Blind source separation-based encryption of images and speeches

  • Authors:
  • Qiuhua Lin;Fuliang Yin;Hualou Liang

  • Affiliations:
  • School of Electronic and Information Engineering, Dalian University of Technology, Dalian, China;School of Electronic and Information Engineering, Dalian University of Technology, Dalian, China;School of Health Information Sciences, The University of Texas at Houston, Houston, TX

  • Venue:
  • ISNN'05 Proceedings of the Second international conference on Advances in neural networks - Volume Part II
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

Blind source separation (BSS) has been successfully applied in many fields such as communications and biomedical engineering. Its application for image and speech encryption, however, has been scarce. Motivated by the fact that the security of many public-key cryptosystems relies on the apparent intractability of the computational problems such as the integer factorization problem, we present a BSS-based method for encrypting images and speeches by utilizing the BSS underdetermined problem. We discuss how to construct the mixing matrix for encryption and how to generate the key signals. Computer simulation results show that the BSS-based method has high level of security.