Image steganography based on generative implicit neural representation

被引：0
|
作者：
Zhong, Yangjie [1 ,2 ]
Ke, Yan [1 ,2 ]
Liu, Meiqi [1 ,2 ]
Liu, Jia [1 ,2 ]
机构：
[1] Engn Univ PAP, Xian, Peoples R China
[2] Key Lab Network & Informat Secur PAP, Xian, Peoples R China
来源：
JOURNAL OF ELECTRONIC IMAGING | 2024年 / 33卷 / 06期
基金：
中国国家自然科学基金;
关键词：
information hiding; generative steganography; implicit neural representation; continuous function;
D O I：
10.1117/1.JEI.33.6.063043
中图分类号：
TM [电工技术]; TN [电子技术、通信技术];
学科分类号：
0808 ; 0809 ;
摘要：
In deep steganography, the model size is usually related to the grid resolution of the underlying layer, and a separate neural network needs to be trained as a message extractor. We propose image steganography based on generative implicit neural representation, which breaks through the limitation of image resolution using a continuous function to represent image data and allows various kinds of multimedia data to be used as the cover image for steganography, which theoretically extends the class of carriers. Fixing a neural network as a message extractor, and transferring the training of the network to the training of the image itself, reduces the training cost and avoids the problem of exposing the steganographic behavior caused by the transmission of the message extractor. The experiment proves that the scheme is efficient, and it only takes 3 s to complete the optimization for an image with a resolution of 64 x 64 and a hiding capacity of 1 bpp, and the accuracy of message extraction reaches 100%. (c) 2024 SPIE and IS&T
引用
收藏
页数：18
相关论文
共 50 条
  • [21] Optimization Analysis for Image based Steganography using Generative Adversarial Networks
    Arokiasamy, Aldrin Wilfred
    Skarbek, Wladyslaw
    PHOTONICS APPLICATIONS IN ASTRONOMY, COMMUNICATIONS, INDUSTRY, AND HIGH-ENERGY PHYSICS EXPERIMENTS 2019, 2019, 11176
  • [22] High-accuracy image steganography with invertible neural network and generative adversarial network
    Wang, Ke
    Zhu, Yani
    Chang, Qi
    Wang, Junyu
    Yao, Ye
    SIGNAL PROCESSING, 2025, 234
  • [23] Generative Steganography Based on GANs
    Liu, Mingming
    Zhang, Minqing
    Liu, Jia
    Yang, Xiaoyuan
    CLOUD COMPUTING AND SECURITY, PT VI, 2018, 11068 : 537 - 549
  • [24] Lossless Image Steganography Based on Invertible Neural Networks
    Liu, Lianshan
    Tang, Li
    Zheng, Weimin
    ENTROPY, 2022, 24 (12)
  • [25] A New Generative Mathematical Model for Coverless Steganography System Based on Image Generation
    Seddik, Al-Hussien
    Salah, Mohammed
    Behery, Gamal
    El-harby, Ahmed
    Ebada, Ahmed Ismail
    Teng, Sokea
    Nam, Yunyoung
    Abouhawwash, Mohamed
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 74 (03): : 5087 - 5103
  • [26] A novel approach based on modified cycle generative adversarial networks for image steganography
    Kuppusamy, P.G.
    Ramya, K.C.
    Sheeba Rani, S.
    Sivaram, M.
    Dhasarathan, Vigneswaran
    Scalable Computing, 2020, 21 (01): : 63 - 72
  • [27] Disguise of Steganography Behaviour: Steganography Using Image Processing with Generative Adversarial Network
    Li, Mingjie
    Wang, Zichi
    Song, Haoxian
    Liu, Yong
    SECURITY AND COMMUNICATION NETWORKS, 2021, 2021
  • [28] Generative adversarial networks-based image steganography with multiscale features integration
    Song, Yalin
    Zhong, Yuhao
    Gan, Zhihua
    Yang, Yang
    Yu, Junyang
    He, Xin
    JOURNAL OF ELECTRONIC IMAGING, 2022, 31 (05)
  • [29] A NOVEL APPROACH BASED ON MODIFIED CYCLE GENERATIVE ADVERSARIAL NETWORKS FOR IMAGE STEGANOGRAPHY
    Kuppusamy, P. G.
    Ramya, K. C.
    Rani, S. Sheeba
    Sivaram, M.
    Dhasarathan, Vigneswaran
    SCALABLE COMPUTING-PRACTICE AND EXPERIENCE, 2020, 21 (01): : 63 - 72
  • [30] Implicit Neural Representation for Cooperative Low-light Image Enhancement
    Yang, Shuzhou
    Ding, Moxuan
    Wu, Yanmin
    Li, Zihan
    Zhang, Jian
    2023 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2023), 2023, : 12872 - 12881
12345