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

Data security deduplication method based on auto-encoder

A self-encoder, data security technology, applied in the direction of digital data protection, electrical digital data processing, computer security devices, etc., can solve the problem of low efficiency, reduce the number of times, improve the efficiency of deduplication, and improve the efficiency of label comparison.

Active Publication Date: 2021-02-26
CHANGCHUN UNIV OF SCI & TECH
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] In order to solve the problem of low efficiency of the existing data deduplication method based on random message lock encryption, the present invention provides a data security deduplication method based on an autoencoder

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
  • Data security deduplication method based on auto-encoder
  • Data security deduplication method based on auto-encoder
  • Data security deduplication method based on auto-encoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0021]CombineFigure 1 to Figure 2In this embodiment, a method for data security deduplication based on a self-encoder is used to generate a summary label of the data through a self-encoding technology. The original label generated by random message lock encryption is still retained, which is called a fingerprint label. In order to ensure data confidentiality, one key is used to encrypt data, and another key is used to encrypt fingerprint tags. Among them, the same data must be encrypted with the same key to realize the sharing of data among different users; while the fingerprint tag of the same data does not need to be encrypted with the same key, because it is not necessary to compare the fingerprint tag. Decrypt. Since the autoencoder model is similar, that is, the feature distance between similar data is much smaller than that of different data, so the summary tags generated by this model can filter out a set of fingerprint tag sets similar to user data, thereby greatly reducing ...

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 data security deduplication method based on an auto-encoder, relates to the field of information security and artificial intelligence, solves the problem of low efficiency ofan existing data deduplication method based on random message lock encryption, introduces abstract tags in efficiency, quickly screens out a very small subset from a tag library by means of the similarity of the tags, and executes bilinear mapping calculation on the subset, so that the frequency of bilinear mapping calculation is greatly reduced, and the label comparison efficiency is improved. According to the method, a self-encoding technology commonly used in image processing is introduced, the deduplication efficiency is improved by greatly reducing the number of times of label comparison, and the deduplication efficiency is improved by nearly 10 times compared with a data deduplication method based on random message lock encryption. According to the method, the non-monotonic functionis introduced, so that similar labels can be possibly generated even if data with large difference exists, namely, the similar labels can be generated by the similar data but cannot be established inturn, and the difficulty of deducing the data by an attacker according to the labels is further improved.

Description

Technical field[0001]The present invention relates to the fields of information security and artificial intelligence, in particular to a method for data security deduplication based on a self-encoder,Background technique[0002]Under the trend of data outsourcing, the cloud storage side has two main concerns: storage space and network resources (bandwidth or traffic), because they are all costs that need to be invested, and the user side also has two concerns: privacy protection and transmission effectiveness. In order to protect privacy, data needs to be encrypted. In order to save storage space and network resources and improve transmission efficiency, the best way is to deduplicate data. Therefore, how to achieve deduplication of encrypted data has become a hot topic in academia and industry. problem. In 2013, several milestone papers theoretically clarified the feasibility and security of encrypted data deduplication, and proposed a solution—an encryption method based on message l...

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): G06F21/62G06F16/215G06F16/2457
CPCG06F21/6218G06F16/215G06F16/24573Y02D10/00
Inventor 祁晖底晓强李锦青从立钢任维武
Owner CHANGCHUN UNIV OF SCI & TECH
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