Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ UPCommons. Portal de...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
versions View all 3 versions
addClaim

Hiding images in their spoken narratives

Hiding pixels in their spoken narratives
Authors: Domènech Abelló, Teresa;

Hiding images in their spoken narratives

Abstract

La esteganografía es la técnica de ocultar datos secretos dentro de un archivo ordinario, no secreto o mensaje para evitar ser detectado. En este caso el dato secreto oculto es una imagen y los datos no secretos o señal de cobertura es un audio. Para ello, utilizamos una propuesta anterior que usa una arquitectura residual que opera sobre la transformada de coseno discreta de tiempo corto (STDCT) espectrogramas de audio. La configuración de esteganografía de audio residual propuesta permite la codificación de la imagen oculta del audio host sin comprometer la calidad. En esta tesis presentamos esta tarea sobre un nuevo conjunto de datos donde la visión y el lenguaje son conectado y otras modificaciones como el uso de la transformada de Fourier de tiempo corto (STFT) espectrogramas de audio, señales ocultas permutadas, experimentos simulando un escenario real, así como obtener un sistema más eficiente.

L'esteganografia és la tècnica d'ocultar dades secretes dins d'un fitxer ordinari, no secret o missatge per evitar ser detectat. En aquest cas la dada secreta oculta és una imatge i les dades no secretes o senyal de cobertura és un àudio. Per això, utilitzem una proposta prometedora anterior una arquitectura residual que opera sobre la transformada de cosinus discreta de temps curt (STDCT) espectrogrames d'àudio. La configuració d'esteganografia d'àudio residual proposada codifica la imatge oculta de làudio host sense comprometre la qualitat. En aquesta tesis presentem aquesta tasca sobre un nou conjunt de dades on la visió i el llenguatge estan connectat i altres modificacions com l'ús de la transformada de Fourier de temps curt (STFT) espectrogrames dàudio, senyals ocults permutats, experiments simulant escenaris reals, així com obtenir un sistema més eficient.

Steganography is the technique of hiding secret data within an ordinary, non-secret, file or message in order to avoid detection. In this case the hidden secret data is an image and the non-secret data or cover signal is an audio. To this end, we use a previous proposed novel residual architecture operating on top of short-time discrete cosine transform (STDCT) audio spectrograms. The residual audio steganography setup proposed allows independent encoding of the hidden image from the host audio without compromising quality. In this thesis we present this task above a new dataset where the vision and language are connected and other modifications such as the use of short-time fourier transform (STFT) audio spectograms, permuted hidden signals, real-world scenario experiments as well as obtaining a more efficient system.

Country
Spain
Keywords

deep neural networks, STFT espectograms, redes neuronales profundas, Àrees temàtiques de la UPC::Informàtica::Seguretat informàtica::Criptografia, Cryptography, STFT spectograms, Criptografia, Estegonografia, Steganography, esconder imagenes, hiding images, :Informàtica::Seguretat informàtica::Criptografia [Àrees temàtiques de la UPC]

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    OpenAIRE UsageCounts
    Usage byUsageCounts
    visibility views 42
    download downloads 40
  • 42
    views
    40
    downloads
    Powered byOpenAIRE UsageCounts
Powered by OpenAIRE graph
Found an issue? Give us feedback
visibility
download
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
views
OpenAIRE UsageCountsViews provided by UsageCounts
downloads
OpenAIRE UsageCountsDownloads provided by UsageCounts
0
Average
Average
Average
42
40
Green