Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 01018 | |
Number of page(s) | 7 | |
Section | Traffic Prediction and Analysis | |
DOI | https://doi.org/10.1051/itmconf/20257001018 | |
Published online | 23 January 2025 |
A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection
School of Computer Science, Shanghai University, 200444 Shanghai, China
Corresponding author: 1014875532@qq.com
With the continuous advancement of Internet technology, cybersecurity threats are growing more urgent as attack techniques become increasingly sophisticated. Conventional intrusion detection systems struggle to address these emerging threats because they depend heavily on predefined signatures and rules. This research centers on the use of advanced machine learning methods, particularly Support Vector Machines (SVM) and K-Nearest Neighbors (KNN), to improve the detection of network attack traffic. The UNSW-NB15 dataset, which includes various attack types and normal traffic patterns, is used to evaluate the performance of these two models. The results indicate that the SVM model excels in handling high-dimensional and intricate data, demonstrating its capability to tackle the complexity of modern cyber threats. On the other hand, KNN proves to be more efficient and straightforward when applied to less complex data structures. The outcomes of this study provide significant insights into enhancing cybersecurity systems, with recommendations for refining machine learning models to better address emerging threats. Moreover, the research highlights future directions to strengthen the resilience and precision of network intrusion detection systems, ensuring the development of more effective defenses against the ever-evolving landscape of cybersecurity risks.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.