation, distribution and consumption of content, led by AI. The focus is on the integration of parental consent mechanisms along with the child engagement within enhanced digital protection protocols, investigating how current and future artificial intelligence, machine learning technologies can assist in monitoring and minimizing online by cyberbullying, fraud, harassment, trafficking and illicit recruitment efforts. Written for policymakers, technology creators, parents, educators, and law enforcement agencies.
- 18 July 2025
- Published by IGI Global Scientific Publishing
- p. 1-30
Children in Digital Spaces Safety, Privacy, and Protection in the Age of AI
In this chapter, I examine the extraordinary changes in the digital media brought to us by the artificial intelligence technologies, examining at once both the phenomenal indeed unprecedented opportunities they open up, and the huge ethical challenges they arise with. The chapter also serves a crucial role in examining the challenges related to privacy, misinformation, addiction and the protection of the most vulnerable users, especially children, in such processes of creation, curation, distribution and consumption of content, led by AI. The focus is on the integration of parental consent mechanisms along with the child engagement within enhanced digital protection protocols, investigating how current and future artificial intelligence, machine learning technologies can assist in monitoring and minimizing online by cyberbullying, fraud, harassment, trafficking and illicit recruitment efforts. Written for policymakers, technology creators, parents, educators, and law enforcement agencies.
- 23 May 2025
- Published by IGI Global Scientific Publishing
- p. 179-226
AI for Threat Intelligence Integration in Cybersecurity Insurance
In this chapter, natural barriers of combining artificial intelligence and the threat intelligence in cybersecurity insurance framework for cyber risk quantification and transfer are discussed as fundamentals. We evaluate it in terms transforming capabilities of the insurance value chain around machine learning, natural language processing, and predictive analytics. The architectures of data ingestion, AI processing, contextual analysis, and insurance application consist structured way to make the mean of the threat data with considerable insurance insights. We provide empirically validated proof of quantitatively better accuracy in underwriting and prevention of losses, where participating insurers reduce loss ratios by 12.3% below their competitors. We characterize implementation challenges to be data limitations, organizational silos, regulatory constraints and propose governance approaches that aim balance the ethical concerns with innovation.
- 23 May 2025
- Published by IGI Global Scientific Publishing
- p. 179-226
AI for Threat Intelligence Integration in Cybersecurity Insurance
In this chapter, natural barriers of combining artificial intelligence and the threat intelligence in cybersecurity insurance framework for cyber risk quantification and transfer are discussed as fundamentals. We evaluate it in terms transforming capabilities of the insurance value chain around machine learning, natural language processing, and predictive analytics. The architectures of data ingestion, AI processing, contextual analysis, and insurance application consist structured way to make the mean of the threat data with considerable insurance insights. We provide empirically validated proof of quantitatively better accuracy in underwriting and prevention of losses, where participating insurers reduce loss ratios by 12.3% below their competitors. We characterize implementation challenges to be data limitations, organizational silos, regulatory constraints and propose governance approaches that aim balance the ethical concerns with innovation.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 71-98
Generative AI and the Evolving Threat Landscape
This comprehensive guide studies the transformative impact of generative artificial intelligence (AI) on the cybersecurity landscape, analyzing both offensive capabilities and defensive mechanisms. The research makes findings from recent empirical studies and technical analyses to provide a systematic understanding of emerging threats and countermeasures. Through analysis of several attack methodologies, vulnerability patterns, and defense strategies, this study reveals that AI-enabled attacks have achieved disturbing success rates, with social engineering campaigns signifying up to 89% authenticity ratings and automated exploit generation showing 87% effectiveness against traditional defenses.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 71-98
Generative AI and the Evolving Threat Landscape
