Abstract: Identification and machine-readable travel documents, or IDs and MRTDs, are used to identify and authenticate identities in a variety of contexts, including the crossing of borders, civil applications, sales and purchase portals, and access to transaction processing systems. Criminal attacks on ID verification systems now concentrate on falsified copies of real papers and the alteration of facial images because these security mechanisms are tough to go around. Governments and producers of IDs and MRTDs must constantly develop and enhance security measures if they want to lessen hazards associated with this fraud problem. In light of this, we provide the first effective steganography technique, StegoFace, which is tailored for the printing of facial photos in standard IDs and MRTDs. A Deep Convolutional Auto encoder can hide a secret message in a face portrait, creating the stego facial image. A Deep Convolutional Auto encoder can also read a message from the stego facial image, even if it has been printed and then taken with a digital camera. Together, these two components make up the end-to-end facial image steganography model known as StegoFace. In terms of perceptual quality, facial images encoded using our StegoFace method perform better than images created using the stega stamp. Results from the test set's peak signal-to-noise ratio, concealing capacity, and imperceptibility are used to gauge performance.
Keywords: StegoFace, Fake user, Deep convolutional Auto encoder, StegaStamp
|
DOI:
10.17148/IJARCCE.2022.11659
