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{202562,
        author = {P.Pavani and Satish Dekka and S.Kamal Kumar and V.Jahnavi and S.Sirisha},
        title = {Traffic-Aware Adaptive Intrusion Detection System for Dynamic Network Conditions},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {12},
        pages = {7343-7359},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=202562},
        abstract = {The Intrusion Detection System is an indispensable component in ensuring security in computer networks. At present, due to the rapidly growing complexity of networks, it becomes challenging to detect any kind of intrusion accurately. Most intrusion detection systems rely on using a single algorithmic approach to differentiate between normal and suspicious network activities. Despite achieving satisfactory results under some conditions, such an approach loses its effectiveness in different situations caused by varying network traffic conditions. Cases of predominant normal traffic, sudden attacks, or complex network conditions can reduce the accuracy of such a method and raise the number of false positives. Therefore, this paper suggests an adaptive approach for intrusion detection systems to deal with dynamic conditions in computer networks. It involves using multiple machine learning and deep learning approaches, including decision trees, random forests, convolutional neural networks (CNNs), long short-term memory (LSTM), and hybrid CNN-LSTMs. Common intrusion detection datasets will be used for analysis in order to measure the effectiveness of each methodical approach and replicate various network traffic conditions. Then, based on the achieved accuracy, precision, recall, and false positive results, the optimal solution will be chosen. The experimental results demonstrate that the adaptive method enhances detection accuracy, reduces the false alarm rate, and fortifies the overall robustness of the system in comparison to traditional static intrusion detection systems. This problem can be solved well by using the adaptive model.},
        keywords = {Intrusion Detection Systems, Network Security, Adaptive Detection, Machine Learning, Deep Learning, Convolutional Neural Networks, Long Short-Term Memory},
        month = {May},
        }