PRIS: Practical robust invertible network for image steganography
- URL: http://arxiv.org/abs/2309.13620v2
- Date: Tue, 28 Nov 2023 09:28:53 GMT
- Title: PRIS: Practical robust invertible network for image steganography
- Authors: Hang Yang, Yitian Xu, Xuhua Liu, Xiaodong Ma
- Abstract summary: Image steganography is a technique of hiding secret information inside another image, so that the secret is not visible to human eyes.
Most of the existing image steganography methods have low hiding robustness when the container images affected by distortion.
This paper proposed PRIS to improve the robustness of image steganography, it based on invertible neural networks.
- Score: 10.153270845070676
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Image steganography is a technique of hiding secret information inside
another image, so that the secret is not visible to human eyes and can be
recovered when needed. Most of the existing image steganography methods have
low hiding robustness when the container images affected by distortion. Such as
Gaussian noise and lossy compression. This paper proposed PRIS to improve the
robustness of image steganography, it based on invertible neural networks, and
put two enhance modules before and after the extraction process with a 3-step
training strategy. Moreover, rounding error is considered which is always
ignored by existing methods, but actually it is unavoidable in practical. A
gradient approximation function (GAF) is also proposed to overcome the
undifferentiable issue of rounding distortion. Experimental results show that
our PRIS outperforms the state-of-the-art robust image steganography method in
both robustness and practicability. Codes are available at
https://github.com/yanghangAI/PRIS, demonstration of our model in practical at
http://yanghang.site/hide/.
Related papers
- Deep Learning Based Speckle Filtering for Polarimetric SAR Images. Application to Sentinel-1 [51.404644401997736]
We propose a complete framework to remove speckle in polarimetric SAR images using a convolutional neural network.
Experiments show that the proposed approach offers exceptional results in both speckle reduction and resolution preservation.
arXiv Detail & Related papers (2024-08-28T10:07:17Z) - Robust Message Embedding via Attention Flow-Based Steganography [34.35209322360329]
Image steganography can hide information in a host image and obtain a stego image that is perceptually indistinguishable from the original one.
We propose a novel message embedding framework, called Robust Message Steganography (RMSteg), which is competent to hide message via QR Code in a host image.
arXiv Detail & Related papers (2024-05-26T03:16:40Z) - Coarse-to-Fine Latent Diffusion for Pose-Guided Person Image Synthesis [65.7968515029306]
We propose a novel Coarse-to-Fine Latent Diffusion (CFLD) method for Pose-Guided Person Image Synthesis (PGPIS)
A perception-refined decoder is designed to progressively refine a set of learnable queries and extract semantic understanding of person images as a coarse-grained prompt.
arXiv Detail & Related papers (2024-02-28T06:07:07Z) - DKiS: Decay weight invertible image steganography with private key [11.41125892113752]
A novel private key-based image steganography technique has been introduced.
Access requires a corresponding private key, regardless of the public knowledge of the steganography method.
A critical challenge in the invertible image steganography process has been identified.
arXiv Detail & Related papers (2023-11-30T04:21:10Z) - Double-Flow-based Steganography without Embedding for Image-to-Image
Hiding [14.024920153517174]
steganography without embedding (SWE) hides a secret message without directly embedding it into a cover.
SWE has the unique advantage of being immune to typical steganalysis methods and can better protect the secret message from being exposed.
Existing SWE methods are generally criticized for their poor payload capacity and low fidelity of recovered secret messages.
arXiv Detail & Related papers (2023-11-25T13:44:37Z) - Detecting Generated Images by Real Images Only [64.12501227493765]
Existing generated image detection methods detect visual artifacts in generated images or learn discriminative features from both real and generated images by massive training.
This paper approaches the generated image detection problem from a new perspective: Start from real images.
By finding the commonality of real images and mapping them to a dense subspace in feature space, the goal is that generated images, regardless of their generative model, are then projected outside the subspace.
arXiv Detail & Related papers (2023-11-02T03:09:37Z) - Hiding Data in Colors: Secure and Lossless Deep Image Steganography via
Conditional Invertible Neural Networks [20.81947232336795]
Existing deep image steganography methods only consider the visual similarity of container images to host images, and neglect the statistical security (stealthiness) of container images.
We propose deep image steganography that can embed data with arbitrary types into images for secure data hiding and lossless data revealing.
arXiv Detail & Related papers (2022-01-19T07:09:36Z) - Image Restoration by Deep Projected GSURE [115.57142046076164]
Ill-posed inverse problems appear in many image processing applications, such as deblurring and super-resolution.
We propose a new image restoration framework that is based on minimizing a loss function that includes a "projected-version" of the Generalized SteinUnbiased Risk Estimator (GSURE) and parameterization of the latent image by a CNN.
arXiv Detail & Related papers (2021-02-04T08:52:46Z) - A Novel Local Binary Pattern Based Blind Feature Image Steganography [12.970738540611855]
A novel feature based blind image steganography technique is proposed, which preserves the LBP (Local binary pattern) feature of the cover with comparable embedding rates.
The proposed scheme computes the local binary pattern to hide the bits of the secret image in such a way that the local relationship that exists in the cover are preserved in the resulting stego image.
arXiv Detail & Related papers (2021-01-16T06:37:00Z) - Exploiting Deep Generative Prior for Versatile Image Restoration and
Manipulation [181.08127307338654]
This work presents an effective way to exploit the image prior captured by a generative adversarial network (GAN) trained on large-scale natural images.
The deep generative prior (DGP) provides compelling results to restore missing semantics, e.g., color, patch, resolution, of various degraded images.
arXiv Detail & Related papers (2020-03-30T17:45:07Z) - Self-Supervised Linear Motion Deblurring [112.75317069916579]
Deep convolutional neural networks are state-of-the-art for image deblurring.
We present a differentiable reblur model for self-supervised motion deblurring.
Our experiments demonstrate that self-supervised single image deblurring is really feasible.
arXiv Detail & Related papers (2020-02-10T20:15:21Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.