New Media User Privacy Protection Mechanism Based on Differential Privacy and Data Anonymization

Abstract

 With the rapid development of new media, user privacy issues have become increasingly important. New media platforms, such as TikTok, Twitter, and WhatsApp, process vast amounts of user data daily, including personal information, behavioral data, and social relationships. The extensive collection and use of this data present numerous privacy protection challenges. Many users are not fully aware of how their data is collected and used when using new media platforms, lacking informed consent regarding data collection. Consequently, relying on users to take proactive privacy measures to prevent the disclosure of critical information is difficult to achieve. To address this issue, this paper proposes a privacy protection mechanism that combines differential privacy and data anonymization. The mechanism protects query results through differential privacy techniques and hides user identity information using data anonymization techniques, thereby ensuring user privacy during data analysis and processing. This paper conducts necessary experimental analysis on the proposed method, and the results demonstrate its usability and effectiveness.