DHU-Net: High-capacity binary data hiding network based on improved U-Net

  • Duan, Xintao; 
  • Li, Chun; 
  • Wei, Bingxin; 
  • Wu, Guoming; 
  • Qin, Chuan; 
  • ... Nam, Haewoon
Citations

WEB OF SCIENCE

7
Citations

SCOPUS

7

초록

Due to limited data-hiding capacity and low extraction accuracy, most existing data hiding schemes have difficulty in high capacity hiding and lossless extraction of binary data. This paper proposes a novel binary data hiding network (DHU-Net) based on improved U-Net and flow encoding, which deepens the network structure and facilitates lossless extraction of high-capacity binary data. The BN layer is added to address overfitting and prevent vanishing gradient or exploding gradient. Furthermore, a novel binary-to-spatial domain mapping method is proposed to map the binary data to the spatial domain. Experimental results show that our scheme can achieve lossless extraction of binary data while maintaining low distortion and sufficient security. DHU-Net provides a promising solution for secure and efficient transmission of binary data through data hiding. © 2024 Elsevier B.V.

키워드

Binary data hiding; DHU-Net; Flow encoding; Losslessly
제목
DHU-Net: High-capacity binary data hiding network based on improved U-Net
저자
Duan, Xintao; Li, Chun; Wei, Bingxin; Wu, Guoming; Qin, Chuan; Nam, Haewoon
DOI
10.1016/j.neucom.2024.127314
발행일
2024-04
유형
Article
저널명
Neurocomputing
권
576
페이지
1 ~ 16