Imaxe de Portada

AI-Driven Cybersecurity Testing: Redefining Quality Engineering Through Adversarial Simulation and Threat Modeling

Gardado en:
Publicado en:International Journal of Communication Networks and Information Security vol. 17, no. 4 (2025), p. 27-49
Autor Principal: Kathiresan, Gopinath
Publicado:
Kohat University of Science and Technology (KUST)
Materias:
Computer program integrity
Machine learning
Software
Simulation
Threats
Artificial intelligence
Network security
Organizations
Damping
Cybersecurity
Engineering
Malware
Algorithms
Automation
Threat models
Cybercrime
Real time
Acceso en liña:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Engadir etiqueta
Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!
Resumo:Artificial intelligence (Al) is rewriting the book on how organizations do security testing, threat modeling, and quality engineering in the rapidly changing world of cybersecurity. Traditional methods of defense against cyberattacks are becoming insufficient as cyberattacks are becoming more complex and numerous. With its implementation, Al-powered cybersecurity testing brings a paradigm shift as it provides real-time threat detection, automated vulnerability assessment, and proactive defense mechanisms using machine learning and data analytics. This article explores how Al can be integrated into cybersecurity frameworks, especially for adversarial simulation and Al to supplement threat modeling. This explains how these superior methodologies pinpoint system vulnerabilities and emulate actual penetrations to assist organizations in avoiding and damping off agreeable breaches. A further discussion on how quality engineering contributes to modern cybersecurity sounds off and how Al-powered testing reinforces the resilience and integrity of software and systems during the development lifecycle. The article also explores the tools and technologies that enable Al-driven security and compares them as a basis for selecting implementation methods for enterprises. Implementation strategies are provided that are practical, as well as workforce training requirements and common organizational challenges encountered with evidence and ways of overcoming them. We analyze the ethical implications of providing transparency and fairness in decisions and propose responsible Al governance.
ISSN:2073-607X
2076-0930
Fonte:Science Database