Analysis of KDD CUP 99 Dataset using Clustering based Data Mining

Siddiqui, Mohammad Khubeb; Naahid, Shams

doi:10.14257/ijdta.2013.6.5.03

Cited by 85 publications

(22 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…KDD99 [16] is a benchmark test suite exclusively developed for the studies concerning network attacks and security. The dataset contains 500,000 entries consisting of different types of network attacks as well as normal connections (connections showing no attack).…”

Section: Mapping Of Kdd99 Attacks To Stride Modelmentioning

confidence: 99%

Fuzzy STRIDE Model based on Werners Aggregation Operator for Computer Network Threat Modelling

Khan¹

2017

IJCDS

View full text Add to dashboard Cite

Security has become a significant concern in proper functioning of modern network systems. To prevent and mitigate a system from attacks, an important issue is realization of the possible damage that different threats could cause to a network system. Keeping this issue in view, this paper proposes modeling of threats and their risk assessment. The STRIDE threat assessment model covers numerous existing threats that are related to all security properties necessary for a secure network. A STRIDE based strategy has been proposed which takes the number and types of attacks as input and applies a fuzzy logic based threat assessment approach to assess the level of attack. The presented work uses a fuzzy operator, namely, Werners operator and a decision-making approach based on a fuzzy rule. KDD 99 dataset was used to evaluate the proposed fuzzy STRIDE model. Empirical results indicate that the proposed approach was able to identify the combined threat level of multiple types of attacks.

show abstract

Section: Mapping Of Kdd99 Attacks To Stride Modelmentioning

confidence: 99%

Fuzzy STRIDE Model based on Werners Aggregation Operator for Computer Network Threat Modelling

Khan¹

2017

IJCDS

View full text Add to dashboard Cite

show abstract

“…Siddiqui et al [9] perform analysis of 10% of KDD cup'99 training dataset based on intrusion detection. They focused on establishing a relationship between the attack types and the protocol used by the hackers, using clustered data.…”

Section: Tavallaee Et Al [8]mentioning

confidence: 99%

Hybrid Intrusion Detection System Using K-means and J-48

Singh¹,

Bal²

2017

IJSIA

View full text Add to dashboard Cite

Security attacks through internet are increased continuously in recent years therefore the Information security is globally very serious problem at the present time. The importance of protecting networks is most important. The need of intrusion detection system has been brought out. In this work a hybrid intrusion system based on data mining techniques using Kmeans and J48 is proposed. In this paper work hybrid intrusion detection system is proposed first Misuse based detection model is build using K-means clustering algorithm then based upon the output of misuse detection phase Anomaly based intrusion detection model is build using improved J-48 classification algorithm in this way the combine output of these two phases attains very higher detection accuracy. For training and testing of hybrid intrusion detection model famous NSL-kdd dataset is used.

show abstract

“…After changing the dataset we have created 4 types of dataset using some algorithms that can be entitled by the feature selection methods. Using these we have point out 9 features, 16 features, 36 features and 41 features [10,22].…”

Section: Division Of Datasetmentioning

confidence: 99%

Artificial Neural Network based System for Intrusion Detection using Clustering on Different Feature Selection

Tammi¹,

Nasim²,

Biswas³

et al. 2015

IJCA

View full text Add to dashboard Cite

Intrusion Detection System (IDS) is an example of Misuse Detection System that works for detecting malicious attacks. This can be defined as software for security management. Many researchers have proposed the Intrusion Detection System with different techniques to achieve the best accuracy. In this paper it is projected that intrusion detection system with the amalgamation of k-means clustering and artificial neural network to improve the system. To obtain a better result benchmark dataset was split into training and testing part and then cluster the dataset into five different divisions. After getting the cluster data it has been trained by the different Artificial Neural Networks functions as-Feed Forward Neural Network (FFNN), Elman Neural Network (ENN), Generalized Regression Neural Network (GRNN), Probabilistic Neural Network (PNN) and Radial Basis Neural Network (RBNN). After implementing these functions we have proposed a comparative analysis between them and choose the best accuracy rate among them. Here, it has been proved that, using the clustering technique a better accuracy rate can be found that improve the system with the best neural network functions which is the probabilistic neural network. It is also important to select efficient feature sets for better accuracy.

show abstract

Analysis of KDD CUP 99 Dataset using Clustering based Data Mining

Abstract: The KDD Cup

Cited by 85 publications

References 9 publications

Fuzzy STRIDE Model based on Werners Aggregation Operator for Computer Network Threat Modelling

Fuzzy STRIDE Model based on Werners Aggregation Operator for Computer Network Threat Modelling

Hybrid Intrusion Detection System Using K-means and J-48

Artificial Neural Network based System for Intrusion Detection using Clustering on Different Feature Selection

Contact Info

Product

Resources

About