{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T03:02:36Z","timestamp":1760151756028,"version":"build-2065373602"},"reference-count":31,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2022,4,22]],"date-time":"2022-04-22T00:00:00Z","timestamp":1650585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61602491"],"award-info":[{"award-number":["61602491"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Generative linguistic steganography encodes candidate words with conditional probability when generating text by language model, and then, it selects the corresponding candidate words to output according to the confidential message to be embedded, thereby generating steganographic text. The encoding techniques currently used in generative text steganography fall into two categories: fixed-length coding and variable-length coding. Because of the simplicity of coding and decoding and the small computational overhead, fixed-length coding is more suitable for resource-constrained environments. However, the conventional text steganography mode selects and outputs a word at one time step, which is highly susceptible to the influence of confidential information and thus may select words that do not match the statistical distribution of the training text, reducing the quality and concealment of the generated text. In this paper, we inherit the decoding advantages of fixed-length coding, focus on solving the problems of existing steganography methods, and propose a multi-time-step-based steganography method, which integrates multiple time steps to select words that can carry secret information and fit the statistical distribution, thus effectively improving the text quality. In the experimental part, we choose the GPT-2 language model to generate the text, and both theoretical analysis and experiments prove the effectiveness of the proposed scheme.<\/jats:p>","DOI":"10.3390\/e24050585","type":"journal-article","created":{"date-parts":[[2022,4,23]],"date-time":"2022-04-23T08:14:06Z","timestamp":1650701646000},"page":"585","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["MTS-Stega: Linguistic Steganography Based on Multi-Time-Step"],"prefix":"10.3390","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7385-7644","authenticated-orcid":false,"given":"Long","family":"Yu","sequence":"first","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"},{"name":"Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation, Hefei 230037, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8502-9907","authenticated-orcid":false,"given":"Yuliang","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"},{"name":"Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation, Hefei 230037, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6388-1720","authenticated-orcid":false,"given":"Xuehu","family":"Yan","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"},{"name":"Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation, Hefei 230037, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Yu","sequence":"additional","affiliation":[{"name":"College of Electronic Engineering, National University of Defense Technology, Hefei 230037, China"},{"name":"Anhui Province Key Laboratory of Cyberspace Security Situation Awareness and Evaluation, Hefei 230037, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,4,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1002\/j.1538-7305.1949.tb00928.x","article-title":"Communication theory of secrecy systems","volume":"28","author":"Shannon","year":"1949","journal-title":"Bell Syst. Tech. J."},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Cox, I.J., and Miller, M.L. (2002). The first 50 years of electronic watermarking. EURASIP J. Adv. Signal Process., 2002.","DOI":"10.1155\/S1110865702000525"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"46","DOI":"10.1016\/j.image.2018.03.012","article-title":"Image steganography in spatial domain: A survey","volume":"65","author":"Hussain","year":"2018","journal-title":"Signal Process. Image Commun."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Krishnan, R.B., Thandra, P.K., and Baba, M.S. (2017, January 16\u201318). An overview of text steganography. Proceedings of the 2017 Fourth International Conference on Signal Processing, Communication and Networking (ICSCN), Chennai, India.","DOI":"10.1109\/ICSCN.2017.8085643"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Mishra, S., Yadav, V.K., Trivedi, M.C., and Shrimali, T. (2018). Audio steganography techniques: A survey. Advances in Computer and Computational Sciences, Springer.","DOI":"10.1007\/978-981-10-3773-3_56"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"238","DOI":"10.1016\/j.neucom.2018.09.091","article-title":"Video steganography: A review","volume":"335","author":"Liu","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_7","unstructured":"Bennett, K. (2004). Linguistic Steganography: Survey, Analysis, and Robustness Concerns for Hiding Information in Text, Purdue University."