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{199028,
        author = {Raj  Vibhuti Singh and Manjesh Tiwari and Utkarsh tiwari and Prof Tarunima Mukherjee},
        title = {A Hybrid Machine Learning Framework for Real-Time Malware Detection Using PE Feature Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {11925-11931},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199028},
        abstract = {The conventional malware detection systems are based on signature-based methods that cannot work against zero-day attacks and advanced evasion methods. The current paper describes CyberGuardX (Cerberus-AI CyberShield), a multi-modal malware detection system with a combination of a static analysis, machine learning classification, explainable artificial intelligence (XAI), and real-time monitoring functionalities. The system uses Random Forest classifiers which are trained with deep static features which are found on PE files, PDFs and document formats with 99.9% accuracy in malware detection. One of the major advances is the incorporation of SHAP (SHapley Additive explanations) as a method of transparent decision-making, which solves the problem of the black box of AI-based security systems. The framework includes VirusTotal API integration as an external threat intelligence, real-time file system monitoring, and a full web-based dashboard to support a security analyst. Performance analysis proves to be highly effective with better detection percentage more than the traditional signature-based systems having response times, less than 2.3 seconds to complete analysis processes. Its containerized deployment and scalable batch processing architecture is relevant to enterprise security operations centers (SOCs).},
        keywords = {Malware Detection, Explainable AI, Machine Learning, Static Analysis, SHAP, Cybersecurity, Threat Intelligence, Real-time Monitoring.},
        month = {April},
        }