Unsupervised detection of botnet activities using frequent pattern tree mining

Hao, Siqiang; Liu, Di; Baldi, Simone; Yu, Wenwu

doi:10.1007/s40747-021-00281-5

Cited by 6 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An optimal set of parameter values was used to get a detection rate of 100 percent with no false positives [8]. The effectiveness of the botnet detection technique that uses DNS query data analysed using a range of machine learning algorithms, which includes decision trees, kNN, random forests, and Naive Bayes [9,17,22]. The detection model is developed in two steps: training and detection.…”

Section: Fig3 Weka Tool For Clusteringmentioning

confidence: 99%

“…To detect botnets, the random forest machine learning method is used because of its high accuracy in classification [9]. Similar Techniques of using different supervised techniques with CTU-13 dataset and UNSW-NB15 datasets are also proposed [17,22]. Use of Logistic Regression in detection of Botnet using various type of numerical datasets are proposed which have given the better accuracy [18].…”

Section: Fig3 Weka Tool For Clusteringmentioning

confidence: 99%

See 1 more Smart Citation

A Report on Botnet Detection Techniques for Intrusion Detection Systems

Sathya¹

2022

IJRASET

View full text Add to dashboard Cite

Abstract— A botnet is a malware that degrades the functionality as well as access to a healthy computer system through malware programs. Botnet programs perform DDoS attack, Spam, phishing attacks. Botnet attack takes place in two ways which are peer to peer attacks and command and control attack. The peer-to-peer attack takes place to by passing botnet attacks from one system to another in a peer-to-peer network while the command-and-control attack takes place by a botmaster attack on a server which uses various transactions in exchange with systems on the network and those nodes in the networks function as slaves. The report presents a survey of various techniques of botnet detection models built using several types of machine learning techniques. The report gives the review on various methodologies involved in Botnet Detection and to identify the best methods involved to understand various dataset. We also surveyed on how classification, clustering is used in detection of Botnet to improve the accuracy of the model.

show abstract

Section: Fig3 Weka Tool For Clusteringmentioning

confidence: 99%

Section: Fig3 Weka Tool For Clusteringmentioning

confidence: 99%

A Report on Botnet Detection Techniques for Intrusion Detection Systems

Sathya¹

2022

IJRASET

View full text Add to dashboard Cite

show abstract

“…Hidayah et al [147] obtained up to 92% accuracy using ML algorithms that filter and classify data to detect the botnets C&C server. Siqlang et al [148] studied the use of unsupervised detection of botnet activities and used the Frequent pattern tree algorithm provided by Weka. They achieved up to 100% accuracy varying with the thresholds chosen and up to 100% precision.…”

Section: Machine Learning and Network-based Detection Mechanismsmentioning

confidence: 99%

A Survey on Botnets: Incentives, Evolution, Detection and Current Trends

Stege

El-Habr

et al. 2021

Future Internet

View full text Add to dashboard Cite

Botnets, groups of malware-infected hosts controlled by malicious actors, have gained prominence in an era of pervasive computing and the Internet of Things. Botnets have shown a capacity to perform substantial damage through distributed denial-of-service attacks, information theft, spam and malware propagation. In this paper, a systematic literature review on botnets is presented to the reader in order to obtain an understanding of the incentives, evolution, detection, mitigation and current trends within the field of botnet research in pervasive computing. The literature review focuses particularly on the topic of botnet detection and the proposed solutions to mitigate the threat of botnets in system security. Botnet detection and mitigation mechanisms are categorised and briefly described to allow for an easy overview of the many proposed solutions. The paper also summarises the findings to identify current challenges and trends within research to help identify improvements for further botnet mitigation research.

show abstract

“…A botnet is defined as a network of robots, and these robots may be smart systems on the Internet. 1 They are remotely commanded by a botmaster, also called a command and control (C&C) server. These smart systems can carry out malicious attacks on key targets by sending spam, phishing, stealing information, and by the distributed denial of service (DDoS).…”

Section: Introductionmentioning

confidence: 99%

A novel and highly efficient botnet detection algorithm based on network traffic analysis of smart systems

Duan

Zhou

You

et al. 2022

International Journal of Distributed Sensor Networks

View full text Add to dashboard Cite

In smart systems, attackers can use botnets to launch different cyber attack activities against the Internet of Things. The traditional methods of detecting botnets commonly used machine learning algorithms, and it is difficult to detect and control botnets in a network because of unbalanced traffic data. In this article, we present a novel and highly efficient botnet detection method based on an autoencoder neural network in cooperation with decision trees on a given network. The deep flow inspection method and statistical analysis are first applied as a feature selection technique to select relevant features, which are used to characterize the communication-related behavior between network nodes. Then, the autoencoder neural network for feature selection is used to improve the efficiency of model construction. Finally, Tomek-Recursion Borderline Synthetic Minority Oversampling Technique generates additional minority samples to achieve class balance, and an improved gradient boosting decision tree algorithm is used to train and establish an abnormal traffic detection model to improve the detection of unbalanced botnet data. The results of experiments on the ISCX-botnet traffic dataset show that the proposed method achieved better botnet detection performance with 99.10% recall, 99.20% accuracy, 99.1% F1 score, and 99.0% area under the curve.

show abstract

Unsupervised detection of botnet activities using frequent pattern tree mining

Cited by 6 publications

References 28 publications

A Report on Botnet Detection Techniques for Intrusion Detection Systems

A Report on Botnet Detection Techniques for Intrusion Detection Systems

A Survey on Botnets: Incentives, Evolution, Detection and Current Trends

A novel and highly efficient botnet detection algorithm based on network traffic analysis of smart systems

Contact Info

Product

Resources

About