Loading...

An Intrusion Detection System for the Grid Environment

Movahed, Amirvala | 2009

687 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: English
  3. Document No: 39675 (52)
  4. University: Sharif University of Technology, International Campus, Kish Island
  5. Department: Science and Engineering
  6. Advisor(s): Jalili, Rasool
  7. Abstract:
  8. Existing Intrusion Detection Systems (IDSs) are not designed to deal with all categories of processing environments. This thesis focuses on IDSs for the Grid computing environment, and concentrates on feature selection and performance. An existing framework, Globus, is used as the basis for the consideration and development of the research issue in Grid computing. The system is based on two engine designs: (a) Signature and (b) Support Vector Machine; SVM has been selected for pattern discovery in traffic analysis. We found that the performance of the system greatly depends on the efficiency of the underlying framework and the number of Intrusion Detection System instances. We demonstrate and present a number of optimizations that can improve the algorithm's performance. The simulation process of the proposed framework shows that the performance of the system clearly depends on the number of the GIDS instances. During the simulation process of different algorithms of SVM, We document a higher level of accuracy of the SVM engine when using the CT-SVM algorithm. In the case of increasing the instances of GIDS, the false positive and false negative also appear to decrease at a much faster pace.
  9. Keywords:
  10. Intrusion Detection System ; Grid Computing ; Support Vector Machine (SVM) ; Globus Framework

 Digital Object List

 Bookmark

No TOC