Portrait biological characteristic privacy protection and decryption method

A privacy protection and biometric technology, applied in the field of deep learning applications, can solve problems such as illegal use of privacy

Active Publication Date: 2020-09-29
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

While enjoying the "dividends" brought by artificial inte

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Portrait biological characteristic privacy protection and decryption method
  • Portrait biological characteristic privacy protection and decryption method
  • Portrait biological characteristic privacy protection and decryption method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0056] The technology of the network architecture design in this embodiment mainly involves the following types of technologies: 1) portrait encryption and key generation method: use the attention mechanism and the codec network to precisely encrypt the portrait image, and at the same time, extract the input portrait data The portrait identity feature vector defines the identity characteristics of the encrypted result, so that the encrypted portrait and the input portrait data have similar visual effects; 2) Encrypted portrait and key storage method: according to the principle of who uploads who has the right , after encrypting the actual collected face image, the encrypted portrait is uploaded to the cloud server, and the corresponding unique key is stored in the local server, and the read permission of the key is reserved locally; 3) Portrait decryption method: cloud The server adopts a cooperative processing method to process user applications and local server key authorizat...

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

No PUM Login to view more

Abstract

The invention discloses a portrait biological characteristic privacy protection and decryption method. The method comprises the following steps: constructing and training a portrait encryption and keygeneration network model, extracting portraits and corresponding identity information as input of the network model according to annotation information of a face database, and training a designed network by utilizing constructed data to finally obtain network model weights; actual portrait encryption and key storage: performing encryption and key generation on the actually acquired portrait by using the network model, and separately storing the encrypted portrait and the key; and decrypting the encrypted portrait, and cooperatively processing a decryption task of the user by the cloud serveraccording to a decryption demand of the user side. According to the method, a deep learning network technology is applied to portrait encryption to generate encrypted portraits with similar visual effects; the encrypted portrait and the secret key are stored separately, and the user is assisted to decode the portrait in a cloud cooperative processing mode, so that the possibility of information leakage can be reduced, and rapid decryption of the user is realized.

Description

technical field [0001] The invention relates to the field of deep learning application technology, in particular to a method for protecting and decrypting the privacy of portrait biometric features. Background technique [0002] With its security and convenience, biometric identification has been widely used in the field of identity authentication. Identification based on biometrics can solve the problems of insecurity and inconvenience in traditional identification. Among biometric features such as fingerprints, portraits, palmprints, iris, retina, voice, and gait, portraits are the most widely used for identification due to their high versatility, uniqueness, permanence, availability, and acceptability. one of the biological characteristics. In recent years, portrait recognition has achieved very significant research results, and the recognition rate and recognition speed have been greatly improved. [0003] The rise of a new generation of artificial intelligence, while...

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
no application Login to view more
IPC IPC(8): G06F21/62G06F21/60G06K9/00G06K9/62
CPCG06F21/6245G06F21/602G06V40/168G06F18/214
Inventor 谢巍余孝源张浪文余锦伟
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap