Dissertation > Excellent graduate degree dissertation topics show

Matching algorithm oriented characteristics of high-speed network

Author: HuYongGang
Tutor: LiuWeiGuo
School: Central South University
Course: Traffic Information Engineering \u0026 Control
Keywords: Intrusion Detection Sequence Alignment Support Vector Machine Pattern Matching Double hash lookup
CLC: TP393.08
Type: Master's thesis
Year: 2011
Downloads: 16
Quote: 0
Read: Download Dissertation

Abstract


In recent years, with the development of network technology, network bandwidth is growing, increasing the number of users of the Internet business, traditional network intrusion detection system is facing new challenges. First, the increased intrusion attacks are emerging and new means of attack, the need to extract new rule base of the intrusion signature updates. Secondly, in the backbone network traffic increases, network intrusion detection system based on pattern matching technology is limited by the efficiency of matching algorithm, can not meet the requirements of high-speed data stream in real-time detection. To solve the above problems, the paper work is mainly to study the attack signatures automatically extraction and pattern matching algorithms. Attack signatures automatically extract without human assistance, automatic discovery of new attacks and extract its attack features, its purpose is to provide faster and more accurate for intrusion detection system quality feature detection rules. Faced with the problem of debris and noise sequence alignment used in the attack feature extraction process, this paper SVM classifier sample is converted into a single attack samples, in order to reduce the noise associated with the process sequence will be more attacks; and in the traditional sequence alignment change the gap penalty on the basis of the algorithm Smith-Waterman algorithm, introduced continuous matching character reward proposed an improved Smith-Waterman algorithm. Ultimately proposed an anti-noise sequence alignment model experiments show associated with using SVM classifier results more accurately express the characteristics of attack, thereby reducing the rate of false positives. WM algorithm is used intrusion detection systems, pattern-matching engine algorithm, pattern-matching efficiency directly affects the performance of intrusion detection systems, increasing pattern set with the speed of the network and intrusion rules, the system faces in the high-speed network data stream in real time detected the problem of the abnormal data packet. Traditional pattern matching algorithm performance analysis based on a new type of Wu-Manber algorithm: The double hash Find Wu-Manber algorithm in the preprocessing stage, the new Shift1 the table and Hash1 table, and change the storage structure of the pattern string; Find stage, using a double hashing find mode string to avoid the access mode long linked list and increase the sliding distance of the search window. By testing the comparison shows that, with the increase of the size of the set of modes, the algorithm utilizes a double hashing massive lookup good performance and can significantly improve matching speed and efficiency.

Related Dissertations

  1. Research on Automatic Detection Algorithm for Substructure Distress of Highway Pavement Based on SVM,U418.6
  2. Research on Autamatic Music Structrue Analysis,TN912.3
  3. Research on Transductive Support Vector Machine and Its Application in Image Retrieval,TP391.41
  4. Fault Diagnosis Method Based on Support Vector Machine,TP18
  5. Process Support Vector Machine and Its Application to Satellite Thermal Equilibrium Temperature Prediction,TP183
  6. Intrusion detection based on the ultrasonic echo envelope in the military security patrols,E919
  7. Research for Infrared Image Target Identification and Tracking Technology,TP391.41
  8. Study on the Road Condition Monitoring Based on Vehicular 3D Acceleration Sensor,TP274
  9. Research on Intrusion Detection Technology of Wireless Sensor Networks Based on Behavior Trust,TP212.9
  10. Research of Diagnosing Cucumber Diseases Based on Hyperspectral Imaging,S436.421
  11. Association rule mining based Intrusion Detection System Research and Implementation,TP393.08
  12. The Research on Intrusion Detection System Based on Machine Learning,TP393.08
  13. Prediction of Binding Affinity of Human Transporter Associated with Antigen Processing,R392.1
  14. Research and Implementation of Pedestrian Detection in Video Images,TP391.41
  15. Research on Relationship Extraction Based on Semantic Pattern Matching in Web Environment,TP391.1
  16. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  17. Research on Face Recognition Based on AdaBoost Algorithm,TP391.41
  18. Research on Feature Extraction, Selection and Classification Algorithms for Pulmonary CAD,TP391.41
  19. Construction of Amino-Acid Substitution Matrix of Archaea Domain,Q936
  20. Research on Subimage Selection and Mathching Method for Synthetic Aperture Radar(SAR) Target Recognition,TN957.52
  21. Research of Facial Expression Recognition Algorithm,TP391.41

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Computer network > General issues > Computer Network Security
© 2012 www.DissertationTopic.Net  Mobile