Data security filtering system and method in crowd sensing

Abstract

The invention discloses a data security filtering system and method in crowd sensing. The method comprises six parts of initialization and key generation, task generation, task release, data sensing, data security filtering and data decryption. A feature vector encrypted by a public key of a crowd sensing platform CSP is submitted by a sensing user to an edge node for filtering, and the edge node can only obtain a corrected cosine similarity relationship between the data feature vector of the sensing user and a data sample provided by the crowd sensing platform CSP and cannot obtain other information of the sensing user. And the filtered submitted data is also encrypted by the public key of the crowd sensing platform, so that the edge node cannot mine the effective information of the user, and the privacy of the user is ensured. Meanwhile, the edge node can calculate and correct the cosine similarity only by performing one round of interaction with the sensing user, so that the communication overhead can be greatly reduced. The method has the advantages of high privacy protection security, high communication efficiency and high data availability.

Description

technical field [0001] The invention belongs to the technical field of crowdsensing (Crowdsensing) and the technical field of security data filtering, and relates to a data security filtering system and method in crowdsensing; in particular, it relates to a method for filtering heterogeneity by modifying cosine similarity in crowdsensing A system and method for obtaining data without leaking perceived user data to edge nodes. Background technique [0002] As an emerging spatial crowdsourcing application, crowd sensing is considered to be a useful paradigm for data collection and decision-making, allowing a group of individuals to collaboratively perceive data through their mobile devices, such as smartphones, tablets, cameras, and smart vehicles. Extract social events and some useful information from it. At present, many applications based on group intelligence have been produced, such as restaurant recommendation, vehicle navigation and parking lot discovery, environmental...

AI Technical Summary

Problems solved by technology

[0004] At present, there are some methods to solve the above problems, such as interaction-based privacy-preserving cosine similarity calculation; simply speaking, it is to calculate the cosine similarity between user data and sample data through multiple rounds of interaction between edge nodes and sensing users to judge whether Data needs to be filtered; however, ordinary cosine similarity cannot be used for data filtering when some features are missing, and the data can only be discarded, and too much user interaction will bring greater communication overhead and calculation delay

Images