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{195829,
        author = {Desai Prashanth Mudiraj and G. Manish Reddy and Ch. Veda Yeshwanth and R. Kanif Naik and A. Sandhya Rani},
        title = {XAI-Sec: A Unified Explainable AI Framework for Intrusion Detection and Malware Classification},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {1009-1016},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195829},
        abstract = {The rapid increase in cyber threats has created a strong demand for security systems that are not only accurate but also transparent and interpretable. Traditional machine learning-based Intrusion Detection Systems (IDS) often operate as black-box models, which makes it difficult for security analysts to understand how decisions are made and respond effectively to potential threats. To address this limitation, this paper proposes XAI-Sec, an advanced cybersecurity framework that combines machine learning techniques with explainable artificial intelligence (XAI) methods. The proposed system performs both multi-class intrusion detection and malware classification while providing clear explanations using SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-Agnostic Explanations). The model is evaluated using the NSL-KDD dataset for intrusion detection along with a curated dataset for malware analysis, achieving high performance with 99.2% accuracy in intrusion detection and 98.7% in malware classification while maintaining interpretability. In addition, a Security Operations Center (SOC) dashboard is developed to support real-time monitoring and provide meaningful insights into detected threats, thereby reducing alert fatigue and improving analyst efficiency. The results demonstrate that integrating XAI techniques enhances trust, improves decision-making, and maintains strong detection performance. Furthermore, the proposed system aligns with modern regulatory requirements such as GDPR and emerging AI governance standards, making it suitable for deployment in real-world cybersecurity environments.},
        keywords = {Explainable AI, Intrusion Detection System, Malware Detection, SHAP, LIME, Cybersecurity, Machine Learning Interpretability, Network Security, Threat Analysis},
        month = {April},
        }