Evaluating Effectiveness of Ensemble Classifiers When Detecting Fuzzers Attacks on the Unsw-Nb15 Dataset

Thanh, Hoàng Ngoc; Lăng, Trần Văn

doi:10.15625/1813-9663/36/2/14786

Cited by 13 publications

(4 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Fuzzers assault systems by flooding them with a lot of random data to break them and identify faults. It can locate security gaps in networks and operating systems as well as vulnerabilities in software and systems [39]. It has been demonstrated that deep neural networks (DNNs) are extremely sensitive to even small changes in their input data.…”

Section: ) Fuzzersmentioning

confidence: 99%

Hybrid Machine Learning Model for Efficient Botnet Attack Detection in IoT Environment

Ali,

Shahroz,

Mushtaq

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Cyber attacks are growing with the rapid development and wide use of internet technology. Botnet attack emerged as one of the most harmful attacks. Botnet identification is becoming challenging due to the numerous attack vectors and the ongoing evolution of viruses. As the Internet of Things (IoT) technology is developing rapidly, many network devices have been subject to botnet attacks leading to substantial losses in different sectors. Botnets pose serious risks to network security and deep learning models have shown potential for efficiently identifying botnet activity from network traffic data. In this research, a botnet identification system is proposed based on the stacking of artificial neural network (ANN), convolutional neural network (CNN), long short-term memory (LSTM), and recurrent neural network (RNN) (ACLR). The experiments are conducted by employing both the individual models, as well as, the proposed ACLR model for performance comparison. The UNSW-NB15 dataset is used for botnet attacks and contains nine different attack types including 'Normal', 'Generic', 'Exploits', 'Fuzzers', 'DoS', 'Reconnaissance', 'Analysis', 'Backdoor', 'Shell code' and 'Worms'. Experimental results indicate the proposed ACLR model gains 0.9698 testing accuracy showing that it is successful in capturing the intricate patterns and characteristics of botnet attacks. The proposed ACLR model's k values (3, 5, 7, and 10) for a K-fold cross-validation accuracy score is 0.9749 indicating that the model's robustness and generalizability are demonstrated by k = 5. In addition, the proposed model detects botnets with a high receiver operating characteristic area under the curve (ROC-AUC) of 0.9934 and a precision-recall area under the curve (PR-AUC) of 0.9950. Performance comparison with existing state-of-the-art models further corroborates the superior performance of the proposed approach. The results of this research can be helpful against evolving threats and enhance cyber security procedures.

show abstract

Section: ) Fuzzersmentioning

confidence: 99%

Hybrid Machine Learning Model for Efficient Botnet Attack Detection in IoT Environment

Ali,

Shahroz,

Mushtaq

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Experimental results demonstrate that Ada boost with Naive Bayes Tree (NBTree) has the best accuracy score of 98.65 percent. In [12] Hoang Ngoc Thanh and Tran Van Lang suggested a fuzzers detection system using the UNSW-NB15 dataset, to analyze and evaluate the experimental outcomes. Single classifiers such (J48 (DT), logistic (LR), Lib SVM (SVM), Naive Bayes (NB), Random Tree (RT), and ibk (KNN)) were used in bagging, Ada boost, stacking, random forest, and decorate ensemble techniques.…”

Section: Related Workmentioning

confidence: 99%

Intrusion Detection System Based on Ada boosting and Bagging Algorithm

2022

IJCCCE

View full text Add to dashboard Cite

Computer worms execute damaging functions in the network systems, compromising system security. Although researchers use a variety of methods to detect worms and prevent their spread. Detecting worms remains a challenge for the following reasons: First, a huge volume of irrelevant data affects classification accuracy. Second, frequently used individual classifiers in systems are poor at detecting all types of worms, Third, many systems are built on out-of-date information, rendering them useless for new worm species. As a result, providing a network intrusion detection system is vital for ensuring security and reducing the harm caused by worms on networks to information systems. The goal of the study is to discover computer worms in the computer networks and protect the systems from their damages. The proposed method uses the UNSW NB15 dataset to train and test the ensemble Ada boosting and Bagging algorithms with the Support Vector Nachine (SVM) as a contribution rather than a decision tree. Due to Correlation Feature Selection (CFS) identifying relationships between features and classes, and Chi-square (Chi2) determining whether features and classes are independent or not, we combined these two algorithms as a contribution in a method called CFS&Chi2fs to select the relevant features and reduce the time. The system achieved accuracy reaching 0.998 with Bagging(SVM), and 0.989 with Ada boost(SVM). Index Terms— Intrusion Detection System, Computer Worms, Ada boosting, Bagging.

show abstract

“…Thanh and Lang [14] suggested a fuzzers detection system using the UNSW-NB15 dataset. The system use ensemble methods such as Bagging, Ada Boost, Stacking, Decorate, and Random Forest for fuzzers detection.…”

Section: Related Workmentioning

confidence: 99%

Building an Efficient System to Detect Computer Worms in Websites Based on Ensemble Ada Boosting and SVM Classifiers Algorithms

Hilool¹,

Hashem²,

jafer³

2022

ETJ

View full text Add to dashboard Cite

 Union of two feature selection methods strength the NIDS  Performance of the NIDS will increase by using ensemble learning  Bagging and boosting by SVM have much more power than DT  Worm detection is much more strongest by using NIDS with two levelsComputer worms perform harmful tasks in network systems due to their rapid spread, which leads to harmful consequences on system security. However, existing worm detection algorithms are still suffered a lot to achieve good performance. The reasons for that are: First, a large number of irrelevant data impacts classification accuracy (irrelevant feature gives estimator new ways to go wrong without any expected benefit also can cause overfitting, which will generally lead to decreased accuracy). Second, the individual classifiers used extensively in the systems do not effectively detect all types of worms. Third, many systems are built based on old datasets, making them less suitable for new types of worms. The research aims to detect computer worms in the network based on data mining algorithms for their high ability to automatically and accurately detect new types of computer worms. The proposal uses misuse and anomaly detection techniques based on the UNSW_NB15 dataset to train and test the ensemble Ada Boosting algorithm using SVM and DT classifiers. To select the most important features, we propose to conduct the similar features selected by Correlation and Chi-Square feature selection (since correlation finds the relations between features and classes whereas Chi finds whether features and classes are independent or not). The contribution suggests using SVM in the boosting ensemble algorithm as base estimators instead of DT to efficiently detect various types of worms. The system achieved accuracy, reaching 100% with CFS+Chi2fs and 99.38, 99.89 with correlation and chi-square separately.

show abstract

Evaluating Effectiveness of Ensemble Classifiers When Detecting Fuzzers Attacks on the Unsw-Nb15 Dataset

Cited by 13 publications

References 11 publications

Hybrid Machine Learning Model for Efficient Botnet Attack Detection in IoT Environment

Hybrid Machine Learning Model for Efficient Botnet Attack Detection in IoT Environment

Intrusion Detection System Based on Ada boosting and Bagging Algorithm

Building an Efficient System to Detect Computer Worms in Websites Based on Ensemble Ada Boosting and SVM Classifiers Algorithms

Contact Info

Product

Resources

About