Abstract

Linguistic Steganography is concerned with hiding information in a natural language text, for the purposes of sending secret messages. A related area is natural language watermarking, in which information is added to a text in order to identify it, for example for the purposes of copyright. Linguistic Steganography algorithms hide information by manipulating properties of the text, for example by replacing some words with their synonyms. Unlike image-based steganography, linguistic steganography is in its infancy with little existing work. In this talk we will motivate the problem, in particular as an interesting application for Natural Language Processing (NLP) and especially natural language generation. Linguistic steganography is a difficult NLP problem because any change to the cover text must retain the meaning and style of the original, in order to prevent detection by an adversary.

Our method embeds information in the cover text by replacing words in the text with appropriate substitutes. We use a large database of word sequences collected from the Web (the Google n-gram data) to determine if a substitution is acceptable, obtaining promising results from an evaluation in which human judges are asked to rate the acceptability of modified sentences.