A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection
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 r...
Saved in:
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2025-01-01
|
| Series: | ITM Web of Conferences |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_01018.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1825206581721038848 |
|---|---|
| author | Han Zhuoxi |
| author_facet | Han Zhuoxi |
| author_sort | Han Zhuoxi |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-9ea76f0d5d8f412981a16f7980cc69c9 |
| institution | Kabale University |
| issn | 2271-2097 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj-art-9ea76f0d5d8f412981a16f7980cc69c92025-02-07T08:21:10ZengEDP SciencesITM Web of Conferences2271-20972025-01-01700101810.1051/itmconf/20257001018itmconf_dai2024_01018A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic DetectionHan Zhuoxi0School of Computer Science, Shanghai UniversityWith 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.https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_01018.pdf |
| spellingShingle | Han Zhuoxi A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection ITM Web of Conferences |
| title | A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection |
| title_full | A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection |
| title_fullStr | A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection |
| title_full_unstemmed | A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection |
| title_short | A Comparative Analysis of Support Vector Machine and K-Nearest Neighbors Models for Network Attack Traffic Detection |
| title_sort | comparative analysis of support vector machine and k nearest neighbors models for network attack traffic detection |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2025/01/itmconf_dai2024_01018.pdf |
| work_keys_str_mv | AT hanzhuoxi acomparativeanalysisofsupportvectormachineandknearestneighborsmodelsfornetworkattacktrafficdetection AT hanzhuoxi comparativeanalysisofsupportvectormachineandknearestneighborsmodelsfornetworkattacktrafficdetection |