This comprehensive guide studies the transformative impact of generative artificial intelligence (AI) on the cybersecurity landscape, analyzing both offensive capabilities and defensive mechanisms. The research makes findings from recent empirical studies and technical analyses to provide a systematic understanding of emerging threats and countermeasures. Through analysis of several attack methodologies, vulnerability patterns, and defense strategies, this study reveals that AI-enabled attacks have achieved disturbing success rates, with social engineering campaigns signifying up to 89% authenticity ratings and automated exploit generation showing 87% effectiveness against traditional defenses.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 123-142
AI-Powered Social Engineering and Impersonation Attacks
This chapter presents a comprehensive analysis of advanced social engineering attack vectors enhanced by Generative Artificial Intelligence (GenAI) technologies, focusing on impersonation methodologies and synthetic content generation. The research employs a systematic evaluation framework to analyze attack patterns leveraging Large Language Models (LLMs) and deepfake architectures within social engineering campaigns. Through quantitative analysis, we investigate the efficacy of GenAI-driven phishing content, examining success rates, behavioral patterns, and attack sophistication metrics across multiple enterprise environments. The study presents empirical evidence demonstrating a 45% increase in attack effectiveness when leveraging AI-driven impersonation techniques compared to traditional methods. Our primary contribution encompasses the development and validation of novel detection methodologies and defensive frameworks engineered for AI-enhanced social engineering threats.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 123-142
AI-Powered Social Engineering and Impersonation Attacks
This chapter presents a comprehensive analysis of advanced social engineering attack vectors enhanced by Generative Artificial Intelligence (GenAI) technologies, focusing on impersonation methodologies and synthetic content generation. The research employs a systematic evaluation framework to analyze attack patterns leveraging Large Language Models (LLMs) and deepfake architectures within social engineering campaigns. Through quantitative analysis, we investigate the efficacy of GenAI-driven phishing content, examining success rates, behavioral patterns, and attack sophistication metrics across multiple enterprise environments. The study presents empirical evidence demonstrating a 45% increase in attack effectiveness when leveraging AI-driven impersonation techniques compared to traditional methods. Our primary contribution encompasses the development and validation of novel detection methodologies and defensive frameworks engineered for AI-enhanced social engineering threats.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 235-276
Detection and Analysis of AI-Generated Malicious Content
Generative artificial intelligence (AI) technologies are advancing rapidly and, for the first time, pose unprecedented cybersecurity challenges with sophisticated AI-generated malicious content. While these technologies are amazing, they create huge security risks when weaponized to perform cyber attacks. To bridge the critical gap of detecting and analyzing AI-generated malicious content, this research develops comprehensive detection and forensic analysis frameworks. The goal of the study is to develop techniques for identifying, profiling, and analyzing AI-generated threats using advanced pattern recognition and machine learning techniques. The research methodology includes the development of statistical models to distinguish between human and AI-generated malicious content, the implementation of real-time neural network-based detection systems, and the creation of forensic analysis protocols.
- 2 May 2025
- Published by IGI Global Scientific Publishing
- p. 235-276
Detection and Analysis of AI-Generated Malicious Content
Generative artificial intelligence (AI) technologies are advancing rapidly and, for the first time, pose unprecedented cybersecurity challenges with sophisticated AI-generated malicious content. While these technologies are amazing, they create huge security risks when weaponized to perform cyber attacks. To bridge the critical gap of detecting and analyzing AI-generated malicious content, this research develops comprehensive detection and forensic analysis frameworks. The goal of the study is to develop techniques for identifying, profiling, and analyzing AI-generated threats using advanced pattern recognition and machine learning techniques. The research methodology includes the development of statistical models to distinguish between human and AI-generated malicious content, the implementation of real-time neural network-based detection systems, and the creation of forensic analysis protocols.
