{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T20:39:17Z","timestamp":1781383157102,"version":"3.54.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T00:00:00Z","timestamp":1741910400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T00:00:00Z","timestamp":1741910400000},"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":["62302117"],"award-info":[{"award-number":["62302117"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372128"],"award-info":[{"award-number":["62372128"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2023A1515011428"],"award-info":[{"award-number":["2023A1515011428"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2024A1515010666"],"award-info":[{"award-number":["2024A1515010666"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100021171","name":"Guangdong Basic and Applied Basic Research Foundation","doi-asserted-by":"crossref","award":["2023A1515011575"],"award-info":[{"award-number":["2023A1515011575"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Science and Technology Foundation of Guangzhou","award":["2024A04J4143"],"award-info":[{"award-number":["2024A04J4143"]}]},{"name":"Science and Technology Foundation of Guangzhou","award":["2023A04J1723"],"award-info":[{"award-number":["2023A04J1723"]}]},{"name":"Science and Technology Foundation of Guangzhou","award":["2024A03J0092"],"award-info":[{"award-number":["2024A03J0092"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cybersecurity"],"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Steganography aims to embed and extract secret information in digital media for enhancing information security, which is widely applied to covert communication, copyright and privacy protection, digital forensics, etc. To resist steganalysis detection, generative steganography is one of the most promising techniques with embedding secret information into a generated image. Although existing generative steganographic methods could perform well with low hiding capacity, most of them encode the secret information in non-distribution-preserving manners, leading to poor security performance against steganalyzers when hiding more secret information. Meanwhile, the secret information tends to be difficult to be extracted with these methods because the secret-to-image transformations are irreversible. To tackle these issues, in this paper, we propose a reversible generative steganography with distribution-preserving scheme, which is mainly composed of a secret message mapping strategy with distribution-preserving and a reversible Glow model. To improve the anti-detectability against steganalyzers, the message mapping strategy with distribution-preserving is customized to encode the secret information into latent vectors which follow the Gaussian distribution as they are usually done in typical image generation models. The Glow model is then trained with reversible transformation to map the latent vectors into the generated stego-images with information hiding. Owing to the distribution-preserving and reversibility of the message mapping and Glow model, the proposed generative steganographic method achieves superior security performance and accurate extraction of secret message. Extensive experimental results demonstrate that the proposed method outperforms several state-of-the-art methods in terms of information extraction accuracy and anti-detectability, especially for high hiding capacity (up to 4.0 bpp).<\/jats:p>","DOI":"10.1186\/s42400-024-00317-6","type":"journal-article","created":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T01:02:31Z","timestamp":1741914151000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Reversible generative steganography with distribution-preserving"],"prefix":"10.1186","volume":"8","author":[{"given":"Weixuan","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3150-5103","authenticated-orcid":false,"given":"Yuan","family":"Rao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zuopeng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fei","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xutong","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peijun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,3,14]]},"reference":[{"key":"317_CR1","doi-asserted-by":"crossref","unstructured":"Arifianto A, Maulana MA, Mahadi MRS, et\u00a0al. (2022) EDGAN: disguising text as image using generative adversarial network. In: International Conference on Information and Communication Technology, pp. 1\u20136","DOI":"10.1109\/ICoICT49345.2020.9166184"},{"key":"317_CR3","first-page":"306","volume":"1998","author":"C Cachin","year":"1998","unstructured":"Cachin C (1998) An information-theoretic model for steganography. Int Workshop Inf Hiding 1998:306\u2013318","journal-title":"Int Workshop Inf Hiding"},{"issue":"2020","key":"317_CR4","first-page":"1","volume":"1","author":"Y Cao","year":"2020","unstructured":"Cao Y, Zhou Z, Wu Q et al (2020) Coverless information hiding based on the generation of anime characters. EURASIP J Image Video Process 1(2020):1\u201315","journal-title":"EURASIP J Image Video Process"},{"issue":"5","key":"317_CR5","doi-asserted-by":"publisher","first-page":"3343","DOI":"10.1109\/TDSC.2021.3095072","volume":"19","author":"K Chen","year":"2022","unstructured":"Chen K, Zhou H, Zhao H et al (2022) Distribution-preserving steganography