Generating Steganographic Text with LSTMs
This work addresses privacy concerns for users needing covert communication, representing a novel method for a known bottleneck in steganography.
The authors tackled the problem of enabling private communication by developing a steganographic system using LSTM neural networks to hide encrypted messages in text, achieving high-quality steganographic text and significantly improving capacity (encrypted bits per word) compared to state-of-the-art methods on Twitter and Enron email datasets.
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.