Medical data publishing based on average distribution and clustering

Most of the data publishing methods have not considered sensitivity protection, and hence adversary can disclose privacy by attack. Faced with this problem, paper presents a medical method based on determination. To protect sensitivity, disease information is determined semantics. seek trade-off between utility security, new focusses protection sensitive values high assigns highly to groups as evenly possible. The experiments are conducted two real-world datasets, which records include various attributes patients. measure authors define metric, evaluate degree disclosure. Besides, additional loss discernability metrics used availability released tables. experimental results indicate that provide better than traditional one while guaranteed. Besides value proposed available releasing for data.