Exploiting Adversarial Embeddings for Better Steganography

This work proposes a protocol to iteratively build a distortion function for adaptive steganography while increasing its practical security after each iteration. It relies on prior art on targeted attacks and iterative design of steganalysis schemes. It combines targeted attacks on a given detector with a min max strategy, which dynamically selects the most difficult stego content associated with the best classifier at each iteration. We theoretically prove the convergence, which is confirmed by the practical results. Applied on J-Uniward this new protocol increases P-err from 7% to 20% estimated by Xu-Net, and from 10% to 23% for a non-targeted steganalysis by a linear classifier with GFR features.