Linguistic Steganography Using Automatically Generated Paraphrases

This paper describes a method for checking the acceptability of paraphrases in context. We use the Google n-gram data and a CCG parser to certify the paraphrasing grammaticality and fluency. We collect a corpus of human judgements to evaluate our system. The ultimate goal of our work is to integrate text paraphrasing into a Linguistic Steganography system, by using paraphrases to hide information in a cover text. We propose automatically generated paraphrases as a new and useful source of transformations for Linguistic Steganography, and show that our method for checking paraphrases is effective at maintaining a high level of imperceptibility, which is crucial for effective steganography.