Intrusion Detection Systems Based on Machine Learning Algorithms

Amanoul, Sandy Victor; Abdulazeez, Adnan Mohsin; Zeebare, Diyar Qader; Ahmed, Falah Y. H.

doi:10.1109/i2cacis52118.2021.9495897

Cited by 25 publications

(9 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It comprises of a massive number of decision trees, often known as estimators as shown in figure 8. Each node in the tree is taught to make its predictions using a separate set of observations [31]. The random forest's final predictions are then calculated by averaging the forecasts of each tree.It is solved by eqs.…”

Section: Fig 8 Random Forest Architecture [31]mentioning

confidence: 99%

WITHDRAWN: Fake News Detection Using Ensemble Techniques

Malhotra

Malik

2023

Preprint

View full text Add to dashboard Cite

Fake news is misinformation or distorted news that is spread over social media with the intent of harming an individual, organization, or government body. Collecting news from an internet platform is simple because it is quick, user-friendly, and constantly updated. However, this information is also subject to personal preferences or interests, which can negatively affect individuals or organizations. As a result, it is critical to detect the spread of fake news by computational methods. Semantic web approaches also plays an important role in detecting false news since they are used to understand the data that is available online in the same manner that humans do. As a result, this research examined various learning models for classifying whether the information is true or false using a fake and real news dataset. Around 40,000 items were analyzed, including approximately 20,000 from each fake and actual news dataset. Ensemble learning models such as support vector machine, logistic regression, CatBoost, XgBoost, multinomial, Naive Bayes, and random forest were used and evaluated using recall, accuracy, false rejection rate (FRR), F1 score, precision, negative predictive value (NPV), false discovery rate (FDR), and Matthews' correlation coefficient. Based on these evaluations, the best learning models were hybridized and computed alongside the passive-aggressive classifier and deep Auto_ViML model. Following computation, it was determined that the deep Auto_ViML model had the highest accuracy, precision, recall, and F1 score of 99%. In contrast, the hybrid learning model had the best value of false rejection rate of 71%. In comparison, the support vector machine was computed in 0.000245 seconds.

show abstract

Section: Fig 8 Random Forest Architecture [31]mentioning

confidence: 99%

WITHDRAWN: Fake News Detection Using Ensemble Techniques

Malhotra

Malik

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…For feature selection in IDS, Correlation Feature Selection (CFS) and BestFirst search have been merged, resulting in reduced feature dimensions while maintaining excellent detection accuracy [4]. To increase classification performance and reduce false positive rates, hybrid approaches combining machine learning algorithms with heuristic methods for feature selection have also been developed [12].…”

Section: Related Workmentioning

confidence: 99%

Enhancing Cybersecurity: Innovative Hybrid Feature Selection for Intrusion Detection

Guntoro,

Lisnawita,

Costaner

2024

Proceedings of the 2nd International Conference on Environmental, Energy, and Earth Science, ICEEES 2023, 30 October 2023, Peka

View full text Add to dashboard Cite

Network security has evolved into a major issue that necessitates careful consideration in the present digital world. Intrusion Detection Systems (IDS) are critical in detecting and preventing network intrusions. In this work, we propose a feature selection and majority vote based intrusion detection method. Using the Majority Voting approach, an intrusion detection system with many models is created. The proposed method was tested using the NSL-KDD benchmark dataset. To improve the model's performance, we combined the BestFirst search strategy with the Correlation Feature Selection (CFS) technique. This strategy successfully reduced the number of available features from 41 to 12 while maintaining detection accuracy. The experiment findings reveal that the suggested model has an accuracy rate of 96.49%, indicating the method's worth in selecting the most relevant and instructive features for the classification operation. This research contributes significantly to the development of more efficient and effective intrusion detection systems by emphasizing the role of feature selection in improving classification model performance in detecting network security threats.

show abstract

“…Authors in the article [24] introduces a hybrid machine learning approach that combines feature selection and data reduction methods, using feature importance decision treebased methods and the Local Outlier Factor (LOF) method to achieve high accuracy in detecting network anomalies, particularly in the NSL-KDD dataset, demonstrating superior stability compared to other methods, albeit facing challenges in the UNSW-NB15 dataset. In this paper [25] proposes a taxonomy for Intrusion Detection Systems (IDS) based on deep learning, categorizing IDS literature primarily by data objects and evaluates the performance of three machine learning algorithms (Bayes Net, Random Forest, Neural Network) and two deep learning algorithms (RNN, LSTM) using the KDD cup 99 dataset for accuracy assessment with the WEKA program. In this study [26], Support Vector Machine (SVM) and Naïve Bayes machine learning techniques are employed for intrusion detection using the NSL-KDD dataset, with SVM demonstrating superior performance compared to Naïve Bayes, as measured by accuracy and misclassification rates.…”

Section: Related Workmentioning

confidence: 99%

Securing Networks: An In-Depth Analysis of Intrusion Detection using Machine Learning and Model Explanations

Vo,

Thien,

Mui

et al. 2024

ijacsa

View full text Add to dashboard Cite

As cyber threats continue to evolve in complexity, the need for robust intrusion detection systems (IDS) becomes increasingly critical. Machine learning (ML) models have demonstrated their effectiveness in detecting anomalies and potential intrusions. In this article, we delve into the world of intrusion detection by exploring the application of four distinct ML models: XGBoost, Decision Trees, Random Forests, and Bagging. And leveraging the interpretability tools LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive ex-Planations) to explain the classification results. Our exploration begins with an in-depth analysis of each machine learning model, shedding light on their strengths, weaknesses, and suitability for intrusion detection. However, machine learning models often operate as "black boxes" making it crucial to explain their inner workings. This article introduces LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive ex-Planations) as indispensable tools for model interpretability. Throughout the article, we demonstrate the practical application of LIME and SHAP to explain and interpret the output of our intrusion detection models. By doing so, we gain valuable insights into the decision-making process of these models, enhancing our ability to identify and respond to potential threats effectively.

show abstract

Intrusion Detection Systems Based on Machine Learning Algorithms

Cited by 25 publications

References 38 publications

WITHDRAWN: Fake News Detection Using Ensemble Techniques

WITHDRAWN: Fake News Detection Using Ensemble Techniques

Enhancing Cybersecurity: Innovative Hybrid Feature Selection for Intrusion Detection

Securing Networks: An In-Depth Analysis of Intrusion Detection using Machine Learning and Model Explanations

Contact Info

Product

Resources

About