Qing Haohua, Ibrahim Roliana, Nies Hui Wen
Department of Applied Computing and Artificial Intelligence, Faculty of Computing, Universiti Teknologi Malaysia, Johor Bahru, Johor 81310, Malaysia.
iScience. 2024 Nov 18;27(12):111412. doi: 10.1016/j.isci.2024.111412. eCollection 2024 Dec 20.
With the increasing popularity of location-based services (LBSs), safeguarding location privacy has become critically important. Traditional methods often struggle to balance the intensity of privacy protection with service quality. To address this challenge, this research proposes the comprehensive location privacy enhanced model (CLPEM), which enhances personalized privacy protection by integrating dynamic weight allocation at the policy layer, incorporating a user feedback mechanism, and designing tailored privacy strategies for various scenarios. Additionally, the model employs data fusion and optimization techniques to enhance the usability of location data while ensuring effective privacy protection. Our experimental results demonstrate that CLPEM outperforms existing technologies in terms of privacy strength, data availability, and user satisfaction, providing a robust technical framework for location privacy and paving the way for future research and applications.
随着基于位置的服务（LBS）越来越受欢迎，保护位置隐私变得至关重要。传统方法往往难以在隐私保护强度和服务质量之间取得平衡。为应对这一挑战，本研究提出了综合位置隐私增强模型（CLPEM），该模型通过在策略层集成动态权重分配、纳入用户反馈机制以及为各种场景设计定制的隐私策略来增强个性化隐私保护。此外，该模型采用数据融合和优化技术来提高位置数据的可用性，同时确保有效的隐私保护。我们的实验结果表明，CLPEM在隐私强度、数据可用性和用户满意度方面优于现有技术，为位置隐私提供了一个强大的技术框架，并为未来的研究和应用铺平了道路。
