Intrusion Detection Model for Imbalanced Dataset Using SMOTE and Random Forest Algorithm

Alshamy, Reem; Ghurab, Mossa; Othman, Suad; Alshami, Faisal

doi:10.1007/978-981-16-8059-5_22

Cited by 15 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A random forest (RF) is a decision tree-based algorithm that uses an ensemble of decision trees to make predictions [48]. Moreover, it is a very popular technique for network intrusion detection [46,49]. In our case, employing RF, several CART-type decision trees were created using randomly selected subsets of training data and features.…”

Section: Cart (Classification and Regression Treesmentioning

confidence: 99%

Machine Learning Algorithms for Raw and Unbalanced Intrusion Detection Data in a Multi-Class Classification Problem

Bacevičius

Paulauskaitė-Tarasevičienė

2023

Applied Sciences

View full text Add to dashboard Cite

Various machine learning algorithms have been applied to network intrusion classification problems, including both binary and multi-class classifications. Despite the existence of numerous studies involving unbalanced network intrusion datasets, such as CIC-IDS2017, a prevalent approach is to address the issue by either merging the classes to optimize their numbers or retaining only the most dominant ones. However, there is no consistent trend showing that accuracy always decreases as the number of classes increases. Furthermore, it is essential for cybersecurity practitioners to recognize the specific type of attack and comprehend the causal factors that contribute to the resulting outcomes. This study focuses on tackling the challenges associated with evaluating the performance of multi-class classification for network intrusions using highly imbalanced raw data that encompasses the CIC-IDS2017 and CSE-CIC-IDS2018 datasets. The research concentrates on investigating diverse machine learning (ML) models, including Logistic Regression, Random Forest, Decision Trees, CNNs, and Artificial Neural Networks. Additionally, it explores the utilization of explainable AI (XAI) methods to interpret the obtained results. The results obtained indicated that decision trees using the CART algorithm performed best on the 28-class classification task, with an average macro F1-score of 0.96878.

show abstract

Section: Cart (Classification and Regression Treesmentioning

confidence: 99%

Machine Learning Algorithms for Raw and Unbalanced Intrusion Detection Data in a Multi-Class Classification Problem

Bacevičius

Paulauskaitė-Tarasevičienė

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Each decision tree model gives the output based on the input data. The RF model merges the final output using the voting mechanism [42]. The hyperparameter of the RF model is presented in Table 1.…”

Section: Random Forest Model For Intrusion Detectionmentioning

confidence: 99%

A Machine Learning-Based Framework with Enhanced Feature Selection and Resampling for Improved Intrusion Detection

Malik,

Waqas Khan,

Rizwan

et al. 2024

Mathematics

View full text Add to dashboard Cite

Intrusion Detection Systems (IDSs) play a crucial role in safeguarding network infrastructures from cyber threats and ensuring the integrity of highly sensitive data. Conventional IDS technologies, although successful in achieving high levels of accuracy, frequently encounter substantial model bias. This bias is primarily caused by imbalances in the data and the lack of relevance of certain features. This study aims to tackle these challenges by proposing an advanced machine learning (ML) based IDS that minimizes misclassification errors and corrects model bias. As a result, the predictive accuracy and generalizability of the IDS are significantly improved. The proposed system employs advanced feature selection techniques, such as Recursive Feature Elimination (RFE), sequential feature selection (SFS), and statistical feature selection, to refine the input feature set and minimize the impact of non-predictive attributes. In addition, this work incorporates data resampling methods such as Synthetic Minority Oversampling Technique and Edited Nearest Neighbor (SMOTE_ENN), Adaptive Synthetic Sampling (ADASYN), and Synthetic Minority Oversampling Technique–Tomek Links (SMOTE_Tomek) to address class imbalance and improve the accuracy of the model. The experimental results indicate that our proposed model, especially when utilizing the random forest (RF) algorithm, surpasses existing models regarding accuracy, precision, recall, and F Score across different data resampling methods. Using the ADASYN resampling method, the RF model achieves an accuracy of 99.9985% for botnet attacks and 99.9777% for Man-in-the-Middle (MITM) attacks, demonstrating the effectiveness of our approach in dealing with imbalanced data distributions. This research not only improves the abilities of IDS to identify botnet and MITM attacks but also provides a scalable and efficient solution that can be used in other areas where data imbalance is a recurring problem. This work has implications beyond IDS, offering valuable insights into using ML techniques in complex real-world scenarios.

show abstract

“…Hasil akhir diperoleh dengan menentukan simpul akar dan diakhiri dengan beberapa simpul daun. SMOTE (Synthetic Minority Over-sampling Technique) adalah sebuah teknik oversampling yang digunakan dalam pemrosesan data untuk menangani ketidakseimbangan kelas dalam masalah klasifikasi [20], [21].…”

Section: Random Forest Dan Smoteunclassified

Analisis Sentimen Aplikasi Primaku Menggunakan Algoritma Random Forest dan SMOTE untuk Mengatasi Ketidakseimbangan Data

Aryanti,

Misriati,

Sagiyanto

2023

JoSYC

View full text Add to dashboard Cite

The Primaku application is an application that can be used as a tool to monitor the growth of children under five, this application can be used to collect data on the growth of children under five, apart from that this application can also provide clear information and visualization about the growth of children under five, including nutritional status and growth development In accordance with the standards that have been set, the Primaku application can help parents or health workers in routinely monitoring the growth of children under five and early detecting the potential risk of stunting. Stunting is a growth disorder that occurs in children under five due to malnutrition which is characterized by the child's height. which is shorter than the age standard. Stunting can have a long-term impact on a child's quality of life, such as disrupting physical, cognitive and social development, as well as increasing the risk of chronic disease in adulthood. The primaku application has been widely used, more than 500,000 users have downloaded this application and 44,700 reviews have been given by users to this application, however, reading all the reviews may take time, but if there are few reviews read, then the review results will be biased. Therefore, sentiment analysis aims to overcome this problem by automatically grouping user reviews into positive and negative reviews. Therefore, research on toddler growth detection to determine the public's response to the Primaku application can be of great benefit in efforts to prevent stunting in children under five in Indonesia. In this research, the random forest algorithm with the SMOTE technique was used to carry out sentiment analysis of Primaku application reviews. The random forest algorithm is a machine learning algorithm based on decision trees. The SMOTE technique is used to overcome data imbalance problems and is able to reduce overfitting while increasing the performance of the Random Forest algorithm. The data used in this research is Primaku application review data obtained from scrapping results from the Google Play Store. This data contains comments from application users, namely positive and negative. The results of this sentiment analysis show a deep understanding of user perceptions of the Primaku application. This sentiment analysis can be a basis for further improvement and development of the Primaku application, with a focus on aspects that influence user satisfaction and the research results show that the random forest algorithm with the SMOTE technique can produce quite good accuracy in sentiment analysis of the Primaku application. obtained in this study was 88%.

show abstract

Intrusion Detection Model for Imbalanced Dataset Using SMOTE and Random Forest Algorithm

Cited by 15 publications

References 25 publications

Machine Learning Algorithms for Raw and Unbalanced Intrusion Detection Data in a Multi-Class Classification Problem

Machine Learning Algorithms for Raw and Unbalanced Intrusion Detection Data in a Multi-Class Classification Problem

A Machine Learning-Based Framework with Enhanced Feature Selection and Resampling for Improved Intrusion Detection

Analisis Sentimen Aplikasi Primaku Menggunakan Algoritma Random Forest dan SMOTE untuk Mengatasi Ketidakseimbangan Data

Contact Info

Product

Resources

About