A hybrid artificial immune system for IDS based on SVM and belief function

Singh, Sandeep; Singh, Jasvinder Pal; Shrivastva, Gaurav

doi:10.1109/icccnt.2013.6726835

Cited by 3 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM with Belief theory Singh et al [7] This method is a hybrid one wherein intrusive behavior is detected using the Dempster belief algorithm (DCA) and Dendritic Cell Algorithm and where data are classified with the SVM.…”

Section: Fuzzy Multiclass Svmmentioning

confidence: 99%

“…Compared with that in Table 8 for UNSW-NB15 data set, the accuracy of the multiclass classifications in Table 9 was lower because of the effects of imbalanced data. We analyzed several cases of misclassification of the training data and discovered that they primarily occurred for six minority classes: Analysis (0), Backdoor (1), DoS (2), Exploits (3), Fuzzers (4), and Reconnaissance (7). Thus, SMOTE was employed to oversample six minority classes by using the command, BorderlineSMOTE(sampling_ strategy = 'minority') for multiclass classification accuracy and compare the model performance of RF with the SVC.…”

Section: Case Ii: Over-sampling For Misclassification Classmentioning

confidence: 99%

“…Typically, network intrusion detection (NID) involves collecting behavioral information to classify all potential threats into attacker and victim categories under some given constraints on the quantity of packets collected and NIDS computational time. Many classification approaches incorporate ML algorithms to assist managers in precisely identifying network attacks [4][5][6][7]. ML techniques for threat classification-such as support vector machine (SVM) and hybrid approaches-are used to aid category prediction, wherein the SVM [4] is incorporated with other classification approaches, such as those based on decision trees (DTs) [5], principal component analysis (PCA) [6], and the Dempster-Shafer theory [7].…”

Section: Introductionmentioning

confidence: 99%

“…Many classification approaches incorporate ML algorithms to assist managers in precisely identifying network attacks [4][5][6][7]. ML techniques for threat classification-such as support vector machine (SVM) and hybrid approaches-are used to aid category prediction, wherein the SVM [4] is incorporated with other classification approaches, such as those based on decision trees (DTs) [5], principal component analysis (PCA) [6], and the Dempster-Shafer theory [7]. These network threat classification schemes are summarized in Table 1.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Ensemble Learning for Threat Classification in Network Intrusion Detection on a Security Monitoring System for Renewable Energy

et al. 2021

View full text Add to dashboard Cite

Most approaches for detecting network attacks involve threat analyses to match the attack to potential malicious profiles using behavioral analysis techniques in conjunction with packet collection, filtering, and feature comparison. Experts in information security are often required to study these threats, and judging new types of threats accurately in real time is often impossible. Detecting legitimate or malicious connections using protocol analysis is difficult; therefore, machine learning-based function modules can be added to intrusion detection systems to assist experts in accurately judging threat categories by analyzing the threat and learning its characteristics. In this paper, an ensemble learning scheme based on a revised random forest algorithm is proposed for a security monitoring system in the domain of renewable energy to categorize network threats in a network intrusion detection system. To reduce classification error for minority classes of experimental data in model training, the synthetic minority oversampling technique scheme (SMOTE) was formulated to re-balance the original data sets by altering the number of data points for minority class to imbue the experimental data set. The classification performance of the proposed classifier in threat classification when the data set is unbalanced was experimentally verified in terms of accuracy, precision, recall, and F1-score on the UNSW-NB15 and CSE-CIC-IDS 2018 data sets. A cross-validation scheme featuring support vector machines was used to compare classification accuracies.

show abstract

Section: Fuzzy Multiclass Svmmentioning

confidence: 99%

Section: Case Ii: Over-sampling For Misclassification Classmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Ensemble Learning for Threat Classification in Network Intrusion Detection on a Security Monitoring System for Renewable Energy

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Then, the classifier is used to classify unlabeled test data to distinguish normal data and intrusion data. Many basic supervised learning algorithms such as decision tree [1], [2], [3], support vector machine [4], [5], neural network [6], [7] and ensemble learning [8], were all used in intrusion detection system. In addition, some unsupervised methods were also applied to assist supervised models in some cases.…”

Section: Related Workmentioning

confidence: 99%

MSML: A Novel Multilevel Semi-Supervised Machine Learning Framework for Intrusion Detection System

Yao

Zhang

et al. 2019

IEEE Internet Things J.

101

View full text Add to dashboard Cite

Intrusion detection technology has received increasing attention in recent years. Many researchers have proposed various intrusion detection systems using machine learning methods. However, there are two noteworthy factors affecting the robustness of the model. One is the severe imbalance of network traffic in different categories, and the other is the non-identical distribution between training set and test set in feature space. This paper presents a multi-level intrusion detection model framework named MSML to address these issues. The MSML framework includes four modules: pure cluster extraction, pattern discovery, fine-grained classification and model updating. In the pure cluster module, we introduce an concept of "pure cluster" and propose a hierarchical semi-supervised k-means algorithm (HSK-means) with an aim to find out all the pure clusters. In the pattern discovery module, we define the "unknown pattern and apply cluster based method aiming to find those unknown patterns. Then a test sample is sentenced to labeled known pattern or unlabeled unknown pattern. The fine-grained classification module can achieves fine-grained classification for those unknown pattern samples. The model updating module provides a mechanism for retraining. KDDCUP99 dataset is applied to evaluate MSML. Experimental results show that MSML is superior to other existing intrusion detection models in terms of overall accuracy, F1 score and unknown pattern recognition capability.

show abstract

An Efficient Flow Control Approach for SDN-Based Network Threat Detection and Migration Using Support Vector Machine

Wang

Chao

Lin

et al. 2016

2016 IEEE 13th International Conference on E-Business Engineering (ICEBE)

View full text Add to dashboard Cite

A hybrid artificial immune system for IDS based on SVM and belief function

Cited by 3 publications

References 11 publications

Ensemble Learning for Threat Classification in Network Intrusion Detection on a Security Monitoring System for Renewable Energy

Ensemble Learning for Threat Classification in Network Intrusion Detection on a Security Monitoring System for Renewable Energy

MSML: A Novel Multilevel Semi-Supervised Machine Learning Framework for Intrusion Detection System

An Efficient Flow Control Approach for SDN-Based Network Threat Detection and Migration Using Support Vector Machine

Contact Info

Product

Resources

About