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{198342,
        author = {Ruchita Kundle and Vaishnavi Kumari and Pravartika Bhagat and Siddhi Jagtap},
        title = {Machine Learning in Cybersecurity for Threat Detection and Future Attack Prediction},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {8606-8610},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=198342},
        abstract = {This paper presents an experimental study on machine learning techniques applied to cybersecurity for software threat detection and future attack prediction. Five algorithms — Decision Tree, Random Forest, SVM, KNN, and Neural Network (MLP) — were implemented and evaluated on the NSL-KDD benchmark dataset comprising 125,973 training samples and 22,544 test samples across 41 features. Binary classification was performed to distinguish normal network traffic from attack traffic. Results show that Decision Tree achieved the best F1-Score of 77.81% with 78.85% accuracy, while SVM recorded the highest precision at 97.57%. All models exhibited consistently high precision (>96%) with recall as the primary differentiating metric. Findings indicate that ML significantly improves intrusion detection over traditional signature-based methods, and future directions include class balancing, deep learning integration, and adversarial robustness.},
        keywords = {Cybersecurity, Decision Tree, Intrusion Detection System, Machine Learning, NSL-KDD, Predictive Analysis, Random Forest, Support Vector Machine, Threat Detection.},
        month = {April},
        }