{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T10:24:24Z","timestamp":1786962264650,"version":"build-2736575974"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J. King Saud Univ. Comput. Inf. Sci."],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Steganography aims to conceal secret messages within carrier data without introducing perceptible distortion. Existing methods are typically designed for a single type of carrier (e.g., images) and cannot meet the requirements of the current trend toward multimodal media. Moreover, many deep-learning\u2013based schemes require transmitting a message extractor alongside the carrier for accurate recovery, which significantly undermines steganographic stealthiness. To address these limitations, we propose Unified Token-Space Steganography (UTS), a multimodal steganographic framework based on fast implicit neural representations. Our core idea is to eliminate modality discrepancies through unified representation, enabling multimodal adaptation within a single framework. We employ a fast implicit neural representation method to encode multimodal data into compact spatial vector tokens and embed secret messages under the constraint of a fixed message extractor\u2014whose parameters are initialized with a pre-agreed random seed and then frozen. During communication, the sender and receiver only need to exchange stego tokens to recover the secret message, avoiding the transmission of an additional extractor. Experiments on three modalities (images, weather data, and 3D scenes) demonstrate that UTS achieves 100% message accuracy, with PSNR exceeding 35 dB for stego images and weather data, and high-quality reconstruction for 3D scenes. These results demonstrate that UTS provides an efficient and practical steganographic framework for modern multimodal media.<\/jats:p>","DOI":"10.1007\/s44443-026-01076-9","type":"journal-article","created":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T09:26:47Z","timestamp":1786958807000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UTS: Unified Token-Space steganography for multimodal data via fast implicit neural representation"],"prefix":"10.1007","volume":"38","author":[{"given":"Qiya","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jia","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,17]]},"reference":[{"issue":"5","key":"1076_CR1","doi-asserted-by":"publisher","first-page":"1181","DOI":"10.1109\/TIFS.2018.2871749","volume":"14","author":"M Boroumand","year":"2018","unstructured":"Boroumand M, Chen M, Fridrich J (2018) Deep residual network for steganalysis of digital images. IEEE Trans Inf Forensics Secur 14(5):1181\u20131193","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"1","key":"1076_CR2","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman L (2001) Random forests. Mach Learn 45(1):5\u201332. https:\/\/doi.org\/10.1023\/A:1010933404324","journal-title":"Mach Learn"},{"key":"1076_CR3","doi-asserted-by":"crossref","unstructured":"Chen H, Xie S, Lim SN (2024) Fast encoding and decoding for implicit video representation. In: European conference on computer vision. Springer, pp 402\u2013418","DOI":"10.1007\/978-3-031-72933-1_23"},{"issue":"3","key":"1076_CR4","doi-asserted-by":"publisher","first-page":"03303","DOI":"10.1117\/1.JEI.33.3.033031","volume":"33","author":"W Dong","year":"2024","unstructured":"Dong W, Liu J, Chen L et al (2024a) Stega4NeRF: cover selection steganography for neural radiance fields. J Electron Imaging 33(3):03303","journal-title":"J Electron Imaging"},{"key":"1076_CR5","doi-asserted-by":"crossref","unstructured":"Dong W, Liu J, Chen L et al (2024b) Implicit neural representation steganography by neuron pruning. Multimed Syst 30(5):266","DOI":"10.1007\/s00530-024-01476-9"},{"issue":"6","key":"1076_CR6","doi-asserted-by":"publisher","first-page":"063017","DOI":"10.1117\/1.JEI.33.6.063017","volume":"33","author":"W Dong","year":"2024","unstructured":"Dong W, Liu