based on text-to-speech generative models. IEEE Trans Dependable Secure Comput 19(5):3343\u20133356","journal-title":"IEEE Trans Dependable Secure Comput"},{"issue":"3","key":"317_CR6","doi-asserted-by":"publisher","first-page":"920","DOI":"10.1109\/TIFS.2011.2134094","volume":"6","author":"T Filler","year":"2011","unstructured":"Filler T, Judas J, Fridrich JJ (2011) Minimizing additive distortion in steganography using syndrome-trellis codes. IEEE Trans Inf Forensics Secur 6(3):920\u2013935","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"3","key":"317_CR7","doi-asserted-by":"publisher","first-page":"868","DOI":"10.1109\/TIFS.2012.2190402","volume":"7","author":"J Fridrich","year":"2012","unstructured":"Fridrich J, Kodovsky J (2012) Rich models for steganalysis of digital images. IEEE Trans Inf Forensics Secur 7(3):868\u2013882","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"317_CR8","doi-asserted-by":"crossref","unstructured":"Girshick RB (2015) Fast R-CNN. In: Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, December 7\u201313, pp. 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"317_CR9","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, et\u00a0al. (2014) Generative adversarial nets. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 2672\u20132680"},{"key":"317_CR10","doi-asserted-by":"crossref","unstructured":"Holub V, Fridrich J, Denemark T (2014) Universal distortion function for steganography in an arbitrary domain. EURASIP J Image Video Process 2014(1):1\u201313","DOI":"10.1186\/1687-417X-2014-1"},{"key":"317_CR11","doi-asserted-by":"publisher","first-page":"38303","DOI":"10.1109\/ACCESS.2018.2852771","volume":"6","author":"D Hu","year":"2018","unstructured":"Hu D, Wang WL, Jiang Zheng S et al (2018) A novel image steganography method via deep convolutional generative adversarial networks. IEEE Access 6:38303\u201338314","journal-title":"IEEE Access"},{"issue":"1","key":"317_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s42400-023-00147-y","volume":"6","author":"CC Islamy","year":"2023","unstructured":"Islamy CC, Ahmad T, Ijtihadie RM (2023) Reversible data hiding based on histogram and prediction error for sharing secret data. Cybersecurity 6(1):1\u201312","journal-title":"Cybersecurity"},{"key":"317_CR2","unstructured":"Jea B (2023) Improving image generation with better captions. https:\/\/cdn.openai.com\/papers\/dall-e-3.pdf"},{"key":"317_CR13","doi-asserted-by":"crossref","unstructured":"Jiang W, Hu D, Yu C, et\u00a0al. (2020) A new steganography without embedding based on adversarial training. In: Proceedings of the ACM Turing Celebration Conference, pp. 219\u2013223","DOI":"10.1145\/3393527.3393564"},{"key":"317_CR14","unstructured":"Jin Y, Zhang J, Li M, et\u00a0al. (2017) Towards the automatic anime characters creation with generative adversarial networks. ArXiv preprint, arXiv:1708.05509"},{"key":"317_CR15","unstructured":"Karras T, Aila T, Laine S, et\u00a0al. (2018) Progressive growing of gans for improved quality, stability, and variation. 6th International Conference on Learning Representations (ICLR), Vancouver, BC, Canada, Apr. 30\u2013May. 3"},{"key":"317_CR16","unstructured":"Kingma DP, Dhariwal P (2018) Glow: Generative flow with invertible 1$$\\times$$1 convolutions. In: Proceedings of Advances in Neural Information Processing Systems (NIPS), pp. 10215\u201310224"},{"key":"317_CR17","doi-asserted-by":"crossref","unstructured":"Li J, Niu K, Liao L, et\u00a0al. (2020) A generative steganography method based on WGAN\u2013GP. In: International Conference on Artificial Intelligence and Security, pp. 386\u2013397","DOI":"10.1007\/978-981-15-8083-3_34"},{"key":"317_CR18","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.ins.2020.12.002","volume":"553","author":"Q Li","year":"2021","unstructured":"Li Q, Wang X, Wang X et al (2021) An encrypted coverless information hiding method based on generative models. Inf Sci 553:19\u201330","journal-title":"Inf Sci"},{"issue":"3","key":"317_CR19","doi-asserted-by":"publisher","first-page":"1482","DOI":"10.1109\/TIP.2018.2878290","volume":"28","author":"S Li","year":"2018","unstructured":"Li S, Zhang X (2018) Toward construction-based data hiding: from secrets to fingerprint images. IEEE Trans Image Process 28(3):1482\u20131497","journal-title":"IEEE Trans Image Process"},{"key":"317_CR20","unstructured":"Liu M, Zhang M, Liu J, et\u00a0al. (2017) Coverless information hiding based on generative adversarial networks. ArXiv preprint, arXiv:1712.06951"},{"key":"317_CR21","doi-asserted-by":"crossref","unstructured":"Liu X, Ma Z, Ma J, et\u00a0al. (2022) Image disentanglement autoencoder for steganography without embedding. