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{206849,
        author = {Shreya and Harishma K V and Nisha K and Nishan M C and Varsha K},
        title = {Network Anomaly Detection Using Machine Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {no},
        pages = {693-701},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206849},
        abstract = {The development of new Cyber Security threats will create challenges for Network Security which requires a dependable system that can track and study network irregularities to protect communication infrastructure. The use of traditional Anomaly Detection systems which base their detection methods on signature-based attacks will result in high False Positive rates and delayed threat detection because they cannot identify new and evolving attack patterns. The Automatic Anomaly Detection System that we developed in our invention needs to use Machine Learning algorithms for its network anomaly detection functions which will use manual packet input and continuous monitoring of network traffic to identify malicious activities. Our Network Anomaly Detection System uses multiple models including KNN RNN and LSTM which can classify Network Traffic into Normal or Anomalous states while we collect real-time network traffic through Scapy Python Network Scapy Libraries which allows us to monitor the network without external applications and tools. The Anomaly Detection Recommendation system provides end users with threat mitigation recommendations which include descriptions of new attacks that the system has detected. Our system testing results show that the LSTM Model outperformed all other models because it achieved better accuracy results with fewer false positives during anomaly detection compared to the models used in this system. The system aims to conduct.},
        keywords = {anomaly detection, network intrusion detection, machine learning, deep learning, LSTM, RNN, real-time network monitoring, network security},
        month = {July},
        }