Motivated by concerns for user privacy, we design a steganographic system ("stegosystem") that enables two users to exchange encrypted messages without an adversary detecting that such an exchange is taking place. We propose a new linguistic stegosystem based on a Long Short-Term Memory (LSTM) neural network. We demonstrate our approach on the Twitter and Enron email datasets and show that it yields high-quality steganographic text while significantly improving capacity (encrypted bits per word) relative to the state-of-the-art.
@article{arxiv.1705.10742,
title = {Generating Steganographic Text with LSTMs},
author = {Tina Fang and Martin Jaggi and Katerina Argyraki},
journal= {arXiv preprint arXiv:1705.10742},
year = {2017}
}