Privacy-aware multidimensional indexing

Abstract

Deleting data from a database system in a forensic secure environment and in a high performant way is a complex challenge. Due to redundant copies and additional information stored about data items, it is not appropriate to delete only data items themselves. Additional challenges arise when using multidimensional index structures. This is because information of data items are used to index the space. As initial result, we present different deletion levels, to overcome this challenge. Based on this classification, we analyze how data can be reconstructed from the index and modify index structures to improve privacy of data items. Second, we benchmark our index structure modifications and quantify our modifications. Our results indicate that forensic secure deletion is possible with modification of multidimensional index structures having only a small impact on computational performance, in some cases.