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, June 18\u201324, pp. 2303-2312","DOI":"10.1109\/CVPR52688.2022.00234"},{"issue":"7","key":"317_CR22","doi-asserted-by":"publisher","first-page":"2779","DOI":"10.1109\/TCSVT.2020.3033945","volume":"31","author":"Y Luo","year":"2020","unstructured":"Luo Y, Qin J, Xiang X et al (2020) Coverless image steganography based on multi-object recognition. IEEE Trans Circuits Syst Video Technol 31(7):2779\u20132791","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"2","key":"317_CR23","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.32604\/cmc.2020.010867","volume":"64","author":"Y Luo","year":"2020","unstructured":"Luo Y, Qin J, Xiang X et al (2020) Coverless image steganography based on image segmentation. Comput Mater Continua 64(2):1281\u20131295","journal-title":"Comput Mater Continua"},{"issue":"1","key":"317_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s42400-023-00156-x","volume":"6","author":"JDLC Ntivuguruzwa","year":"2023","unstructured":"Ntivuguruzwa JDLC, Ahmad T (2023) A convolutional neural network to detect possible hidden data in spatial domain images. Cybersecurity 6(1):1\u201323","journal-title":"Cybersecurity"},{"key":"317_CR25","doi-asserted-by":"crossref","unstructured":"Peng J, Sun P, Zhang L, et\u00a0al. (2012) Timing synchronization for ofdma femtocells in the presence of co-channel interference. In: International Wireless Communications and Mobile Computing Conference (IWCMC). Limassol, Cyprus, August 27-31, pp. 1215\u20131220","DOI":"10.1109\/IWCMC.2012.6314380"},{"key":"317_CR26","unstructured":"Radford A, Metz L, Chintala S (2016) Unsupervised representation learning with deep convolutional generative adversarial networks. In: International Conference on Learning Representations (ICLR), San Juan, Puerto Rico, May 2\u20134"},{"key":"317_CR27","doi-asserted-by":"crossref","unstructured":"Rombach R, Blattmann A, Lorenz D, et\u00a0al. (2022) High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA, pp. 10674\u201310685","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"317_CR28","doi-asserted-by":"crossref","unstructured":"Saito M, Matsui Y (2015) Illustration2vec: a semantic vector representation of illustrations. In: SIGGRAPH Asia Technical Briefs, Kobe, Japan pp. 5:1\u20135:4","DOI":"10.1145\/2820903.2820907"},{"key":"317_CR29","doi-asserted-by":"publisher","first-page":"2826","DOI":"10.1109\/TIFS.2024.3354411","volume":"19","author":"W Tang","year":"2024","unstructured":"Tang W, Zhou Z, Li B et al (2024) Joint cost learning and payload allocation with image-wise attention for batch steganography. IEEE Trans Inf Forensics Secur 19:2826\u20132839","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"7","key":"317_CR30","doi-asserted-by":"publisher","first-page":"4151","DOI":"10.1109\/TITS.2020.3017596","volume":"22","author":"S Wan","year":"2020","unstructured":"Wan S, Gu R, Umer T et al (2020) Toward offloading internet of vehicles applications in 5g networks. IEEE Trans Intell Transp Syst 22(7):4151\u20134159","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"5","key":"317_CR31","doi-asserted-by":"publisher","first-page":"708","DOI":"10.1109\/LSP.2016.2548421","volume":"23","author":"G Xu","year":"2016","unstructured":"Xu G, Wu H, Shi YQ (2016) Structural design of convolutional neural networks for steganalysis. Signal Process Lett 23(5):708\u2013712","journal-title":"Signal Process Lett"},{"issue":"12","key":"317_CR32","doi-asserted-by":"publisher","first-page":"1653","DOI":"10.1007\/s00371-014-1045-z","volume":"31","author":"J Xu","year":"2015","unstructured":"Xu J, Mao X, Jin X et al (2015) Hidden message in a deformation-based texture. Vis Comput 31(12):1653\u20131669","journal-title":"Vis Comput"},{"key":"317_CR33","doi-asserted-by":"publisher","first-page":"839","DOI":"10.1109\/TIFS.2019.2922229","volume":"15","author":"J Yang","year":"2019","unstructured":"Yang J, Ruan D, Huang J et al (2019) An embedding cost learning framework using GAN. IEEE Trans Inf Forensics Secur 15:839\u2013851","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"3","key":"317_CR34","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.1007\/s12083-020-01033-x","volume":"14","author":"C Yu","year":"2021","unstructured":"Yu C, Hu D, Zheng S et al (2021) An improved steganography without embedding based on attention GAN. Peer-to-Peer Netw Appl 14(3):1446\u20131457","journal-title":"Peer-to-Peer Netw Appl"},{"issue":"4","key":"317_CR35","doi-asserted-by":"publisher","first-page":"516","DOI":"10.26599\/TST.2019.9010027","volume":"25","author":"Z Zhang","year":"2020","unstructured":"Zhang Z, Fu G, Ni R et al (2020) A generative method for steganography by cover synthesis with auxiliary semantics. Tsinghua Sci Technol 25(4):516\u2013527","journal-title":"Tsinghua Sci Technol"},{"issue":"13","key":"317_CR36","doi-asserted-by":"publisher","first-page":"4927","DOI":"10.1007\/s00500-018-3151-8","volume":"23","author":"Z Zhou","year":"2019","unstructured":"Zhou Z, Mu Y, Wu QMJ (2019) Coverless image steganography using partial-duplicate image retrieval. Soft Comput 23(13):4927\u20134938","journal-title":"Soft Comput"}],"container-title":["Cybersecurity"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42400-024-00317-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s42400-024-00317-6\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s42400-024-00317-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,14]],"date-time":"2025-03-14T01:02:53Z","timestamp":1741914173000},"score":1,"resource":{"primary":{"URL":"https:\/\/cybersecurity.springeropen.com\/articles\/10.1186\/s42400-024-00317-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,14]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["317"],"URL":"https:\/\/doi.org\/10.1186\/s42400-024-00317-6","relation":{},"ISSN":["2523-3246"],"issn-type":[{"value":"2523-3246","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,14]]},"assertion":[{"value":"14 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"18"}}