| ABSTRACT | 第1-11页 |
| 摘要 | 第11-21页 |
| CHAPTER 1 INTRODUCTION | 第21-35页 |
| ·Background | 第22-26页 |
| ·Aim of the research | 第26页 |
| ·The Hypotheses | 第26-27页 |
| ·Contribution of the Thesis | 第27-29页 |
| ·Research Methodology and Analyses of Data and Information of This Research | 第29-30页 |
| ·Organization of the Thesis | 第30-35页 |
| CHAPTER 2 BASIC CONCEPTS OF PRIVACY PRESERVING DATE MINING - A LITERATURE SURVEY | 第35-76页 |
| ·Knowledge Discovery in Databases | 第36-45页 |
| ·The KDD Process | 第36-38页 |
| ·A momentary look at Data Mining Tasks | 第38-40页 |
| ·Data Mining versus Statistical Methods | 第40-42页 |
| ·Data Stores for Mining | 第42-45页 |
| ·The Basics of Clustering Analysis | 第45-50页 |
| ·The Major Distance Based Clustering Methods | 第45-47页 |
| ·Data Matrix | 第47-48页 |
| ·Dissimilarity Matrix | 第48-50页 |
| ·The Basics of Association Rule Mining | 第50-54页 |
| ·The Support Confidence Framework | 第50-51页 |
| ·Interestingness Measures | 第51-52页 |
| ·Sensitive Rules and Sensitive Transactions | 第52-53页 |
| ·The Process of Protecting Sensitive Knowledge | 第53-54页 |
| ·The Basics of Dimensionality Reduction | 第54-59页 |
| ·Methods for Dimensionality Reduction | 第55-57页 |
| ·Random Projection | 第57-59页 |
| ·Survey on Privacy Preserving Data Sharing on Data Mining Environments | 第59-76页 |
| ·Classification of Privacy Preserving Techniques | 第59-62页 |
| ·Data mining algorithms | 第62-69页 |
| ·Induction of Decision Trees (IDT) | 第62-63页 |
| ·Rough Sets | 第63-64页 |
| ·Bayesian Approach | 第64-66页 |
| ·k-means Algorithm | 第66-67页 |
| ·The Apriori algorithm | 第67页 |
| ·k-nearest Neighbor Classification | 第67-68页 |
| ·Classification And Regression Trees (CART) | 第68-69页 |
| ·Applications of Privacy Preserving Data Mining | 第69-74页 |
| ·Medicine | 第69-70页 |
| ·Engineering | 第70页 |
| ·Education | 第70-71页 |
| ·Business and Marketing | 第71-73页 |
| ·Against Terrorism | 第73-74页 |
| ·Human Resources | 第74页 |
| ·Summary | 第74-76页 |
| CHAPTER 3 k-ANONYMITY MODEL FOR PRIVACY PRESERVING DATA SHARING | 第76-94页 |
| ·Motivation for k-anonymization of databases for privacy preserving data sharing | 第77-78页 |
| ·k-anonymity Model | 第78-82页 |
| ·Various k-anonymization methods | 第82-85页 |
| ·k-anonymity-Mathematical View | 第85-92页 |
| ·Summary | 第92-94页 |
| CHAPTER 4 SECURE MULTIPARTY COMPUTATION MODEL FOR PRIVACY PRESERVING DATASHARING | 第94-120页 |
| ·Motivation and Highlights | 第95-96页 |
| ·An Introduction to Secure Multiparty Computation | 第96-100页 |
| ·Historical Background of Secure Multiparty Computation (SMC) | 第100-101页 |
| ·Theoretical background of SMC | 第101-103页 |
| ·Foundation of the SMC model | 第103-108页 |
| ·Sub Protocols of SMC | 第105-108页 |
| ·Secure Sum | 第105-106页 |
| ·Secure Comparison/Yao's Millionaire Problem | 第106页 |
| ·Dot Product Protocol | 第106页 |
| ·Oblivious Evaluation of Polynomials | 第106-107页 |
| ·Privately Computing In x | 第107页 |
| ·Secure Intersection | 第107页 |
| ·Secure Set Union | 第107-108页 |
| ·SMC problems | 第108-113页 |
| ·Privacy Preserving Cooperative Scientific Computations | 第108-109页 |
| ·Privacy Preserving Database Query | 第109页 |
| ·Privacy Preserving Intrusion Detection | 第109页 |
| ·Privacy Preserving Data Mining | 第109-110页 |
