Organizations, such as government agencies or hospitals, regularly release microdata (e.g., census data or medical records) to serve benign purposes. However, such data can inadvertently reveal sensitive personal information to malicious adversaries. Experience has shown that merely concealing explicit identifying attributes, such as name or phone number, does not suffice to protect personal privacy. Today, the publication of microdata poses a privacy threat. Vast research has striven to define the privacy condition that microdata should satisfy before it is released, and devise algorithms to anonymizing the data so as to achieve this condition. Yet, no method proposed to date explicitly bounds the percentage of information an adversary gains after seeing the published data for each sensitive value therein.