Anonymizing transaction data to eliminate sensitive inferences

摘要: Publishing transaction data containing individuals' activities may risk privacy breaches, so the need for anonymizing such before their release is increasingly recognized by organizations. Several approaches have been proposed recently to deal with this issue, but they are still inadequate preserving both utility and privacy. Some incur unnecessary information loss in order protect data, while others allow sensitive inferences be made on anonymized data. In paper, we propose a novel approach that enhances protection anonymization. We model potential of identities associated as set implications, design an effective algorithm capable prevent these minimal loss. Experiments using real-world show our outperforms state-of-the-art method terms utility.