Visualiation of Steganalysis
AbstractSteganography means hiding a hidden payload within an apparently-innocent cover, usually an item of digital media (in this project: images). Steganalysis is the art of detecting that hiding took place. The most effective ways to detect steganography are machine learning algorithms applied to "features" extracted from the images, trained on massive sets of known cover and stego objects. The images are thus turned into points in high-dimensional space. We have little intuition as to the geometrical structure of the features (do images form a homogeneous cluster? do they scale naturally with image size? how much and in what ways do images from different cameras differ?), or how they are altered under embedding (do they move in broadly the same direction? is there is linear separator of cover from stego?). This is a programming project that creates a visualization tool for features, extracting them from images and then projecting them onto 2-dimensional space in interesting ways, while illustrating the effects of embedding.
Prerequisites: Linear Algebra, Computer Graphics. Machine Learning an advantage.