With the rapid development of artificial intelligence and the Internet of Things technology, the demand for concealment of data and information is increasingly strong, and information hiding technology plays a key role in information security. At present, there are some problems in the generative steganography mechanism based on deep learning, such as low quality of generative steganography and weak anti-steganographic analysis ability. In view of the above problem, this paper proposes a Realness-DCGAN based information hiding mechanism, this mechanism will secret information mapping division and the noise vector generator, according to the noise generated vector containing the secret image by using fidelity distribution as a standard of judging output, constraint generator to generate a higher quality of the secret image, finally using an extractor to extract the secret information. Experiments show that compared with the traditional steganography mechanism based on deep learning, the information hiding mechanism proposed in this paper by embedding RealnessGAN into the traditional DCGAN can significantly improve the quality of generated images containing secrets, and improve the accuracy and security of information extraction.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Information Hiding Mechanism Based on Generative Adversarial Networks


    Beteiligte:
    Cheng, Xiaohui (Autor:in) / Zhao, Jun (Autor:in) / Kang, Yanping (Autor:in)


    Erscheinungsdatum :

    2020-10-14


    Format / Umfang :

    230949 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    EvolGAN: Evolutionary Generative Adversarial Networks

    Roziere, Baptiste / Teytaud, Fabien / Hosu, Vlad et al. | British Library Conference Proceedings | 2021


    Ensemble-Based Distributed Learning for Generative Adversarial Networks

    Liu, Chonghe / Ren, Jinke / Yu, Guanding | IEEE | 2022


    Imitating driver behavior with generative adversarial networks

    Kuefler, Alex / Morton, Jeremy / Wheeler, Tim et al. | IEEE | 2017


    Circuit Synthesis Using Generative Adversarial Networks (GANs)

    Guo, Tinghao / Herber, Daniel / Allison, James T. | AIAA | 2019


    Circuit Synthesis Using Generative Adversarial Networks (GANSs)

    Guo, Tinghao / Herber, Daniel / Allison, James T. | TIBKAT | 2019