Camilo, Rojas and Yuki, Sato and Eleanor, Bennett (2024) AI-DRIVEN THREAT INTELLIGENCE: ENHANCING CYBERSECURITY IN MODERN SOFTWARE SYSTEMS. Journal of Adaptive Learning Technologies, 1 (8). pp. 53-68. ISSN 2997-3902

Text AI-DRIVEN THREAT INTELLIGENCE ENHANCING.pdf Download (332kB)

Abstract

The increasing complexity and sophistication of cyberattacks pose significant risks to modern software systems, demanding advanced security mechanisms beyond traditional rule-based approaches. Recent studies indicate that global cybercrime damages are projected to reach $10.5 trillion annually by 2025, with over 493 million ransomware attacks reported in 2022 alone. These escalating threats underscore the need for intelligent, adaptive, and proactive defense strategies. Artificial Intelligence (AI)-driven threat intelligence has emerged as a transformative approach for enhancing cybersecurity resilience, enabling real-time detection, automated response, and predictive analytics. Leveraging machine learning, natural language processing, and deep learning, AI systems can analyze vast volumes of unstructured and structured threat data, identify anomalous behaviors, and uncover zero-day vulnerabilities with higher accuracy than conventional methods. Empirical findings show that AI-based detection models achieve up to 95% accuracy in identifying malware variants, compared to 85% in traditional signature-based systems. Furthermore, Gartner predicts that by 2027, 60% of organizations will rely on AI-augmented threat intelligence platforms to support security operations. This paper explores the role of AI in threat intelligence, highlighting its contributions to proactive threat hunting, automated incident response, and adversarial resilience. Additionally, it discusses challenges such as adversarial AI, data privacy, and model explainability, while proposing a framework for integrating AI-driven intelligence into modern software systems. The findings suggest that AI not only enhances detection speed and precision but also establishes a scalable and adaptive cybersecurity paradigm, essential for safeguarding digital infrastructures in the evolving threat landscape.

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:	27 Sep 2025 12:08
Last Modified:	27 Sep 2025 12:08
URI:	http://eprints.umsida.ac.id/id/eprint/16393

Actions (login required)

View Item