Data Perturbation

Data perturbation, as the expression implies, is the act of perturbing or disturbing data. This technique is typically used in statistical databases, where it is important to obtain accurate analysis while protecting sensitive data. A census or medical database is an example of a database with lots of statistical information that could be used for good or evil. There are many ways to perform perturbation on data. However, you will want to be careful that the perturbation does not affect the results of any data mining that you would like to perform. The effect that perturbation has on a set of data is typically called bias. The four main types of bias that can occur with perturbation are classified as types A, B, C, and D.[12] ...

Get Privacy What Developers and IT Professionals Should Know now with the O’Reilly learning platform.

O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.