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{204984,
        author = {Vinit Venkanna Guglot and Gourav Pramod Kumbhare and Sarang Vinod Channe and Yash Anand Ghotekar and Dikshant Vilas Fulzele and Prof.Sachin dhawas},
        title = {AI-Based Network Threat Detection using Wavelet Transform},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {5641-5648},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204984},
        abstract = {— Artificial Intelligence and Machine Learning have become crucial technologies for securing modern networks and managing data traffic over the internet. However, the increasing sophistication of cyber-attacks creates significant security challenges, such as unauthorized access and network intrusions. This project, titled “AI-Based Network Threat Detection using Wavelet Transform,” focuses on developing an advanced machine learning-based intrusion detection system to identify malicious activities by leveraging signal processing techniques.
The proposed system uses the Discrete Wavelet Transform (DWT) to decompose complex network traffic data into multi-resolution time-frequency coefficients, allowing the system to isolate anomalies and sudden traffic fluctuations from normal behaviour. Publicly available benchmark datasets, such as NSL-KDD and CICIDS2017, are utilized for training and evaluating the system's performance. The project aims to improve threat detection accuracy and reduce false alarms by combining wavelet-based feature extraction with intelligent machine learning classifiers.
The system is implemented in a local development environment using Python and Visual Studio Code (VS Code) for academic purposes. It does not perform live intrusion detection on real-time networks but demonstrates the practical application of signal processing and machine learning in network security. The project helps in understanding advanced feature engineering pipelines and the implementation of machine learning techniques in cybersecurity applications.},
        keywords = {Artificial Intelligence, Network Threat Detection, Discrete Wavelet Transform (DWT), Feature Extraction, Machine Learning, Visual Studio Code (VS Code), Cybersecurity Simulation.},
        month = {June},
        }