Document Type

Article

Publication Date

Spring 3-22-2023

Abstract

. The recent development of deep learning has made a significant breakthrough in linguistic generative steganography. The text has become one of the most intensely used communication carriers on the Internet, making steganography an efficient carrier for concealing secret messages. Text steganography has long been used to protect the privacy and confidentiality of data via public transmission. Steganography utilizes a carrier to embed the data to generate a secret unnoticed and less attractive message. Different techniques have been used to improve the security of the generated text and quality of the steganographic text, such as the Markov model, Recurrent Neural Network (RNN), Long short-term memory (LSTM), Transformers, Knowledge Graph, and Variational autoencoder (VAE). Those techniques enhance the steganographic text’s language model and conditional probability distribution. This paper provides a comparative analysis to review the key contributions of generative linguistic steganographic deep learning based methods through different perspectives such as text generation, encoding algorithm, and evaluation criteria

Download

Share

COinS