Privacy protection in cross-platform recommender systems: techniques and challenges

【Author】 Sun, Zewei; Wang, Zining; Xu, Yanwei

【Source】WIRELESS NETWORKS

【影响因子】2.701

【Abstract】This paper provides an in-depth exploration of privacy protection in crossplatform recommender systems. With the rapid development of information technology, cross-platform recommender systems have become a vital tool for providing personalized experiences to users. However, these systems, while collecting vast amounts of personal data for targeted recommendations, pose significant privacy risks. This paper presents a review of the current state-of-the-art techniques for privacy protection, including differential privacy, federated learning, and blockchain-based methods. Each technique's effectiveness and limitations are evaluated, offering insights into their practical application in real-world settings. Additionally, the paper identifies the distinct challenges associated with preserving privacy in cross-platform scenarios due to the complex data-sharing mechanisms among different platforms. These challenges involve multiple aspects, such as user identity linkage, data inconsistency, and diverse privacy policies across platforms. Finally, we propose potential solutions and future research directions to address these challenges, emphasizing the need for balancing effective personalization and stringent privacy protection in cross-platform recommender systems.

【Keywords】Privacy protection; Recommender systems; Cross-platform; Personalization; Survey

【发表时间】2023 2023 SEP 28

【收录时间】2023-10-22

【文献类型】综述

【主题类别】

区块链技术-协同技术-推荐系统