Before we publish any statistic, we apply safeguards. These safeguards help prevent someone from using that statistic to learn about a specific person.

We call these safeguards “disclosure avoidance,” although these methods are also known as “statistical disclosure controls” or “statistical disclosure limitations.”

Although it might appear that a published table shows information about a specific individual, the Census Bureau uses disclosure avoidance methods to remove, modify, or disguise the original data to protect confidentiality, while also ensuring that the results are still useful. These statistical methods include techniques such as “suppression,” “coarsening,” and “noise infusion."

A June 2026 Department of Commerce administrative order, developed by the Department in conjunction with the Office of the Undersecretary for Economic Affairs and with technical guidance from the U.S. Census Bureau, updated the set of disclosure avoidance methods available for statistical products. Under this policy, noise infusion may no longer be used, and coarsening is now the preferred disclosure avoidance method, with suppression permitted only when necessary (such as if coarsening of a statistical product is prohibited by law or would substantially defeat the accuracy or usability of the product). We are evaluating alternative protections for the data products impacted by the new policy and will update those web pages as decisions are made.

Implementing any disclosure avoidance system involves design choices. These choices ultimately determine how tradeoffs between accuracy of the disseminated statistics, the degree of data protection, and the availability of the resulting statistics are managed. We call this the “triple tradeoff.”

Design implementation choices on any of those three dimensions can result in different statistical results. These implementation choices are separate and distinct from the different strengths and weaknesses that are inherent in disclosure avoidance methods, such as a disclosure avoidance method’s ability to measure disclosure risk or how easy it is to understand the impact of the method on the usability of the statistics.

When we are choosing between disclosure avoidance methods for a specific statistical product, we use an objective set of principles as the selection framework. The principles include the degree to which a disclosure avoidance method can assess both the risk of disclosure and the impact on statistical accuracy, its ability to target both protection and usability of statistics for different types of geographical units and subpopulations, its ability to track cumulative disclosure risk over time, its transparency, and its feasibility. You can learn more about this framework here:

You can find descriptions of specific disclosure avoidance methods in the technical documentation for most data products, as well as the following pages: