Name
Abstract | ||
|---|---|---|
At present, data mining algorithms are largely the domain of governments, large organisations and academia where they provide useful insight into the data. However, without the ability to assure privacy protection, the availability of datasets for research purposes may be impaired. Moreover, privacy-preservation is essential if data mining is to be permitted widespread use in government and commercial contexts. Indeed, as data mining algorithms become more widespread, even the datasets currently made available under limited release now may become more restricted. In addition, the ambiguous definitions currently in use hinder the assessment of the quality of the privacy preservation. This paper categorises the protection objectives during the data mining process into bands and then presents a reconceptualization of privacy-preserving data mining algorithms from the viewpoint of these bands. Existing algorithms from eight protection strategies are selected as examples to explain the six bands. Significantly, gaps are revealed in the Privacy Preserving Data Mining literature that indicate areas for future research. |
Year | Venue | Field |
|---|---|---|
2011 | AusDM | Data mining,Privacy by Design,Computer science,Computer security,Data mining algorithm,Privacy management,Privacy software,Government |
DocType | Citations | PageRank |
Conference | 3 | 0.42 |
References | Authors | |
52 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rui Li | 1 | 3 | 0.42 |
| Denise De Vries | 2 | 53 | 8.14 |
| John F. Roddick | 3 | 1908 | 331.20 |