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{189781,
        author = {Ms. Shivani S. Konde and Dr. V. B. Gadicha and Dr. P. P. Pawade},
        title = {A Comprehensive Review on Intrusion Detection Systems Using Hybrid Machine Learning and Heuristic Techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {413-420},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189781},
        abstract = {In the rapidly maturing digital landscape, it has become a major source of concern to guarantee network security because of the increasing complexity of cyber-attacks. Conventional Intrusion Detection Systems (IDS) often struggle to manage the professional categorisation of original and multidimensional attack patterns. On the one hand, this paper proposes that an Interruption Detection System (IDS) with heuristic operations can be enhanced with mixture machine learning (ML) techniques to enhance the accuracy of the system and its flexibility and speed of discovery. The suggested prototype integrates both monitored and unmonitored learning procedures, integrating the advantages of algorithms providing random forest, Support Vector Machine (SVM), and K-Means clustering. The assortment of features is optimised as opposed to heuristic algorithms to reclaim the organisation's competence and minimise the computational upstairs. Normal datasets such as NSL-KDD and UNSW-NB15 are used to test the system, and presentation measures that include correctness, exactness, recall, and F1-score are evaluated. It is also shown by its trial outcomes that the hybrid heuristic can substantially recover the functions of intrusion discovery acts that are comparable to the old-fashioned ML IDS. The solution proposed has a solid and scalable solution to detect anomalies in real-time, which leads to the creation of intelligent and responsive cybersecurity systems.},
        keywords = {—Intrusion Detection System (IDS); Hybrid Machine Learning; Heuristic Approach; Network Security; Anomaly Detection;},
        month = {January},
        }