News Dissemination Information Model and User Privacy Protection Method Based on BP Neural Network

Jingjing Guo, Jianqiang Wang


Online social networks are widely used as the main way of news dissemination, but the dynamic information dissemination process in online social networks often requires more work to predict and control user privacy accurately. A novel dissemination information model and user privacy protection method based on BP neural network is proposed. First, in constructing a neural network, it is necessary to calculate the network weight vector for the training sample set. Secondly, to ensure that the private information of the neural network learning model is not leaked, this paper proposes to allocate the weight vector to all participants so that each participant has part of the private value of the weight vector. In addition, a secure multi-party computing protocol is used to ensure the safety of the intermediate and final weights of the neural network. Ensure the rationality of information dissemination and the security of user privacy. Experimental results show that the proposed algorithm has more advantages in execution time and accuracy error than traditional non-privacy protection algorithms.

Full Text:



Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.