Encrypting video and image streams using OpenCL code on-demand
Universidad Nacional del Centro de la Provincia de Buenos Aires (UNCPBA), Consejo Nacional de Investigaciones Cientificas y Tecnicas (CONICET), Facultad de Ciencias Exactas, Tandil, Argentina, 7000
CLEI Electronic Journal, Volume 17, Number 1, Paper 5, 2014
@article{albert2014exploiting,
title={Exploiting Parallel Processing Power of GPU for High Speed Frequent Pattern Mining},
author={Albert, D William and Fayaz, K and Babu, D Veerabhadra},
year={2014}
}
The amount of multimedia information transmitted through the web is very high and increasing. Generally, this kind of data is not correctly protected, since users do not appreciate the amount of information that images and videos may contain. In this work, we present architecture for managing safely multimedia transmission channels. The idea is to encrypt or encode images and videos in an efficient and dynamic way. At the same time, these media could be enhanced applying a real-time image process. The main novelty of the proposal is the application of on-demand parallel code written in OpenCL. The algorithms and data structure are known by the parties only at communication time, what we suppose increases the robustness against possible attacks. We conducted a complete description of the proposal and several performance tests with different known algorithms.
August 23, 2014 by hgpu
