Steganography is the science of hiding a secret message within an ordinary public message. Over the years, steganography has been used to encode a lower resolution image into a higher resolution image by simple methods like LSB manipulation. We aim to utilize deep neural networks for the encoding and decoding of multiple secret images inside a single cover image of the same resolution.
Paper
References (18)
07successfully in both cases. The losses received for the below results
08we are taking both the λ s and λ c as 1.0
09Model has been trained for 800 epochs with a batch size of 256 and an additional 100 epochs with batch size of 32
10While training the reveal network we only consider the secret image component of the loss
11Mean sum of squared error has been used for calculating decoder’s loss
12To make sure weights are updated only once, reveal network weights are frozen before adding it to the full model
Scroll for more · 6 remaining