Soft Computing Models for Network Intrusion Detection Systems

  title={Soft Computing Models for Network Intrusion Detection Systems},
  author={Ajith Abraham and Ravi Jain},
Security of computers and the networks that connect them is increasingly becoming of great significance. Computer security is defined as the protection of computing systems against threats to confidentiality, integrity, and availability. There are two types of intruders: external intruders, who are unauthorized users of the machines they attack, and internal intruders, who have permission to access the system with some restrictions. This chapter presents a soft computing approach to detect… 

Integration Soft Computing Approach to Network Security

  • S. Srinoy
  • Computer Science
    First Asia International Conference on Modelling & Simulation (AMS'07)
  • 2007
Empirical results clearly show that support vector machine and rough set approach could play a major role for intrusion detection systems.

Integrated soft computing for Intrusion Detection on computer network security

The new intrusion detection technique that applied hybrid of unsupervised/supervised learning scheme is presented, able to improve the performance of anomaly intrusion detection and intrusion detection.

Soft Computing in Intrusion Detection

Empirical results clearly show that soft computing approach could play a major role for intrusion detection, and the shortcomings of some of the more conventional approaches used in intrusion detection are concerned.

Intelligence system approach for computer network security

Experimental result shows that the particle swarm optimization method allows us to recognize not only known attacks but also to detect suspicious activity that may be the result of a new, unknown attack.

Analysis of Hybrid Soft Computing Techniques for Intrusion Detection on Network

The approaches including the examination of efforts in hybrid system of SC such as neuro-fuzzy, fuzzy-genetic, neuro- genetic, and neuro- fuzzy-genetics used the development of the systems and outcome their implementation are analyzed.

An effective intrusion detection method using optimal hybrid model of classifiers

  • S. Aljahdali
  • Computer Science
    J. Comput. Methods Sci. Eng.
  • 2010
Experimental results indicate that hybrid approach effectively generates a more accurate intrusion detection model on detecting both normal usages and malicious activities.

Computer network security based on Support Vector Machine approach

The proposed hybrid methods of unsupervised/supervised learning scheme can improve the performance of anomaly intrusion detection, the intrusion detection rate and generate fewer false alarms.

Network Intrusion detection by using Feature Reduction Technique

Experimental results show that the proposed method is promising in terms of detection accuracy, computational expense and implementation for real-time intrusion detection.

Network Intrusion detection by using PCA via SMO-SVM

Experimental results show that the proposed method is promising in terms of detection accuracy, computational expense and implementation for real-time intrusion detection.

Design an anomaly-based intrusion detection system using soft computing for mobile ad hoc networks

Simulation results show that the proposed soft computing-based approach is able to identify the known and unknown attacks in mobile ad hoc networks with high positive and low false positive rates.



Intrusion Detection Systems Using Decision Trees and Support Vector Machines

Investigating and evaluating the decision tree data mining techniques as an intrusion detection mechanism and comparing it with Support Vector Machines shows that Decision trees gives better overall performance than the SVM.

Intrusion Detection Using Ensemble of Soft Computing Paradigms

It is shown that ensemble of ANN and SVM is superior to individual approaches for intrusion detection in terms of classification accuracy.

Adaptive neuro-fuzzy intrusion detection systems

Two machine-learning paradigms, artificial neural networks and fuzzy inference system, are used to design an intrusion detection system and a signature pattern database is constructed using protocol analysis and neuro-fuzzy learning method.

An Intrusion-Detection Model

  • D. Denning
  • Computer Science
    IEEE Transactions on Software Engineering
  • 1987
A model of a real-time intrusion-detection expert system capable of detecting break-ins, penetrations, and other forms of computer abuse is described. The model is based on the hypothesis that

A data mining framework for building intrusion detection models

  • Wenke LeeS. StolfoK. Mok
  • Computer Science
    Proceedings of the 1999 IEEE Symposium on Security and Privacy (Cat. No.99CB36344)
  • 1999
A data mining framework for adaptively building Intrusion Detection (ID) models is described, to utilize auditing programs to extract an extensive set of features that describe each network connection or host session, and apply data mining programs to learn rules that accurately capture the behavior of intrusions and normal activities.

ADAM: a testbed for exploring the use of data mining in intrusion detection

The design and experiences with the ADAM (Audit Data Analysis and Mining) system are described, which is used as a testbed to study how useful data mining techniques can be in intrusion detection.

Secure Computing: Threats and Safeguards

The breadth of coverage and the attention to real-world context make this authoritative book unique in its treatment of an extemely hot topic-the security of computers, computer networks, and the

Roles of Soft Computing and Fuzzy Logic in the Conception, Design and Deployment of Information/Intelligent Systems

The guiding principle of soft computing is to exploit the tolerance for imprecision, uncertainty and partial truth to achieve tractability, robustness, low solution cost and better rapport with reality.

A comparison of linear genetic programming and neural networks in medical data mining

An efficient algorithm that eliminates intron code and a demetic approach to virtually parallelize the system on a single processor are discussed, which show that GP performs comparably in classification and generalization.

Learning Trees and Rules with Set-Valued Features

It is argued that many decision tree and rule learning algorithms can be easily extended to set-valued features, and it is shown by example that many real-world learning problems can be efficiently and naturally represented with set- valued features.