Hybrid Anonymization Technique For Improving The Privacy In Network Data
There has been a considerable research over the last decades on methods for limiting disclosure in data publishing, especially for the last twenty years in the computer science field. Researchers have studied the problems of publishing microdata or network data without revealing any sensitive inform...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English |
| Published: |
2016
|
| Subjects: | |
| Online Access: | http://eprints.utem.edu.my/id/eprint/18567/1/Hybrid%20Anonymization%20Technique%20For%20Improving%20The%20Privacy%20In%20Network%20Data%2024%20Pages.pdf http://eprints.utem.edu.my/id/eprint/18567/2/Hybrid%20Anonymization%20Technique%20For%20Improving%20The%20Privacy%20In%20Network%20Data.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | There has been a considerable research over the last decades on methods for limiting disclosure in data publishing, especially for the last twenty years in the computer science field. Researchers have studied the problems of publishing microdata or network data without revealing any sensitive information that may have cause the paradigm preservation of information privacy. There are organizations that would like to publish their data for research, advertisement or prediction purposes. Nevertheless, they had the problems in information loss and lack of privacy. Hence, there are a few techniques and research that have been in highlights like the K-anonymity, l-diversity, generalization, clustering and randomization techniques, but most of these techniques is not comprehensive and the chances to lose the information is still high and may cause privacy leakage on the original data. The contribution of this research is the hybrid technique in anonymization process that will improve the protection and the privacy of data. With this better and comprehensive solution, it will decrease the loss of information. There are four major phases in this methodology as research guidance. The first phase is an overview of the entire research process and the second phase is the description of the anonymization process and techniques. It will be followed by the third phase of describing the design and module of the system, and the fourth phase is the researcher highlights on the comparison methods that are designed in this study. The researcher stated that there are two main contributions in this research. The first contribution is to introduce a new technique to anonymize the network data using the hybrid technique; and for the second contribution, the researcher creates a profile of a hybrid anonymization technique based on K-anonymity, l-diversity, generalization, clustering and randomization techniques. It is quite difficult to identify the best technique of anonymization process. Due to this, the researcher provides the details of analyzing, summarizing and profiling of the anonymization techniques. The researcher realizes that there are a few opportunities to advance this research within this domain in the near future, such as implementing a real-time based in anonymization process. Unfortunately, this type of processing needs to be revamped from the architectural design until the data processing part; and it is more thought-provoking if it were implemented in a real-time based or in the batch processing process, if the variable of the optimization is to be used in the anonymization process. Apart from that, the profiling of the anonymization processing techniques will also help the researcher to propose a generalization technique that might be implemented to anonymize data either using the micro or the network data. |
|---|