Multidimensional data local privacy preservation method based on connection function in group intelligence perception system
A technology of group intelligence sensing system and connection function, which is applied in the field of privacy protection, can solve the problems of dimensionality disaster, signal-to-noise ratio reduction, and vulnerability to internal attacks, etc., and achieve the effect of improving utility, effective privacy protection, and avoiding dimensionality disaster
Active Publication Date: 2019-03-22
XI AN JIAOTONG UNIV
View PDF3 Cites 4 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
On the one hand, most of the existing methods assume that the server is trusted, that is, non-local privacy protection, which makes it vulnerable to internal attacks; on the other hand, the output of multi-dimensional sensing data is huge, and when the dimension of sensing data increases, the existing methods are easy to suffer from the "curse of dimensionality", and the signal-to-noise ratio will be severely reduced
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0039] The present invention will be described in further detail below in conjunction with the accompanying drawings.
[0040] reference figure 1 The method for local privacy protection of multi-dimensional data based on connection functions in the intelligent perception system provided by the present invention specifically includes the following steps:
[0041] Step1 Perceived data local privacy conversion: Given the d-dimensional perceptual data D of N users, the data of each user is directly hashed into a bit string on the user side, and then the bit string is randomly flipped to obtain the privacy-protected bit string , And sent to the server, the expression for obtaining differential privacy protection is
[0042]
[0043] Among them, ε represents the degree of differential privacy protection, h is the number of hash functions, and f is the rollover probability;
[0044] Step1 specifically includes the following steps:
[0045] Step1-1 Hash mapping: d-dimensional data for each us...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a multidimensional data local privacy protection method based on a connection function in an intelligent perception system. The method of the invention is firstly based on a method of local privacy conversion, local privacy protection is carried out on the perceptual data of the participating users at the user end, and then sampling and synthesizing the privacy preserved data based on the connection function, Compared with the general privacy protection method, the invention not only can provide local differential privacy protection at the user end, but also can improvethe utility of the published data by reducing the multidimensional perceived data range space. In the process of realizing the invention, the dimensionality reduction processing of the multidimensional data is realized, and the overhead is limited to the part of local conversion and two-dimensional probability distribution estimation, without complex operation or encryption and decryption. In thegroup intelligence perception system, the invention is simple, easy to realize, strong in expansibility and high in practical value.
Description
Technical field [0001] The invention belongs to the field of privacy protection, and specifically relates to a multi-dimensional data local privacy protection method based on a connection function in a group intelligence perception system. Background technique [0002] With the advent and rapid development of the information age, a wide range of data sources and the fusion of diverse data have formed a real big data group intelligence perception system. Perception data from a large number of participating users will be aggregated on the server side, and finally the server will be aggregated. The multi-dimensional group intelligence perception data is sent to a third-party organization for analysis and research to facilitate people's production and life and provide a more efficient social environment. However, the direct release of high-dimensional perception data will expose the private information of participating users, and due to the correlation between the attributes of high-...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06F21/62G06F21/60
CPCG06F21/602G06F21/6245
Inventor 杨新宇王腾任雪斌姚向华魏洁翟守沛王舒阳
Owner XI AN JIAOTONG UNIV