Linguistic Generative Steganography With Enhanced Cognitive-Imperceptibility

In recent years, linguistic generative steganography has been greatly developed. The previous works are mainly to optimize the perceptual-imperceptibility and statistical-imperceptibility of the generated steganographic text, and the latest developments show that they have been able to generate steganographic texts that look authentic enough. However, we noticed that these works generally cannot control the semantic expression of the generated steganographic text, and we believe this will bring potential security risks. We named this kind of security challenges as cognitive-imperceptibility. We think this is a new challenge that the generative steganography models must strive to overcome in the future. In this letter, we conduct some preliminary attempts to solve this challenge. Experimental results show that the proposed methods can further constrain the semantic expression of the generated steganographic text on the basis of ensuring certain perceptual-imperceptibility and statistical-imperceptibility, so as to enhance its cognitive-imperceptibility.

[1]  Yongfeng Huang,et al.  AAG-Stega: Automatic Audio Generation-based Steganography , 2018, ArXiv.

[2]  Yongfeng Huang,et al.  IStego100K: Large-scale Image Steganalysis Dataset , 2019, IWDW.

[3]  Alex Wilson,et al.  Linguistic steganography on Twitter: hierarchical language modeling with manual interaction , 2014, Electronic Imaging.

[4]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[5]  Lingyun Xiang,et al.  Novel Linguistic Steganography Based on Character-Level Text Generation , 2020, Mathematics.

[6]  Stephen Clark,et al.  Practical Linguistic Steganography using Contextual Synonym Substitution and a Novel Vertex Coding Method , 2014, CL.

[7]  Erez Lieberman Aiden,et al.  Quantitative Analysis of Culture Using Millions of Digitized Books , 2010, Science.

[8]  Yongfeng Huang,et al.  TS-RNN: Text Steganalysis Based on Recurrent Neural Networks , 2019, IEEE Signal Processing Letters.

[9]  Yongfeng Huang,et al.  Graph-Stega: Semantic Controllable Steganographic Text Generation Guided by Knowledge Graph , 2020, ArXiv.

[10]  Yongfeng Huang,et al.  Text Steganography Based on Ci-poetry Generation Using Markov Chain Model , 2016, KSII Trans. Internet Inf. Syst..

[11]  Yongfeng Huang,et al.  Behavioral Security in Covert Communication Systems , 2019, IWDW.

[12]  Si Liu,et al.  Video steganography: A review , 2019, Neurocomputing.

[13]  A. N. Shniperov,et al.  A text steganography method based on Markov chains , 2016, Automatic Control and Computer Sciences.

[14]  Jianfeng Gao,et al.  Deep Reinforcement Learning for Dialogue Generation , 2016, EMNLP.

[15]  Falcon Z. Dai,et al.  Towards Near-imperceptible Steganographic Text , 2019, ACL.

[16]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[17]  Pushmeet Kohli,et al.  Story Cloze Evaluator: Vector Space Representation Evaluation by Predicting What Happens Next , 2016, RepEval@ACL.

[18]  Yongfeng Huang,et al.  Image Captioning with Object Detection and Localization , 2017, ICIG.

[19]  Katerina J. Argyraki,et al.  Generating Steganographic Text with LSTMs , 2017, ACL.

[20]  Yongfeng Huang,et al.  Automatically Generate Steganographic Text Based on Markov Model and Huffman Coding , 2018, ArXiv.

[21]  Anita K. Jones,et al.  Reflections on Cybersecurity , 2009, Science.

[22]  Alon Lavie,et al.  Meteor Universal: Language Specific Translation Evaluation for Any Target Language , 2014, WMT@ACL.

[23]  Yongfeng Huang,et al.  GAN-TStega: Text Steganography Based on Generative Adversarial Networks , 2019, IWDW.

[24]  Xuyu Xiang,et al.  Coverless Image Steganography Based on Multi-Object Recognition , 2021, IEEE Transactions on Circuits and Systems for Video Technology.

[25]  Jianfeng Gao,et al.  An Information-Theoretic Approach to Automatic Evaluation of Summaries , 2006, NAACL.

[26]  Yongfeng Huang,et al.  Text Steganography with High Embedding Rate: Using Recurrent Neural Networks to Generate Chinese Classic Poetry , 2017, IH&MMSec.

[27]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[28]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[29]  Yongfeng Huang,et al.  A novel method of speech information hiding based on 3D-Magic Matrix , 2018, ArXiv.

[30]  Yongfeng Huang,et al.  TS-CSW: text steganalysis and hidden capacity estimation based on convolutional sliding windows , 2020, Multimedia Tools and Applications.

[31]  Arun Kumar Sangaiah,et al.  Aspect based sentiment analysis by a linguistically regularized CNN with gated mechanism , 2019, J. Intell. Fuzzy Syst..

[32]  Yongfeng Huang,et al.  RITS: Real-Time Interactive Text Steganography Based on Automatic Dialogue Model , 2018, ICCCS.

[33]  H. Hernan Moraldo,et al.  An Approach for Text Steganography Based on Markov Chains , 2014, ArXiv.

[34]  Danilo Montesi,et al.  Content-preserving Text Watermarking through Unicode Homoglyph Substitution , 2016, IDEAS.

[35]  Yong-Feng Huang,et al.  RNN-Stega: Linguistic Steganography Based on Recurrent Neural Networks , 2019, IEEE Transactions on Information Forensics and Security.

[36]  Yongfeng Huang,et al.  A Sudoku Matrix-Based Method of Pitch Period Steganography in Low-Rate Speech Coding , 2017, SecureComm.

[37]  Zhong-Liang Yang,et al.  VAE-Stega: Linguistic Steganography Based on Variational Auto-Encoder , 2021, IEEE Transactions on Information Forensics and Security.

[38]  Seam-Carved Image Tampering Detection Based on the Cooccurrence of Adjacent LBPs , 2020, Secur. Commun. Networks.

[39]  Yongfeng Huang,et al.  A Fast and Efficient Text Steganalysis Method , 2019, IEEE Signal Processing Letters.

[40]  Alex Wilson,et al.  Avoiding detection on twitter: embedding strategies for linguistic steganography , 2016, Media Watermarking, Security, and Forensics.

[41]  Wei-Ying Ma,et al.  Topic Aware Neural Response Generation , 2016, AAAI.

[42]  Katia Kermanidis.  Hiding Secret Information by Automatically Paraphrasing Modern Greek Text with Minimal Resources , 2010, 2010 22nd IEEE International Conference on Tools with Artificial Intelligence.

[43]  Alexander M. Rush,et al.  Neural Linguistic Steganography , 2019, EMNLP.

[44]  Mark Chapman,et al.  Hiding the Hidden: A software system for concealing ciphertext as innocuous text , 1997, ICICS.

[45]  Yongfeng Huang,et al.  Linguistic Steganography: From Symbolic Space to Semantic Space , 2021, IEEE Signal Processing Letters.