Chunxiao Ye

Network Anomaly Detection Based on DSOM and ACO Clustering

An approach to network anomaly detection is investigated, based on dynamic self-organizing maps (DSOM) and ant colony optimization (ACO) clustering. The basic idea of the method is to produce the cluster by DSOM and ACO. With the classified data instances, anomaly data clusters can be easily identified by normal cluster ratio. And then the identified cluster can be used in real data detection. In the traditional clustering-based intrusion detection algorithms, clustering using a simple distance-based metric and detection based on the centers of clusters, which generally degrade detection accuracy and efficiency. Our approach based on DSOM and ACO clustering can settle these problems effectively. The experiment results show that our approach can detect unknown intrusions efficiently in the real network connections.

Intrusion Detection Based on Adaptive RBF Neural Network

Recently the machine learning-based intrusion detection approaches have been subjected to extensive researches because they can detect both misuse and anomaly. In this paper, we propose a new method to design classifier based on multiple granularities immune network. Firstly a multiple granularities immune network (MGIN) algorithm is employed to reduce the data and get the candidate hidden neurons and construct an original RBF network including all candidate neurons. Secondly, the removing redundant neurons procedure is used to get a smaller network. Experimental results on the real network data set show that the new classifier has higher detection and lower false positive rate than traditional RBF classifier

An enhanced swarm intelligence clustering-based RBFNN classifier and its application in deep Web sources classification

The central problem in training a radial basis function neural network (RBFNN) is the selection of hidden layer neurons, which includes the selection of the center and width of those neurons. In this paper, we propose an enhanced swarm intelligence clustering (ESIC) method to select hidden layer neurons, and then, train a cosine RBFNN based on the gradient descent learning process. Also, we apply this new method for classification of deep Web sources. Experimental results show that the average Precision, Recall and F of our ESIC-based RBFNN classifier achieve higher performance than BP, Support Vector Machines (SVM) and OLS RBF for our deep Web sources classification problems.

An Enhanced Swarm Intelligence Clustering-Based RBF Neural Network Detection Classifier

The central problem in training a radial basis function neural network (RBFNN) is the selection of hidden layer neurons, which includes the selection of the center and width of those neurons. In this paper, we propose an enhanced swarm intelligence clustering (ESIC) method to select hidden layer neurons, and then, training a cosine RBFNN base on gradient descent learning process. Also, the new method is applied for intrusion detection. Experimental results show that the average DR and FPR of our ESIC-based RBFNN detection classifier maintained a better performance than BP, SVM and OLS RBF.

Clustering based on Self-Organizing Ant Colony Networks with Application to Intrusion Detection

Due to the fact that it is more and more improbable to a system administrator to recognize and manually intervene to stop an attack, there is an increasing recognition that ID systems should have a lot to earn on following its basic principles on the behavior of complex natural systems, namely in what refers to self-organization, allowing for a real distributed and collective perception of this phenomena. A clustering model based on self-organizing ant colony networks (CSOACN) is systematically proposed for intrusion detection system. Instead of using the linear segmentation function of the CSI model, here we propose to use a nonlinear probability conversion function and can help to solve linearly inseparable problems. Using a set of benchmark data from 1998 DARPA, we demonstrate that the efficiency and accuracy of CSOACN

A Novel Authentication Mechanism Based on CGA for BU Message Disposal in Mobile IPv6

In mobile IPv6, the location of a mobile node (MN) is obtained by implementing a binding update (BU) process. During the process, the unauthenticated BU message may give rise to many security risks, such as denial-of-service (DoS) attack. Thus, authentication of the BU message is most important for the security of mobile IPv6. The purpose of cryptographically generated addresses (CGA) is to prevent stealing and spoofing of existent IP addresses. In this paper, a novel authentication mechanism based on CGA is proposed for BU message in mobile IPv6. With the implementation of the novel authentication mechanism, care-of address of MN will be automatically generated, and this will be related to MN private attribute, hence, it would not be possible for a vicious node to steal it. With this method, the BU message can be authenticated.

Artificial Immune Networks Based Radial Basic Function Neural Networks Construction Algorithm and Application

An RBFNN can be regarded as a feedforward artificial neural network with a single layer of hidden units, whose responses are the output of radial basis functions (RBFs). The central problem in training a radial basis function neural network is the selection of hidden layer neurons, which includes the selection of the center and width of those neurons. In this paper, we propose a method to select hidden layer neurons based on multiple granularities immune network, and then, training a cosine RBF neural network base on gradient descent learning process. Also, the new method is applied for intrusion detection and it is observed that the proposed approach gives better performance over some traditional approaches.

An Enhanced Swarm Intelligence Clustering-Based RBF Neural Network Web Text Classifier

The central problem in training a radial basis function neural network (RBFNN) is the selection of hidden layer neurons, which includes the selection of the center and width of those neurons. In this paper, we propose an enhanced swarm intelligence clustering (ESIC) method to select hidden layer neurons, and then, training a cosine RBFNN base on gradient descent learning process. Also, the new method is applied for web text classification. Experimental results show that the average Accuracy, Precision and Recall of our ESIC-based RBFNN classifier maintained a better performance than BP, SVM and OLS RBF.

Revocation in an Attribute-Based Delegation Model

Attribute-based delegation model (ABDM) is a secured and flexible delegation model with an extended delegation constraint. Delegation attribute expressions can be changed in delegation, which induces an automatic revocation in ABDM. In this revocation, delegated permissions can be removed from users automatically according to dominance relation among DAEs of users and delegated permissions. Automatic revocation thus relieves the administrative efforts of delegator or system administrator in revocation. For a better flexibility, ABDM also supports revocation by delegator or system administrator. This paper also discusses some revocation modes of automatic revocation.

Intrusion Detection Classifier Based on Dynamic SOM and Swarm Intelligence Clustering

A clustering analysis model based on dynamic self-organizing maps (DSOM) and swarm intelligence (SI) is systematically proposed for intrusion detection system. The basic idea of the model is to produce the cluster by DSOM and SI. With the classified data instances, the detection classifier can be established. And then the detection classifier can be used in real intrusion detection. Experimental results show that our detection classifier maintained a higher performance than SVM, LGP, DT and K-NN.