- 28 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
An Efficient and Explainable Machine Learning Framework for Alzheimer's Disease Detection
Alzheimer's disease detection is of paramount importance as it is a global health problem in terms of early detection, interventions, and management. The study applies prominent machine learning classification to Alzheimer's disease by integrating longitudinal and cross-sectional data analysis. With careful correlation analysis, we derived the following important predictive features: ‘M/F’, ‘Age’, ‘Education’, ‘SES’, ‘CDR’, ‘MMSE’, ‘eTIV’, ‘nWBV’, ‘ASF’, and ‘Hand’. In this study, the entire dataset was divide into training (80%) and testing (20%) sets, with eight machine learning models implemented on it for classification: CatBoost-CB, Logistic Regression-LR, Extreme Gradient Boosting-XGB, Support Vector Machine-SVM, Random Forest-RF, K-Nearest Neighbors-KNN, Decision Tree-DT, and Gradient Boosting-GB. Our results demonstrated superior performance from ensemble models, with RF, XGB, GB, DT, and CB achieving 98.1% accuracy, 98.2% precision, and 98.1% recall. These models showed exceptional performance with a Kappa score of 0.95, indicating strong reliability in classification. We have also used LIME explainability to enhance model transparency, providing insight into the contribution of different features in support of the interpretability of the model. In this study, we stress the power of machine learning for early detection of Alzheimer's disease, and provide future research directions on improving the predictive accuracy and transparency of predictive models.
- 28 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
An Efficient and Explainable Machine Learning Framework for Alzheimer's Disease Detection
Alzheimer's disease detection is of paramount importance as it is a global health problem in terms of early detection, interventions, and management. The study applies prominent machine learning classification to Alzheimer's disease by integrating longitudinal and cross-sectional data analysis. With careful correlation analysis, we derived the following important predictive features: ‘M/F’, ‘Age’, ‘Education’, ‘SES’, ‘CDR’, ‘MMSE’, ‘eTIV’, ‘nWBV’, ‘ASF’, and ‘Hand’. In this study, the entire dataset was divide into training (80%) and testing (20%) sets, with eight machine learning models implemented on it for classification: CatBoost-CB, Logistic Regression-LR, Extreme Gradient Boosting-XGB, Support Vector Machine-SVM, Random Forest-RF, K-Nearest Neighbors-KNN, Decision Tree-DT, and Gradient Boosting-GB. Our results demonstrated superior performance from ensemble models, with RF, XGB, GB, DT, and CB achieving 98.1% accuracy, 98.2% precision, and 98.1% recall. These models showed exceptional performance with a Kappa score of 0.95, indicating strong reliability in classification. We have also used LIME explainability to enhance model transparency, providing insight into the contribution of different features in support of the interpretability of the model. In this study, we stress the power of machine learning for early detection of Alzheimer's disease, and provide future research directions on improving the predictive accuracy and transparency of predictive models.
- 25 April 2025
- Published by IGI Global Scientific Publishing
- p. 133-160
Theoretical Frameworks for Zero-Knowledge Proof Integration in Autonomous Defense Systems
The proposed research presents a theoretical investigation into the integration of zero-knowledge proofs (ZKP) within autonomous defense architectures, establishing rigorous mathematical foundations for privacy-preserving security verification in next-generation cybersecurity systems. This study addresses fundamental theoretical challenges in autonomous security verification by developing novel mathematical constructs that enable privacy-preserving proof generation and verification while maintaining formal security guarantees. The research methodology encompasses the development of formal mathematical models for non-interactive zero-knowledge proof systems optimized for autonomous verification environments. These models extend existing theoretical frameworks by introducing novel constructs for proof composition and verification in distributed systems, with particular emphasis on formal security properties including completeness, soundness, and zero-knowledge characteristics.
- 25 April 2025
- Published by IGI Global Scientific Publishing
- p. 133-160
Theoretical Frameworks for Zero-Knowledge Proof Integration in Autonomous Defense Systems
The proposed research presents a theoretical investigation into the integration of zero-knowledge proofs (ZKP) within autonomous defense architectures, establishing rigorous mathematical foundations for privacy-preserving security verification in next-generation cybersecurity systems. This study addresses fundamental theoretical challenges in autonomous security verification by developing novel mathematical constructs that enable privacy-preserving proof generation and verification while maintaining formal security guarantees. The research methodology encompasses the development of formal mathematical models for non-interactive zero-knowledge proof systems optimized for autonomous verification environments. These models extend existing theoretical frameworks by introducing novel constructs for proof composition and verification in distributed systems, with particular emphasis on formal security properties including completeness, soundness, and zero-knowledge characteristics.