Novel Text Steganography Using Natural Language Processing and Part-of-Speech Tagging

摘要

The practice of transmitting secret data by using cover data is called steganography. At present, several versatile steganographic methods are available using different digital objects (e.g.image, audio, video, text,etc.) as cover to hide data. Accordingly, many methods of steganalysis have been explored to reveal statistical anomalies in stego object, through which presence of secret data can be detected. However, applications of steganography and steganalysis techniques are challenging when cover object is text, as text does not have any redundant bits. In this paper, an innovative text steganography approach is proposed which uses natural language text as cover as well as secret message. The concept of shared key is also used here, that holds the count of each parts-of-speech of secret message. This key is RSA encrypted and shared with communicative parties. Stego created by this method also is in natural language text. This method is successful as the stego keeps the original meaning of the text in gross which makes it robust and undetectable. It shows good result in capacity ratio; also, the similarity index has been assessed by Jaro-Winkler distance and Generalized Levenshtein distance.