Privacy protection face verification system based on secret sharing
A technology for sharing secrets and protecting people. It is applied in the field of privacy protection face verification system. It can solve the problems of large computing overhead and limit the actual amount of data, and achieve the effect of small amount of calculation, fast calculation speed and high compatibility.
Pending Publication Date: 2021-12-17
神谱科技(上海)有限公司
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This serious privacy concern limits the actual amount of data
Many scholars have proposed to use technologies such as homomorphic encryption to directly train data encryption, which obviously will bring considerable computational overhead.
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
[0028] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.
[0029] see Figure 1-3 , the present invention provides a technical solution: a privacy protection face verification system based on secret sharing, comprising the following steps:
[0030] S1. Face acquisition: capture the face image through the camera device, perform image noise reduction preprocessing, and detect the face area;
[0031] S2. Feature extraction: through the deep convolution network, the feature extraction of the face area picture is carried ...
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 relates to the technical field of privacy calculation and machine learning, and particularly discloses a privacy protection face verification system based on secret sharing. The system comprises the following steps: S1, obtaining a face; s2, carrying out feature extraction; s3, realizing face template registration through a secret sharing protocol; and S4, carrying out face verification through an MPC protocol. The secret sharing protocol has the advantage of small calculation amount, and the calculation speed is higher than that of homomorphic encryption and other technologies; the face features are protected from being stored in the cloud server, the face feature data cannot be cracked under the condition that collusion between the server and the terminal does not exist, and personal privacy is protected; and the method is suitable for various face neural network models, only needs to apply a secret sharing protocol to the neural network feature layer, and has the advantages of high compatibility and wide applicability.
Description
technical field [0001] The invention relates to the technical field of privacy computing and machine learning, in particular to a privacy protection face verification system based on secret sharing. Background technique [0002] Face recognition technology uses machine learning, especially deep neural network technology, to establish and recognize face models. The existing face verification technology obtains the image features of the face through neural network model training, and compares the similarity, and the face that conforms to the feature model is verified. [0003] Face verification technology plays a very important role in banking, finance, retail, security and other fields. Traditionally, machine learning models are trained on a centralized corpus of data, which may be collected by a single or multiple data providers. Although parallel distributed algorithms have been developed to speed up the training process, the training data itself is still collected and st...
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): G06F21/32G06F21/62G06K9/00G06N3/04G06N3/08
CPCG06F21/32G06F21/6245G06N3/08G06N3/045
Inventor 祝文伟黄程韦徐佳新
Owner 神谱科技(上海)有限公司