Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206487,
        author = {Mohammed Sadath P and Dr R. Kaviyarasi},
        title = {Agentic AI, SHAP and LIME for Cyber Threat Pre-emption: Emerging Paradigms in Intelligent Cybersecurity},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {1751-1755},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206487},
        abstract = {The increasing complexity and sophistication of cyber threats have challenged conventional cybersecurity approaches that primarily rely on reactive detection and response mechanisms. The emergence of Artificial Intelligence (AI)-driven cybersecurity has introduced new possibilities for predictive and preventive defence strategies. Among recent technological developments, Agentic Artificial Intelligence (Agentic AI), combined with explainable artificial intelligence (XAI) techniques such as SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations), represents a transformative approach for cyber threat preemption. Unlike traditional AI systems that perform isolated analytical tasks, Agentic AI possesses autonomous decision-making capabilities, enabling continuous monitoring, adaptive learning, threat anticipation, and automated defensive actions. However, the increasing adoption of autonomous AI systems introduces challenges related to transparency, accountability, reliability, and ethical governance. This article examines the role of Agentic AI, SHAP, and LIME in advancing cyber threat preemption by enabling early identification, interpretation, and mitigation of emerging cyber risks. It explores how autonomous AI agents enhance threat intelligence, anomaly detection, vulnerability assessment, and incident response. Furthermore, the study analyses the importance of explainability frameworks such as SHAP and LIME in improving trust, interpretability, and accountability within AI-driven cybersecurity systems. The article argues that integrating autonomous AI agents with explainable machine learning techniques can establish a proactive cybersecurity ecosystem capable of anticipating threats before significant damage occurs. Future cybersecurity frameworks must prioritise human-AI collaboration, ethical AI governance, and transparent decision-making to ensure secure and responsible deployment of intelligent cyber defence systems.},
        keywords = {Agentic AI, Explainable Artificial Intelligence, SHAP, LIME, Cyber Threat Preemption, Cybersecurity, Machine Learning, Threat Intelligence, AI Governance.},
        month = {July},
        }