A method and device for differential privacy protection based on deep learning
A deep learning and differential privacy technology, applied in machine learning, digital data protection, computer security devices, etc., can solve the problem of poor reliability of differential privacy protection, and achieve the effect of protecting accuracy, improving training speed, and improving reliability.
Active Publication Date: 2022-05-17
WUHAN UNIV OF TECH
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The present invention provides a method and device for differential privacy protection based on deep learning, aiming to solve the technical problem of poor reliability of differential privacy protection existing in the prior art
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
[0059]The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative efforts belong to the protection scope of the present invention.
[0060] In the description of the present invention, "plurality" means two or more, unless otherwise specifically defined.
[0061] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the present invention. The occurrences of this phrase in various places in the specification are not necessarily all referring to the same embodiment, ...
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 present invention provides a method and device for protecting differential privacy based on deep learning. The method includes constructing a deep learning model, the deep learning model includes an initial learning rate and various model parameters; obtaining a first training set, and according to the The deep learning model calculates the gradient of the training samples in the first training set; determines the gradient cumulative sum of squares matrix according to the gradient; determines the privacy budget and adaptive learning rate of the various model parameters based on the gradient cumulative sum of squares matrix; Perform gradient clipping on the gradient to obtain multiple clipping gradients; add noise to the multiple clipping gradients based on the privacy budget to obtain noise gradients; The noise gradient iteratively updates the model parameters to obtain a target deep learning model. The present invention ensures the accuracy of the deep learning model while protecting the privacy of the deep learning model.
Description
technical field [0001] The present invention relates to the technical field of differential privacy protection, in particular to a method and device for differential privacy protection based on deep learning. Background technique [0002] In recent years, deep learning technology has achieved great success in various machine learning, such as signal processing, network modeling and so on. The success of deep learning technology is inseparable from a large amount of user data. Usually, collecting a large amount of user data often leads to serious privacy and security issues. Previous work has demonstrated that personal privacy information in datasets can be recovered by repeatedly querying the output probabilities of disease recognition classifiers built on convolutional neural networks. Today's privacy concerns will prevent users from sharing their data, thereby hindering the future development of deep learning itself. [0003] Aiming at privacy issues, methods based on di...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G06F21/62G06N20/00
CPCG06F21/6245G06N20/00
Inventor 杜亚娟柯银
Owner WUHAN UNIV OF TECH