Paper 2007/339

On the security of a class of image encryption schemes

Chengqing Li and Guanrong Chen

Abstract

Recently four chaos-based image encryption schemes were proposed. Essentially, the four schemes can be classified into one class, which is composed of two basic parts: permutation of position and diffusion of pixel value with the same cipher-text feedback function. The operations involved in the two basic parts are determined by a pseudo random number sequence (PRNS) generated from iterating a chaotic dynamic system. According to the security requirement, the two basic parts are performed alternatively for some rounds. Although the designers claimed that the schemes are of high quality, we found the following security problems: 1) the schemes are not sensitive to the changes of plain-images; 2) the schemes are not sensitive to the changes of the key streams generated by any secret key; 3) there exists a serious flaw of the diffusion function; 4) the schemes can be broken with no more than $\lceil\log_L(MN)\rceil+3$ chosen-images when the iteration number is equal to one, where $MN$ is the size of the plain-image and $L$ is the number of different pixel values; 5) the cryptanalysis on one scheme proposed by another research group is questionable.

Metadata
Available format(s)
PDF
Publication info
Published elsewhere. Unknown where it was published
Keywords
cryptanalysis
Contact author(s)
swiftsheep @ hotmail com
History
2008-01-04: last of 2 revisions
2007-08-29: received
See all versions
Short URL
https://ia.cr/2007/339
License
Creative Commons Attribution
CC BY

BibTeX

@misc{cryptoeprint:2007/339,
      author = {Chengqing Li and Guanrong Chen},
      title = {On the security of a class of image encryption schemes},
      howpublished = {Cryptology ePrint Archive, Paper 2007/339},
      year = {2007},
      note = {\url{https://eprint.iacr.org/2007/339}},
      url = {https://eprint.iacr.org/2007/339}
}
Note: In order to protect the privacy of readers, eprint.iacr.org does not use cookies or embedded third party content.