Misfeasors Classification and Detection Models Using Machine Learning Techniques/ (Record no. 9186)

MARC details
000 -LEADER
fixed length control field 04072nam a22002537a 4500
008 - FIXED-LENGTH DATA ELEMENTS--GENERAL INFORMATION
fixed length control field 211216b2010 |||a|||f mb|| 00| 0 eng d
040 ## - CATALOGING SOURCE
Original cataloging agency EG-CaNU
Transcribing agency EG-CaNU
041 0# - Language Code
Language code of text eng
Language code of abstract eng
082 ## - DEWEY DECIMAL CLASSIFICATION NUMBER
Classification number 658
100 0# - MAIN ENTRY--PERSONAL NAME
Personal name Nesrine Sameh Said
245 1# - TITLE STATEMENT
Title Misfeasors Classification and Detection Models Using Machine Learning Techniques/
Statement of responsibility, etc. Nesrine Sameh Said
260 ## - PUBLICATION, DISTRIBUTION, ETC.
Date of publication, distribution, etc. 2010
300 ## - PHYSICAL DESCRIPTION
Extent 94 p.
Other physical details ill.
Dimensions 21 cm.
500 ## - GENERAL NOTE
Materials specified Supervisor: Neamat El-Gayyar
502 ## - Dissertation Note
Dissertation type Thesis (M.A.)—Nile University, Egypt, 2010 .
504 ## - Bibliography
Bibliography "Includes bibliographical references"
505 0# - Contents
Formatted contents note Contents:CONTENT PAGE<br/> <br/>Acknowledgments i<br/>List of Tables iv<br/>List of Figures vi<br/>List of Abbreviations vii<br/>Abstract viii<br/><br/>CHAPTER 1: INTRODUCTION 1<br/>1.1 BACKGROUND 3<br/>1.2 MOTIVATION 7<br/>1.3 PROBLEM FORMULATION 9<br/>1.4 OBJECTIVES AND CONTRIBUTIONS 10<br/>1.5 THESIS OUTLINE 11<br/>CHAPTER 2: MISFEASORS AND MACHINE LEARNING: STATE OF THE ART 12<br/>2.1 MISFEASORS 12<br/>2.2 MISFEASORS AND MACHINE LEARNING 14<br/>2.3 IP SPOOFING DETECTION 16<br/>2.3.1 Arpwatch 16<br/>2.3.3 ARPDefender 18<br/>2.3.4 XArp 18<br/>2.3.5 ArpON 2.0 20<br/>2.3.6 Cisco ASA 5500 Firewall 20<br/>2.3.7 Sygate Personal Firewall 5.0 21<br/>2.3.8 NetScreen 21<br/>CHAPTER 3: MISFEASORS 23<br/>3.1. TYPES 23<br/>3.2. MOTIVES 25<br/>3.3. FEATURES AND ATTACKS 27<br/>3.4. DEFENSIVE MEASURES AGAINST MISFEASORS 31<br/>CHAPTER 4: MACHINE LEARNING 33<br/>4.1. DEFINITION 33<br/>4.2. ADVANTAGES 35<br/>4.3. CLASSIFIERS 37<br/>4.3.1. Naive Bayes Classifier 37<br/>4.3.2. Decision Trees Classifiers 38<br/>4.4. PERFORMANCE MEASURES 40<br/>CHAPTER 5: PROPOSED CLASSIFICATION MODELS 42<br/>5.1. ENHANCING FEATURES USING THE MAC ADDRESS 42<br/>5.2. PROPOSED CLASSIFICATION MODELS 50<br/>5.2.1. The Rule Based Model (Model A) 50<br/>5.2.2. The Hierarchical Classification Model (Model B) 52<br/>5.2.3. The Composite Feature Model (Model C) 54<br/>5.3. EVALUATING CLASSIFIERS PERFORMANCE 55<br/>CHAPTER 6: DATA, EXPERIMENTS AND RESULTS 59<br/>6.1. DATA 59<br/>6.1.1. DARPA1998 Dataset 59<br/>6.1.2. DARPA1999 Dataset 61<br/>6.2. EXPERIMENTS 64<br/>6.2.1. Evaluation Measures 64<br/>6.2.2. Training Data 65<br/>6.3. Results 81<br/>CHAPTER 7: SUMMARY AND FUTURE WORK 89<br/>REFERENCES 92<br/>
520 3# - Abstract
Abstract Abstract:<br/>Misfeasors (or insiders) are considered among the most difficult intruders to detect due to their knowledge and authorization within the organization. Machine learning techniques have been widely used for intrusion detection but only little work has addressed the use of machine learning for detecting and classifying different types of insiders. The aim of this study is to exploit different recognition models for misfeasors detection by adding the Mac address as a feature in classification. Three different recognition models (a Rule Based Model, a Hierarchical Classification Model and a Composite Feature Model) are proposed. The models differ mainly in the amount of prior knowledge required for the problem and hence how training data is used to construct the models. The Rule Based Model uses explicit domain classification rules given by expert to detect insiders. The Hierarchical Classification Model uses some domain specific knowledge to manufacture the training data in order to construct the hierarchy in the recognition model. The Composite Feature Model on the other hand attempts to discover classification rules directly from the training data without any prior knowledge. All three proposed classification models are tested on two benchmark data sets and are evaluated using different performance measures. Results for the different models are presented and compared for several classification techniques. Experiments reveal that using machine learning at different levels in the proposed models yields a good approximation for the classification rules for the problem of misfeasor detection.
546 ## - Language Note
Language Note Text in English, abstracts in English.
650 #4 - Subject
Subject Information Security
655 #7 - Index Term-Genre/Form
Source of term NULIB
focus term Dissertation, Academic
690 ## - Subject
School Information Security
942 ## - ADDED ENTRY ELEMENTS (KOHA)
Source of classification or shelving scheme Dewey Decimal Classification
Koha item type Thesis
650 #4 - Subject
-- 294
655 #7 - Index Term-Genre/Form
-- 187
690 ## - Subject
-- 294
Holdings
Withdrawn status Lost status Source of classification or shelving scheme Damaged status Not for loan Home library Current library Date acquired Total Checkouts Full call number Date last seen Price effective from Koha item type
    Dewey Decimal Classification     Main library Main library 12/16/2021   658/ N.S.M 2010 12/16/2021 12/16/2021 Thesis