Deriving Private Information from Perturbed Data using IQR Based Approach
Several randomized techniques have been proposed for privacy preserving data mining of continuous data. These approaches generally attempt to hide the sensitive data by randomly modifying the data values using some additive noise and aim to reconstruct the original distribution closely at an aggrega...
Saved in:
| Main Authors: | , , |
|---|---|
| 格式: | text |
| 語言: | English |
| 出版: |
Institutional Knowledge at Singapore Management University
2006
|
| 主題: | |
| 在線閱讀: | https://ink.library.smu.edu.sg/sis_research/321 http://dx.doi.org/10.1109/ICDEW.2006.47 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 總結: | Several randomized techniques have been proposed for privacy preserving data mining of continuous data. These approaches generally attempt to hide the sensitive data by randomly modifying the data values using some additive noise and aim to reconstruct the original distribution closely at an aggregate level. However, one challenge here is whether the reconstructed distribution can be exploited by attackers or snoopers to derive sensitive individual data. This paper presents one simple attack using Inter-Quantile Range on reconstructed distribution. The experimental results show that current random perturbation-based privacy preserving data mining techniques may need a careful scrutiny in order to prevent privacy breaches through this model based inference. |
|---|