DNA Steganalysis Using Deep Recurrent Neural Networks

Recent advances of next generation sequencing technologies have facilitated deoxyribonucleic acid (DNA) to be used as a novel covert channel in steganography. There exist various methods in other domains to detect hidden messages in conventional covert channels, however, they have not been applied to DNA steganography. The current most common detection schemes, frequency analysis-based methods, often miss the important signals when directly applied to DNA steganography since the methods depend on the distribution of the number of sequence characters. To address the existing limitation, we propose a general sequence learning-based DNA steganalysis framework. Our approach learns intrinsic distribution of coding and non-coding sequences and detects hidden messages by exploiting distribution variations after hiding messages. Using deep recurrent neural networks (RNNs), our framework identifies the distribution variations by using the classification score whether a sequence is to be a coding or non-coding sequence. We compared our method to various existing methods and biological sequence analysis methods implemented on top of our framework. According to our experimental results, our approach delivers a robust detection performance regardless of sequence lengths.