Copyright © 2025 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{151897,
        author = {Akarsh Srivastava and Mayank Sharma and Faraj Chishti},
        title = {MALWARE DETECTION USING MACHINE LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {8},
        number = {1},
        pages = {1170-1177},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=151897},
        abstract = {Zero-day or dull malware are made utilizing code befuddling techniques that pass down similar handiness of parent yet with various engravings. Malevolent programming, inferred as malware, is dependably making security danger, thus enormous areas of examination. The basic stage in unmistakable confirmation is evaluation. This consolidates either static or dynamic appraisal of known malware and performing isolation. Results of evaluation are refined into a "signature". One methodology for malware affirmation is the utilization of static engravings to survey programs after they are stacked and before execution. Authentic structures subject to AI are used to find plans identifying with malignant lead). Unusually, deterministic etchings are generally evolved through human expert appraisal. Standard malware domain strategies – both static and dynamic – are executed  in programming. In this, we battle against unadulterated programming executions both thinking about their overhead and the going with trust in dealing with base (TCB) swell. Copilot can see certain part level rootkits by checking if these portrayals contrast from their ordinary characteristics},
        keywords = {Zero-day malware, Machine Learning, Sandbox, Feature Extraction, Heuristic Analysis, Model Training},
        month = {},
        }