Text steganography on RNN-Generated lyrics

Abstract

We present a Recurrent Neural Network (RNN) Encoder-Decoder model to generate Chinese pop music lyrics to hide secret information. In particular, on a given initial line of a lyric, we use the LSTM model to generate the next Chinese character or word to form a new line. In so doing, we generate the entire lyric from what has been generated so far. Using common lyric formats and rhymes we extracted, we generate lyrics embedded with secret information to meet the visual and pronunciation requirements. We carry out experiments and theoretical analysis, and show that lyrics generated by our method offer higher embedding capacities for steganography, which also look more natural than the existing steganography methods based on text generations.