Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Deepfake traceability system based on big data federated learning architecture

A big data and federal technology, applied in the field of deep counterfeit traceability system, to improve detection accuracy, prevent web security threats, and protect privacy and security

Active Publication Date: 2021-11-30
UNIV OF ELECTRONICS SCI & TECH OF CHINA
View PDF11 Cites 9 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Video forgery will infringe the legal rights and interests of the video protagonist, such as the portrait right, but if only the detection of video forgery will lead to the people who forgery the video will not be punished as they should

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
  • Deepfake traceability system based on big data federated learning architecture
  • Deepfake traceability system based on big data federated learning architecture
  • Deepfake traceability system based on big data federated learning architecture

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] In this example, if figure 1 As shown, a deep forgery traceability system based on the big data federated learning architecture includes an application layer, an interface layer, a logic layer, a network layer, and a storage layer connected sequentially; Users provide deep fake traceability services and obtain user login and upload data; interface layer is used to provide interface services and realize communication between server and web; logic layer is used to divide system functions and design algorithms to build models to realize the system Functional logic; network layer, used to exchange parameters between the logic layer and storage layer, and encrypt the gradient information during the modeling process of the logic layer; storage layer, used to receive parameter information and encrypted information transmitted by the network layer, And stored in the local database and blockchain network respectively.

[0053] In this embodiment, on the application layer, the ...

Embodiment 2

[0062] In this embodiment, the functions of the system are elaborated and further optimized on the basis of the first embodiment. In this embodiment, in order to solve problems such as deep forgery detection and privacy protection, the following core algorithms are designed. This embodiment mainly introduces the key algorithms used in this system, demonstrates the related principles, and presents the corresponding test results.

[0063] 1. 3DRes Deep Forgery Detection Algorithm Design

[0064] First, we analyze the principle of deep forgery to lay the foundation for proposing a 3DRes deep forgery detection algorithm; secondly, we preprocess the original data set; finally, we build a 3DRes deep forgery detection model, and the experimental results show that compared with traditional algorithms, 3DRes can accurately Sex can be greatly improved.

[0065] 1.1 Principle of Deep Forgery

[0066] Although all users of this system will use federated learning to continuously update ...

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 deepfake traceability system based on a big data federated learning architecture. The system comprises: an application layer, an interface layer, a logic layer, a network layer, and a storage layer which are connected in sequence; the application layer is used for providing a deepfake traceability service for a user and obtaining user login and uploading data; the interface layer is used for providing interface service and realizing communication between a server side and a web side; the logic layer is used for dividing system functions and designing an algorithm to construct a model to realize system function logics; the network layer is used for carrying out parameter exchange and encrypting gradient information in a modeling process; the storage layer is used for receiving transmitted parameter information and encrypted information and storing the parameter information and the encrypted information in a local database and a blockchain network. According to the system, an overall architecture of federated anti-counterfeiting traceability chains is provided, a federated anti-counterfeiting mechanism, an abnormal traceability mechanism and a risk prediction mechanism are established, Web security threats can be prevented, and the problems of data poisoning and single-point failure for federated learning can be effectively solved.

Description

technical field [0001] The invention relates to the technical field of deep forgery detection, in particular to a deep forgery traceability system based on a big data federated learning framework. Background technique [0002] It has been more than ten years since the concept of smart city was put forward. As of 2020, the number of smart city pilot projects announced by the Ministry of Housing and Urban-Rural Development has reached 290. In the process of deep integration of the new generation of information technology and urban modernization, the face recognition system has been widely used in many important fields related to the national economy and people's livelihood, and has become a favorable weapon to promote the construction of smart cities. According to the statistics of Southern Metropolis Daily, the main application scenarios of face recognition in China in 2020 are as follows Picture 1-1 -1 shown. Face recognition technology has become the pearl of various biom...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06N3/04G06N3/08G06N20/00
CPCG06N3/08G06N20/00G06N3/045
Inventor 倪志彬唐龙翔王昊龙梁淇奥何震宇蒋新科向芝莹周啸宇石爻李顺左健甫杨若辰吴世涵张恩华吉雪莲常世晴罗佳源陈攀宇王瑞锦
Owner UNIV OF ELECTRONICS SCI & TECH OF CHINA
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com