Network Attacks and its Harm on the Security and Privacy of Network "Intrusion Detection" Machine Learning Algorithms
| المصدر: | المجلة العربية للنشر العلمي |
|---|---|
| الناشر: | مركز البحث وتطوير الموارد البشرية - رماح |
| المؤلف الرئيسي: | Al-Dosary, Abrar Ali Naseer (Author) |
| مؤلفين آخرين: | Hamad, Nader Omar Fadl Al-Sayed (Co-Author) |
| المجلد/العدد: | ع68 |
| محكمة: | نعم |
| الدولة: |
الأردن |
| التاريخ الميلادي: |
2024
|
| الشهر: | حزيران |
| الصفحات: | 510 - 523 |
| ISSN: |
2663-5798 |
| رقم MD: | 1547303 |
| نوع المحتوى: | بحوث ومقالات |
| اللغة: | الإنجليزية |
| قواعد المعلومات: | EduSearch, HumanIndex |
| مواضيع: | |
| رابط المحتوى: |
عدد مرات التحميل
1
| المستخلص: |
Intrusion detection system can identify attacks in a variety of situations while plays a vital role in preventing data or information from being misused. Over the years, Intrusion Detection Systems (IDS) have proven to be an effective technology for achieving security by identifying malicious actions. we propose a learning supervised and unsupervised algorithms as (RF ,SVM , Naïve Bayes and AdaBoost) to extract and classify intrusion detection data sets, KDDCup99 and the NSL KDD where they found as the most usable cited. An experiment was performed to compare the performance of several machine learning methods. The results demonstrate the most accurate strategy in terms of detection rate and false alarm rate. The RF algorithm gives the best accuracy with the two datasets but it needs one of the highest values for building model. RF gives minimum classifier errors. In addition, using the unsupervised learning, the K-means gives the best results by overall factors. The results obtained from the code in the classification process also show that the random forests recorded the best accuracy. RF gives the minimum classifier errors .While NP records the lowest value in the accuracy of the results and the highest in the emergence of errors. These results are better than those obtained in the scientific paper for R. Ravipati And A. Munther[13]. |
|---|---|
| ISSN: |
2663-5798 |
عناصر مشابهة
-
Network Intrusion Detection: Machine Learning Algorithm
بواسطة: Alsoqour, Kholoud Ali منشور: (2024) -
Combining Multiple Supervised Machine Learning Algorithms to Detect Network Intrusion Attempts
بواسطة: Al Haji, Helmi Naem منشور: (2021) -
Analysis of Botnet Distributed Denial of Service Attack of IOT Devices Using Machine Learning Classifiers and Sequential Detection Architecture
بواسطة: مخاتره، معتز فواز منشور: (2021) -
Classification Adaptation Model for Network Intrusion Detection
بواسطة: AL Hinai, Ghaniya Zahran Abdullah منشور: (2021) -
Intrusion Detection Using Machine Learning and Feature Selection Based on Enhancing Chernobyl Disaster Optimizer Algorithm
بواسطة: الشبلي، إبراهيم موسى منشور: (2024)
