The Protection Analysis of Personal Privacy in the Data Age

With the widespread popularity of intelligent mobile terminals, various social application software has rapidly developed to provide users with convenient and fast communication and sharing experiences. At the same time, due to the continuous expansion of user scale, the phenomenon of pan socialization on social networks is becoming increasingly apparent, which has a negative impact on users’ sharing and browsing. When users share their status, it can unintentionally expand the scope of personal information dissemination, which poses a risk of privacy leakage for users. In addition, due to the mixed data in the network, users are constantly invaded by spam while browsing information, seriously affecting the normal user experience. In response to the above issues, this article proposes a privacy permission setting scheme based on intimacy. In order to address the shortcomings of the binary definition of friend relationships in social platforms, such as inaccurate measurement of friend intimacy and poor flexibility, this scheme utilizes data mining technology and combines friend attribute information, behavioral data and environmental factors to propose a fine-grained intimacy quantification method. And this article sets corresponding access permission levels based on relationship quantification values to further control the scope of privacy information dissemination. By obtaining real-time feature data for online intimacy calculation, different privacy permission openness levels are set based on the calculated relationship values. And this article evaluates the effectiveness of the network model constructed by convolutional neural network (CNN), and the experimental results verify the effectiveness of this scheme, proving its practical application ability.