Scribd
Upload
33 views8 pages

Image Steganography With CNNs

This document presents an exploration of image steganography using Convolutional Neural Networks (CNNs), detailing traditional techniques and the encoder-decoder framework. It highlights the architecture of CNNs, the use of the ImageNet dataset, and experimental results that demonstrate the effectiveness of this approach. Future work includes advancements in video steganography and addressing limitations in current methods.

Uploaded by

ashupandul754
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
33 views8 pages

Image Steganography With CNNs

This document presents an exploration of image steganography using Convolutional Neural Networks (CNNs), detailing traditional techniques and the encoder-decoder framework. It highlights the architecture of CNNs, the use of the ImageNet dataset, and experimental results that demonstrate the effectiveness of this approach. Future work includes advancements in video steganography and addressing limitations in current methods.

Uploaded by

ashupandul754
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 8

Image Steganography

with CNNs
This presentation explores image steganography using
Convolutional Neural Networks (CNNs). We will examine how
CNNs enhance the process of hiding information within
images.

We'll cover traditional methods, the encoder-decoder


framework, and the use of the ImageNet dataset. The goal is
to understand the capabilities and limitations of this cutting-
edge approach.

by EDU with THANU


Background: Steganography and CNNs
Steganography History Traditional Techniques CNN Introduction

Steganography has ancient Common techniques include CNNs excel at image


roots. Early methods involved LSB and DCT. These have processing. They extract
hiding messages physically. limitations in security. features effectively.
CNN Architecture for
Steganography
Convolutional Layers
Extract image features.

Pooling Layers
Reduce dimensionality.

Activation Functions
Introduce non-linearity.

Loss Functions
Optimize the network.
Encoder Network
1 Embedding Role
Embeds secret image.

2 Encoder Input
Cover and secret images.

3 Convolution
Extract features for merging.

4 Stego Output
Creates the stego image.
Decoder Network
Extraction Role
Extracts the secret image.

Decoder Input
Receives the stego image.

Deconvolution
Reconstructs the secret image.

Secret Output
Recovers the original image.
ImageNet Dataset

Size 1 Diversity
2

Preprocessing
4 Suitability
3

ImageNet contains 1.2 million images. It has 1000 classes of objects. This diversity improves model
generalization.
Experimental Results
and Analysis

Metrics like PSNR Embedding Visual examples


and SSIM. capacity of images.
achieved.
Conclusion and Future Work
Summary
1 CNN based approach.

Advantages
2 Encoder-decoder benefits.

Improvements
3 Address limitations.

Future directions include video steganography. Also, explore adversarial attacks. Real-time applications
hold promise.

You might also like