Multidimensional crowdsourcing data truth value discovery method based on localized differential privacy

Abstract

The invention discloses a multidimensional crowdsourcing data true value discovery method based on localized differential privacy, which is applied to a crowdsourcing platform comprising n users, an untrusted server s and m projects, and is carried out according to the following steps of: 1, a data disturbance stage of disturbing crowdsourcing data answered by the users by using a random responsemechanism to generate private data; 2, a private data processing stage of processing private data to generate estimated synthetic data; and 3, a truth value discovery stage of performing truth value discovery on the estimated synthetic data to obtain a final accurate answer. According to the invention, data protection is carried out on data of a user by using a strong privacy protection mechanism-localization differential privacy; and information leakage is prevented, through utilizing truth value discovery, result inaccuracy caused by conflicts among the data and inconsistent user quality issolved, truth value updating accuracy is guaranteed, and user privacy and data availability can be guaranteed in the crowdsourcing platform.

Description

technical field [0001] The invention relates to the technical field of network and information security, in particular to a method for discovering the truth value of multi-dimensional crowdsourcing data based on localized differential privacy. Background technique [0002] With the rapid development of Internet technology, the form of crowdsourcing has developed from an offline mode to a network mode, that is, users can use smart devices to participate in crowdsourcing tasks anytime and anywhere. Enterprises use this method to widely gather user data and understand user needs through data. To reduce its own cost, crowdsourcing has become an effective solution to many challenging tasks. However, on the one hand, due to various reasons, influenced by financial incentives, subjective consciousness inference, etc., the accuracy of users' answers to tasks varies. , that is, there are conflicts between the data provided by users, which requires consideration of how to aggregate no...

AI Technical Summary

Problems solved by technology

[0006] In order to overcome the deficiencies of the existing technology, the present invention provides a method for discovering the truth value of multi-dimensional crowdsourcing data based on localized differential privacy, in order to solve the problem of an adversary with any background knowledge leaking user sensitive data and being unable to learn from the noisy environment. Accurately answer the questions in the data set, and at the same time allow any third party to estimate the original data distribution without knowing the user's sensitive information, so as to ensure the privacy of user data and effectively obtain each crowdsourcing project The purpose of accurate results in

Images