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"64131","DOI":"10.1109\/ACCESS.2018.2878273","article-title":"A word-embedding-based steganalysis method for linguistic steganography via synonym substitution","volume":"6","author":"Xiang","year":"2018","journal-title":"IEEE Access"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Liu, Y., Sun, X., and Wu, Y. (2005). A natural language watermarking based on Chinese syntax. International Conference on Natural Computation, Springer.","DOI":"10.1007\/11539902_119"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Topkara, U., Topkara, M., and Atallah, M.J. (2006, January 26\u201327). The hiding virtues of ambiguity: Quantifiably resilient watermarking of natural language text through synonym substitutions. Proceedings of the 8th Workshop on Multimedia and Security, Geneva, Switzerland.","DOI":"10.1145\/1161366.1161397"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Shirali-Shahreza, M.H., and Shirali-Shahreza, M. (2008, January 15\u201317). A new synonym text steganography. Proceedings of the 2008 International Conference on Intelligent Information Hiding and Multimedia Signal Processing, Harbin, China.","DOI":"10.1109\/IIH-MSP.2008.6"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Muhammad, H.Z., Rahman, S.M.S.A.A., and Shakil, A. (2009, January 25\u201326). Synonym based malay linguistic text steganography. Proceedings of the 2009 Innovative Technologies in Intelligent Systems and Industrial Applications, Kuala Lumpur, Malaysia.","DOI":"10.1109\/CITISIA.2009.5224169"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"785","DOI":"10.4304\/jsw.5.7.785-792","article-title":"Text Steganography System Using Markov Chain Source Model and DES Algorithm","volume":"5","author":"Dai","year":"2010","journal-title":"J. Softw."},{"key":"ref_14","unstructured":"Tina Fang, T., Jaggi, M., and Argyraki, K. (August, January 30). Generating Steganographic Text with LSTMs. Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics-Student Research Workshop, Vancouver, BC, Canada."},{"key":"ref_15","unstructured":"Moraldo, H.H. (2012, January 27\u201331). An approach for text steganography based on Markov Chains. Proceedings of the IV Workshop de Seguridad Inform\u00e1tica (WSegI 2012) XLI JAIIO, La Plata, Argentina."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1280","DOI":"10.1109\/TIFS.2018.2871746","article-title":"RNN-Stega: Linguistic steganography based on recurrent neural networks","volume":"14","author":"Yang","year":"2018","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Xiang, L., Yang, S., Liu, Y., Li, Q., and Zhu, C. (2020). Novel linguistic steganography based on character-level text generation. Mathematics, 8.","DOI":"10.3390\/math8091558"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ziegler, Z., Deng, Y., and Rush, A.M. (2019, January 3\u20137). Neural Linguistic Steganography. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China.","DOI":"10.18653\/v1\/D19-1115"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.sigpro.2019.06.014","article-title":"Generating steganographic image description by dynamic synonym substitution","volume":"164","author":"Li","year":"2019","journal-title":"Signal Process."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yang, Z., Wei, N., Liu, Q., Huang, Y., and Zhang, Y. (2019). GAN-TStega: Text steganography based on generative adversarial networks. International Workshop on Digital Watermarking, Springer.","DOI":"10.1007\/978-3-030-43575-2_2"},{"key":"ref_21","unstructured":"Dai, F., and Cai, Z. (28\u20132, January 28). Towards Near-imperceptible Steganographic Text. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Nakajima, T.V., and Ker, A.D. (2020, January 6\u201311). The Syndrome-Trellis Sampler for Generative Steganography. Proceedings of the 2020 IEEE International Workshop on Information Forensics and Security (WIFS), New York, NY, USA.","DOI":"10.1109\/WIFS49906.2020.9360885"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Zhou, X., Peng, W., Yang, B., Wen, J., Xue, Y., and Zhong, P. (2021). Linguistic steganography based on adaptive probability distribution. IEEE Trans. Dependable Secur. Comput.","DOI":"10.1109\/TDSC.2021.3079957"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"1045","DOI":"10.21437\/Interspeech.2010-343","article-title":"Recurrent neural network based language model","volume":"2","author":"Mikolov","year":"2010","journal-title":"Interspeech. Makuhari"},{"key":"ref_25","unstructured":"Jurafsky, D. (2000). Speech & Language Processing, Pearson Education."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Song, T., Liu, M., Luo, W., and Zheng, P. (2021, January 6\u201311). Enhancing image steganography via stego generation and selection. Proceedings of the ICASSP 2021\u20142021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Toronto, ON, Canada.","DOI":"10.1109\/ICASSP39728.2021.9414723"},{"key":"ref_27","first-page":"1320","article-title":"Adaptive video data hiding through cost assignment and STCs","volume":"18","author":"Chen","year":"2019","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., and Zitnick, C.L. (2014). Microsoft coco: Common objects in context. European Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref_29","unstructured":"Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., and Potts, C. (2011, January 19\u201324). Learning word vectors for sentiment analysis. Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, OR, USA."},{"key":"ref_30","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"1223","DOI":"10.1109\/TGCN.2021.3081616","article-title":"Secure and Energy Efficient-Based E-Health Care Framework for Green Internet of Things","volume":"5","author":"Kaur","year":"2021","journal-title":"IEEE Trans. Green Commun. Netw."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/5\/585\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T22:59:07Z","timestamp":1760137147000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/24\/5\/585"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,4,22]]},"references-count":31,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2022,5]]}},"alternative-id":["e24050585"],"URL":"https:\/\/doi.org\/10.3390\/e24050585","relation":{},"ISSN":["1099-4300"],"issn-type":[{"type":"electronic","value":"1099-4300"}],"subject":[],"published":{"date-parts":[[2022,4,22]]}}}