| ·Privacy Preserving Geometric Computation | 第110-111页 |
| ·Privacy Preserving Statistical Analysis | 第111页 |
| ·More Other Problems | 第111-112页 |
| ·Some More derivative Problems | 第112-113页 |
| ·SMC Problem Solutions | 第113-115页 |
| ·Key Applications of SMC | 第115-118页 |
| ·Classification | 第115-116页 |
| ·Association Rule Mining | 第116-117页 |
| ·Clustering | 第117页 |
| ·Outlier Detection | 第117-118页 |
| ·Summary | 第118-120页 |
| CHAPTER 5 HYBRID METHODS FOR PRIVACY PRESERVING DATA SHARING TECHNIQUES | 第120-160页 |
| ·Motivation for Hybrid model of Privacy Preserving Data Sharing Techniques | 第121-123页 |
| ·The Framework for Privacy Preserving Data Mining in a Hybrid Environment | 第123-136页 |
| ·K-Anonymization | 第124-132页 |
| ·The Inverted File | 第132-133页 |
| ·Library of Sanitizing Algorithms | 第133-134页 |
| ·Set of Metrics | 第134-136页 |
| ·Algorithms | 第136-158页 |
| ·k-Anonymity Preserving Data Mining Algorithms | 第136-140页 |
| ·Data Sharing [Based Sanitizing Algorithms | 第140-149页 |
| ·Round Robin Algorithm for sanitizing | 第141-143页 |
| ·Random Algorithm for sanitizing | 第143-145页 |
| ·Item Grouping Algorithm for sanitizing | 第145-149页 |
| ·Pattern Sharing Based Sanitizing Algorithms | 第149-155页 |
| ·Hybrid Algorithms | 第155-158页 |
| ·Summary | 第158-160页 |
| CHAPTER 6 EVALUATION AND RESULTS | 第160-184页 |
| ·Datasets | 第161-163页 |
| ·Evaluation of the k-anonymized Algorithms | 第163-168页 |
| ·Accuracy vs. Anonymity Tradeoffs in IDT | 第164-165页 |
| ·Privacy Risks and l-Diversity | 第165-168页 |
| ·Evaluation of the Data Sharing Based Algorithms | 第168-176页 |
| ·Sanitizing Algorithms | 第168-169页 |
| ·Methodology | 第169-170页 |
| ·Measuring the Effectiveness | 第170-173页 |
| ·CPU Time for the Sanitization Process | 第173-175页 |
| ·Discussion on the Data Sharing Based Algorithms | 第175-176页 |
| ·Evaluation of the Pattern Sharing Based Algorithms | 第176-182页 |
| ·Pattern Sharing Based Sanitizing Algorithms | 第176-177页 |
| ·Methodology | 第177-178页 |
| ·Measuring Effectiveness | 第178-181页 |
| ·CPU Time for the Sanitization Process | 第181页 |
| ·Discussion on the Pattern Sharing Based Algorithms | 第181-182页 |
| ·Summary | 第182-184页 |
| CHAPTER 7 CONCLUSION AND FUTURE WORKS | 第184-193页 |
| ·Summary | 第185-186页 |
| ·Contributions | 第186-188页 |
| ·Future Research | 第188-193页 |
| ·Challenges Left to Explore | 第188-190页 |
| ·Future Research Trends | 第190-193页 |
| REFERENCES | 第193-204页 |
| APPENDIX A | 第204-221页 |
| A.1 Results of the Transformation of databases in Real Datasets | 第204-209页 |
| A.2 Results of Misses Cost on the Datasets | 第209-221页 |
| A.2.1 Condition C2 (Varying the Number of Sensitive Rules) | 第210-215页 |
| A.2.2 Condition C3 (Varying the Minimum Support Threshold) | 第215-221页 |
| APPENDIX-B | 第221-237页 |
| B1 Results of the Difference between Original and the Sanitized Datasets | 第221-236页 |
| B.1.1 Condition C1 (A set of 6 Sensitive Rules) | 第221-223页 |
| B.1.2 Condition C2 (Varying the Number of Sensitive Rules) | 第223-233页 |
| B.1.3 Effect of y on MC and HF (Rules in Scenario S3) | 第233-236页 |
| B.2 Results of Side Effect Factor on the Datasets | 第236-237页 |
| LIST OF ABBREVIATIONS | 第237-238页 |
| PAPER PUBLICATION AND PRESENTATIONS | 第238-239页 |
| ACKNOWLEDGMENTS | 第239-240页 |
