Priya, Sharma and Michael, Anderson and Ahmed, Al-Khafaji (2025) Generative AI for Cybersecurity: Detecting Zero-Day Vulnerabilities and Advanced Persistent Threats in Cloud-Native Systems. Best Journal of Innovation in Science, Research and Development, 4 (9). pp. 196-215. ISSN 2835-3579

Text Generative AI for Cybersecurity Detecting Zero-Day.pdf Download (784kB)

Abstract

The increasing adoption of cloud-native architectures has amplified the complexity and scale of cybersecurity challenges, particularly in detecting zero-day vulnerabilities and advanced persistent threats (APTs). Traditional security tools, while effective against known exploits, often fail to anticipate novel attack vectors that leverage the dynamic and distributed nature of containerized and microservices-based systems. This article explores the transformative potential of generative artificial intelligence (AI) in fortifying cloud-native cybersecurity. We examine how generative models can autonomously simulate attack scenarios, synthesize threat intelligence, and uncover previously unseen vulnerabilities before exploitation occurs. Furthermore, we highlight the role of generative AI in identifying subtle patterns indicative of stealthy APT activities, which typically evade conventional anomaly detection methods. By integrating generative AI into cloud-native security pipelines, organizations can shift from reactive defense to proactive resilience, thereby reducing detection latency and strengthening overall system integrity. The discussion concludes with practical considerations, challenges, and future research directions for operationalizing generative AI in real-world security environments.

Item Type:	Article
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Postgraduate > Master's of Islamic Education
Depositing User:	Journal Editor
Date Deposited:	03 Oct 2025 12:40
Last Modified:	03 Oct 2025 12:40
URI:	http://eprints.umsida.ac.id/id/eprint/16410

Actions (login required)

View Item