• Corpus ID: 12352558

New Intrusion Detection System Based on Support Vector Domain Description with Information Gain Metric

@article{Boujnouni2018NewID,
  title={New Intrusion Detection System Based on Support Vector Domain Description with Information Gain Metric},
  author={Mohamed el Boujnouni and Mohamed Jedra},
  journal={Int. J. Netw. Secur.},
  year={2018},
  volume={20},
  pages={25-34}
}
With the vulgarization of Internet, the easy access to its resources and the rapid growth in the number of computers and networks, the security of information systems has become a crucial topic of research and development especially in the field of intrusion detection. Techniques such as machine learning and data mining are widely used in anomaly-detection schemes to decide whether or not a malicious activity is taking place on a network. This paper presents a new intrusion detection system… 

Figures and Tables from this paper

A Survey on Machine Learning based Intrusion Detection System on NSL-KDD Dataset

Various type of intrusion detection system and techniques which are based on Support Vector Machine (SVM), machine learning, fuzzy logic, supervised learning are survey and hybrid combination of SVM and Machine learning is suggested so that the accuracy can be improved.

Anomaly Based Intrusion Detection System Using Hierarchical Classification and Clustering Techniques

Experimental evaluation on NSL-KDD, a filtered version of the original KDD99 has shown that the proposed IDS can achieve good performance in terms of intrusions detection and recognition.

Efficient Feature Selection for Intrusion Detection Systems

  • S. AhmadiS. RashadH. Elgazzar
  • Computer Science
    2019 IEEE 10th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON)
  • 2019
The results show that selected reduced attributes from the novel feature selection system give a better performance for building a computationally efficient IDS system.

Network intrusion detection algorithm based on deep neural network

Experiments shows that the NDNN-based method improves the performance of the intrusion detection system (IDS) and the accuracy rate can be obtained as high as 99.9%, which is higher when compared with other dozens of intrusion detection methods.

Exploiting Incremental Classifiers for the Training of an Adaptive Intrusion Detection Model

An Adaptive Intrusion Detection Model (AIDM) is proposed, an intelligent and learnable anomaly detection model that overcomes the problems of traditional anomaly detection systems namely, high false alarm, real-time learning, and scalability.

A Global Intrusion Detection System using PcapSockS Sniffer and Multilayer Perceptron Classifier

The main goal of this paper is to analyze some sniffers tools and to assess the performances of certain intrusion detection and prevention systems.

An Approach for Optimizing Ensemble Intrusion Detection Systems

This study aims to find the best relevant selected features that can be used as important features in a new IDS dataset and demonstrates the optimized ensemble IDSs using (SU and BN) and using (OR and J48) with respective ten and six best respective selected features.

Performance Analysis of Network Attack Detection Framework using Machine Learning

The intrusion detection model developed in this analytical research utilises various machine learning classifiers like Random Forest, SVM, K-Nearest Neighbor, and Naïve Bayes to demonstrate that the approach is modular in structure.

A Framework for Intrusion Detection Based on Workflow Mining

Information systems handle large amount of data within enterprises by offering the possibility to collect, treat, keep and make information available. To achieve this, it is crucial to secure data

Intrusion Detection Algorithm Based on Convolution Neural Network

Tests on KDD99 and NSL-KDD dataset demonstrates that the NDNN-based strategy improves the execution of the interruption recognition framework (IDS) and the precision rate can be gotten as high as 99.9%, which is higher when contrasted and different many interruption location strategies.

References

SHOWING 1-10 OF 38 REFERENCES

An Overview of Intrusion Detection Based on Data Mining Techniques

Various data mining techniques applied on intrusion detection systems are presented for the effective identification of both known and unknown patterns of attacks, to develop secure information systems.

Feature Selection for Intrusion Detection System Using Ant Colony Optimization

This paper proposes an intrusion detection system that its features are optimally selected using ant colony optimization, providing higher accuracy in detecting intrusion attempts and lower false alarm with reduced number of features.

Anomaly Intrusion Detection Method Based on SVDD

Results from preliminary experiments with the KDD CUP'99 network data indicate that the new anomaly intrusion detection method based on support vector data description (SVDD) has satisfying performance.

A genetic clustering method for intrusion detection

A Framework for Adaptive Anomaly Detection Based on Support Vector Data Description

Results of experiments with the KDD'99 network data show that these techniques can handle intensive attacks effectively and adapt to the con- cept drift while still detecting attacks.

Adaptive SVDD-based learning for false alarm reduction in intrusion detection

This paper proposes an adaptive SVDD-based learning approach that aims at continuously enhancing the performances of the SVDd classifier by refining the training dataset by periodically evaluating the classifiers by an expert, and feedback in terms of false positives and confirmed attacks is used to update theTraining dataset.

IDuFG: Introducing an Intrusion Detection using Hybrid Fuzzy Genetic Approach

A hybrid approach for designing Intrusion Detection Systems based on a Fuzzy Genetic Machine Learning Algorithm to generate fuzzy rules able to solve the classification problem in designing an anomaly IDS and can converge faster to the classification accuracy.

Research on SVDD Network Intrusion Detection of the Optimal Feature Selection for Particle Swarm

This method adopts PSO to eliminate the superfluous parameters in SVDD and carries out dimension reduction to data and establishes the super sphere model to detect the network intrusion data and output the results of intrusion detection.

A detailed analysis of the KDD CUP 99 data set

A new data set is proposed, NSL-KDD, which consists of selected records of the complete KDD data set and does not suffer from any of mentioned shortcomings.

New malware detection framework based on N-grams and Support Vector Domain Description

A new framework to detect new malicious programs, based on N-grams and an improved version of Support Vector Domain Description is presented, which is generally regarded as ineffective against attacks like code polymorphism and metamorphism used by malware writers to obfuscate their code.