Louay Karadsheh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Louay Karadsheh has a total of 5 co-authors. Here are the top co-authors by number of shared publications:
- Mohammad Arafah
University of Petra, Jordan
3 shared publications - Ahmad AlMughrabi
Universitat de Barcelona
1 shared publication - Ahmad Aladawi
Loughborough University, UK
1 shared publication - Faisal Aburub
University of Petra
1 shared publication - Sabreen Alhariri
Arab International University, Syria
1 shared publication
Latest Publications
- 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.
- 25 April 2025
- Published by IGI Global Scientific Publishing
- p. 439-464
Cybersecurity for Autonomous Electric Vehicles (EVs)
In this chapter, we study the implementation and effectiveness of AI-driven deception technologies for autonomous defense systems consisting of intelligent honeypots and adaptive decay mechanisms. It studies the ability of machine learning algorithms to make deceptive environments undetectable while being intelligent to capture valuable threat intelligence. The methodology includes the development of dynamic honeypot architectures that are suitable for their behaviors using reinforcement learning in response to attackers. The main areas of investigation include employing generative adversarial networks in designing conceivable system environments, developing the real‐time analysis of attacker behavior patterns, and creating the underlying autonomous decision‐making in deceptive response strategies. Empirical evidence from real-world implementations is provided to show that AI-driven deception can significantly decrease the success attack rates and enhance threat intelligence gathering
- 25 April 2025
- Published by IGI Global Scientific Publishing
- p. 439-464
Cybersecurity for Autonomous Electric Vehicles (EVs)
In this chapter, we study the implementation and effectiveness of AI-driven deception technologies for autonomous defense systems consisting of intelligent honeypots and adaptive decay mechanisms. It studies the ability of machine learning algorithms to make deceptive environments undetectable while being intelligent to capture valuable threat intelligence. The methodology includes the development of dynamic honeypot architectures that are suitable for their behaviors using reinforcement learning in response to attackers. The main areas of investigation include employing generative adversarial networks in designing conceivable system environments, developing the real‐time analysis of attacker behavior patterns, and creating the underlying autonomous decision‐making in deceptive response strategies. Empirical evidence from real-world implementations is provided to show that AI-driven deception can significantly decrease the success attack rates and enhance threat intelligence gathering
- 11 April 2025
- Published by IGI Global Scientific Publishing
- p. 137-156
Formal Verification Theory for AI-Driven Autonomous Defense Systems
This paper investigates how the formal verification methods handle AI autonomous defense system usage through current industry trends. AI deployment within military operations shows a changing trend that makes current standard system verification approaches inadequate to maintain secure system performance. The paper evaluates model checking and theorem proving methods and their combination for AI component verification in addition to their advantages and limitations. The essay examines major concerns about AI system models through insights into operational timing constraints together with AI system complexity and indeterminate characteristics and threats to cybersecurity capabilities. Edge computing technologies applied to IoT systems introduce new validation requirements that need distributed system-specific approaches. This paper examines how measuring performance and blockchain-based architecture verification collectively enhance system protection through discussion of goal and objectives.
- 11 April 2025
- Published by IGI Global Scientific Publishing
- p. 137-156
Formal Verification Theory for AI-Driven Autonomous Defense Systems
This paper investigates how the formal verification methods handle AI autonomous defense system usage through current industry trends. AI deployment within military operations shows a changing trend that makes current standard system verification approaches inadequate to maintain secure system performance. The paper evaluates model checking and theorem proving methods and their combination for AI component verification in addition to their advantages and limitations. The essay examines major concerns about AI system models through insights into operational timing constraints together with AI system complexity and indeterminate characteristics and threats to cybersecurity capabilities. Edge computing technologies applied to IoT systems introduce new validation requirements that need distributed system-specific approaches. This paper examines how measuring performance and blockchain-based architecture verification collectively enhance system protection through discussion of goal and objectives.