Skip to main content
2024 47th International Conference on Telecommunications and Signal Processing (TSP)

Full Program »
Video (.mp4)
View File
mp4
21.9MB

Ownership authentication and integrity verification of digital images using generative models and custom signature

In this paper we present an alternative distortion free algorithm to ownership authentication and integrity verification of digital images that uses Contrastive Language-Image Pre-Training (CLIP), Vector Quantized Generative Adversarial Network (VQGAN) and a custom signature based on cryptographic message digest. The authentication and the integrity of the digital media is proved by a naked eye seen the output of the generative architecture and measured using PSNR and SSIM metrics, respectively.

Jonathan Flores-Monroy
Instituto Politecnico Nacional
Mexico

Manuel Cedillo-Hernandez
Instituto Politecnico Nacional
Mexico

Mariko Nakano-Miyatake
Instituto Politecnico Nacional
Mexico

Hector Perez-Meana
Instituto Politecnico Nacional
Mexico

 

Privacy Policy

Powered by OpenConf®
Copyright ©2002-2024 Zakon Group LLC