Unlock instant, AI-driven research and patent intelligence for your innovation.

A method and system for cracking encrypted images based on deep learning

An encrypted image and deep learning technology, which is applied in the field of encrypted image cracking methods and systems based on deep learning, can solve problems such as the inability to find the correct key, and achieve the effect of solving difficult cracking and cracking takes a long time and a short time

Active Publication Date: 2021-05-11
NORTHWEST UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] As for the encryption algorithm, such as AES encryption, there is no algorithm that can crack it now, only the exhaustive method can be used to search in the key space of the algorithm until the correct key is found, but when the encryption algorithm When the key space is very large, it is impossible to find the correct key within the time range acceptable to humans with the computing speed of existing machines

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
  • A method and system for cracking encrypted images based on deep learning
  • A method and system for cracking encrypted images based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] The encrypted image cracking method based on deep learning provided by the embodiment of the present invention includes the following steps:

[0069] Step 1: Obtain encrypted image samples.

[0070] Among them, the original image can be obtained from various open source datasets, such as Mnist and Celeba datasets. After obtaining the original image, write the code to encrypt the data set according to encryption algorithms such as Arnoldcat and AES, and then the encrypted image sample can be obtained.

[0071] Step 2: Construct a deep learning network model on the basis of the Gan generation confrontation network.

[0072] Specifically, the deep learning network model is constructed according to the Gan generation confrontation network, including the generation network and the confrontation network. The generation network needs to restore the encrypted image with the original image as the target, and the confrontation network is a discriminator to judge the Whether the...

Embodiment 2

[0080] The encrypted image cracking method based on deep learning provided by the embodiment of the present invention specifically includes the following steps:

[0081] Step 1: Obtain encrypted image samples.

[0082] Among them, the original image can be obtained from various open source datasets, such as Mnist and Celeba datasets. After obtaining the original image, write the code to encrypt the data set according to encryption algorithms such as Arnoldcat and AES, and then the encrypted image sample can be obtained.

[0083] Step 2: Construct a deep learning network model based on the Autoencoder autoencoder and the Gan generation confrontation network.

[0084] Specifically, the deep learning network model is constructed based on the Autoencoder self-encoder and the Gan generation confrontation network, including the generation network and the confrontation network. Among them, the generation network needs to restore the encrypted image with the original image as the tar...

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 belongs to the technical fields of image processing, artificial intelligence and information security, and discloses a method and system for cracking encrypted images based on deep learning; obtaining encrypted image samples; constructing a deep learning network model on the basis of an Autoencoder self-encoder; training depth Learn the network; use the trained network model to crack the encrypted image. The system includes: image sample acquisition module, used to obtain encrypted image samples; network model building module, used to realize the construction of deep learning network model on the basis of Autoencoder autoencoder; training module, used to realize training deep learning network; cracking module , which is used to crack the encrypted image using the trained network model. The invention solves the problems that the encryption algorithm is difficult to decipher and takes a long time to decipher. After the network model is trained, the deciphering result can usually be obtained in only a few seconds.

Description

technical field [0001] The invention belongs to the technical fields of image processing, artificial intelligence and information security, and in particular relates to a method and system for decrypting encrypted images based on deep learning. Background technique [0002] At present, the existing technologies commonly used in the industry are as follows: with the development of information technology, information security issues are becoming more and more important, and the safe transmission of important data is particularly important in commercial and military aspects. Here, relevant scholars and researchers have proposed a series of data encryption algorithms. With the introduction of encryption algorithms, corresponding cracking methods also appear. In order to find more secure encryption algorithms, it is necessary to evaluate the security of encryption algorithms and conduct research on cracking methods. [0003] As for the encryption algorithm, such as AES encryptio...

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 Patents(China)
IPC IPC(8): H04N1/44G06N3/04
Inventor 贺晨明刊王永威苏剑颖张汉卿王真
Owner NORTHWEST UNIV