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{205692,
        author = {Yasotha S and B. Ananthi and K.Soniyalakshmi},
        title = {ADVANCED ANOMALY DETECTION FOR INTELLIGENT ZERO-DAY INTRUSION MITIGATION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {8173-8179},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=205692},
        abstract = {The rapid growth of network-based applications has led to an increase in the sophistication and frequency of cyberattacks, creating significant challenges for conventional network security solutions. Traditional signature-based Intrusion Detection Systems (IDS) are often ineffective against zero-day and emerging threats because they depend on predefined attack signatures. To address this limitation, this study presents an intelligent anomaly-based intrusion detection framework capable of identifying both known and unknown network intrusions by detecting deviations from normal network behavior. Machine learning algorithms are utilized to learn traffic patterns from network flow data and accurately classify network activities. The CICIDS2017 dataset is employed for experimental evaluation due to its realistic representation of both benign and malicious network traffic in modern environments. Comprehensive data preprocessing and feature optimization techniques are applied to improve detection performance and minimize false positive rates. Experimental results indicate that the proposed framework achieves high classification accuracy, maintains stable performance across various traffic categories, and effectively detects anomalous activities. In addition, the system demonstrates strong scalability and efficiency in processing large-scale network traffic, making it well suited for real-time intrusion detection and proactive zero-day threat mitigation in contemporary network environments.},
        keywords = {Intrusion Detection System (IDS), Anomaly-Based Detection, Zero-Day Attack Mitigation, Network Security, Machine Learning, Network Traffic Analysis, CICIDS2017 Dataset, Behavioral Modeling, Cyber Threat Detection.},
        month = {June},
        }