In Chap. 3 , we discussed a multi-objective anonymisation approach to generating privacy preserving data in low computational and power resource settings and explained that such a mechanism is useful in creating generic privacy-preserving datasets for contexts in which per-query anonymisation is impractical either due to performance or real-time constraints. multi-objective anonymisation is however not well-suited to anonymising high dimensional datasets that result from composing data belonging to different data owners and that can also arise from distributed data sources.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

High-Dimensional Data: Privacy Considerations

  • Anne V. D. M. Kayem

摘要

In Chap. 3 , we discussed a multi-objective anonymisation approach to generating privacy preserving data in low computational and power resource settings and explained that such a mechanism is useful in creating generic privacy-preserving datasets for contexts in which per-query anonymisation is impractical either due to performance or real-time constraints. multi-objective anonymisation is however not well-suited to anonymising high dimensional datasets that result from composing data belonging to different data owners and that can also arise from distributed data sources.