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{191865,
        author = {Priya Yadav and Trisha Sharma and Himanshi Naval},
        title = {Detecting Network Attacks Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {12},
        number = {no},
        pages = {207-210},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=191865},
        abstract = {As technology continues to evolve, the number of devices connected to the internet is increasing at an exponential rate. This rapid growth has made modern networks more complex and, consequently, more vulnerable to cyberattacks.
Ensuring network security has therefore become a critical research priority. Traditional Intrusion Detection Systems (IDS) depend heavily on predefined rules and signature-based methods, which struggle to detect novel or previously unseen attacks. To overcome these limitations, Machine Learning (ML) offers an intelligent and adaptive approach capable of identifying hidden patterns, learning from network behavior, and detecting anomalies that may indicate malicious activity.
This paper explores the application of various ML techniques in detecting network attacks, comparing the performance of algorithms such as Decision Trees, Random Forests, Support Vector Machines (SVM), K-Nearest Neighbors (KNN), and Deep Neural Networks. It also analyzes how supervised, unsupervised, and hybrid learning models can enhance detection accuracy and reduce false alarms. Emphasis is placed on critical factors like dataset quality, feature selection, model training, and real-time adaptability to ensure robust performance in dynamic environments.
Furthermore, the study discusses the challenges faced by ML-based IDS, including data imbalance, high computational costs, and the need for continuous learning to handle evolving attack patterns. The paper concludes with recommendations for future research, highlighting the potential of deep learning, ensemble methods, and federated learning in developing more scalable, autonomous, and efficient network security systems. By leveraging ML, this research aims to pave the way for next-generation intrusion detection systems capable of defending against the ever-changing landscape of cyber threats.},
        keywords = {Intrusion Detection System, Network Security, Machine Learning, Anomaly Detection, Deep Learning, Cybersecurity.},
        month = {},
        }