J, Chen L et al (2024c) Stegainr4mih: steganography by implicit neural representation for multi-image hiding. J Electron Imaging 33(6):063017\u2013063017","journal-title":"J Electron Imaging"},{"key":"1076_CR7","unstructured":"Dupont E, Kim H, Eslami S (2022) From data to functa: Your data point is a function and you can treat it like one. arXiv preprint arXiv:2201.12204"},{"key":"1076_CR8","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/j.patrec.2005.10.010","volume":"8","author":"T Fawcett","year":"2005","unstructured":"Fawcett T (2005) Roc analysis in pattern recognition. Pattern Recogn Lett 8:861\u201387. https:\/\/doi.org\/10.1016\/j.patrec.2005.10.010","journal-title":"Pattern Recogn Lett"},{"issue":"3","key":"1076_CR9","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":"1076_CR10","doi-asserted-by":"crossref","unstructured":"Han G, Lee DJ, Hur J, et\u00a0al (2023) Deep cross-modal steganography using neural representations. In: 2023 IEEE International Conference on Image Processing (ICIP), IEEE, pp 1205\u20131209","DOI":"10.1109\/ICIP49359.2023.10222113"},{"key":"1076_CR11","doi-asserted-by":"publisher","unstructured":"Hanley JA, McNeil BJ (1982) The meaning and use of the area under a receiver operating characteristic (roc) curve. Radiology 143(1):29\u201336. https:\/\/doi.org\/10.1148\/radiology.143.1.7063747","DOI":"10.1148\/radiology.143.1.7063747"},{"issue":"12","key":"1076_CR12","doi-asserted-by":"publisher","first-page":"1996","DOI":"10.1109\/TIFS.2013.2286682","volume":"8","author":"V Holub","year":"2013","unstructured":"Holub V, Fridrich J (2013) Random projections of residuals for digital image steganalysis. IEEE Trans Inf Forensics Secur 8(12):1996\u20132006","journal-title":"IEEE Trans Inf Forensics Secur"},{"issue":"6","key":"1076_CR13","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1037\/h0070888","volume":"24","author":"H Hotelling","year":"1933","unstructured":"Hotelling H (1933) Analysis of a complex of statistical variables into principal components. J Educ Psychol 24(6):417. https:\/\/doi.org\/10.1037\/h0070888","journal-title":"J Educ Psychol"},{"key":"1076_CR14","doi-asserted-by":"crossref","unstructured":"Huang Q, Li H, Liao Y et al (2024) Noise-nerf: Hide information in neural radiance field using trainable noise. In: Wand M, Malinovsk\u00e1 K, Schmidhuber J et al (eds) Artificial Neural Networks and Machine Learning - ICANN 2024. Springer Nature Switzerland, Cham, pp 320\u2013334","DOI":"10.1007\/978-3-031-72335-3_22"},{"key":"1076_CR15","doi-asserted-by":"crossref","unstructured":"Huang W, Yang Q, Xia S (2025) Linr-pcgc: Lossless implicit neural representations for point cloud geometry compression. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 28577\u201328586","DOI":"10.1109\/ICCV51701.2025.02654"},{"key":"1076_CR16","doi-asserted-by":"crossref","unstructured":"Jing J, Deng X, Xu M (2021) Hinet: Deep image hiding by invertible network. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 4733\u20134742","DOI":"10.1109\/ICCV48922.2021.00469"},{"key":"1076_CR17","unstructured":"Karras T, Laine AT, S (2017) Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196"},{"key":"1076_CR18","doi-asserted-by":"publisher","unstructured":"Kishore V, Raghunathan A, Belongie SJ et\u00a0al (2022) Fixed neural network steganography: Train the images, not the network. In: Proceedings of the international conference on learning representations. OpenReview.net. https:\/\/doi.org\/10.48550\/arXiv.2112.05217","DOI":"10.48550\/arXiv.2112.05217"},{"key":"1076_CR19","doi-asserted-by":"crossref","unstructured":"Li C, Feng BY, Fan Z, et\u00a0al (2023a) Steganerf: Embedding invisible information within neural radiance fields. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 441\u2013453","DOI":"10.1109\/ICCV51070.2023.00047"},{"key":"1076_CR20","unstructured":"Li G, Li S, Li M et\u00a0al (2023b) Towards deep network steganography: from networks to networks. arXiv preprint arXiv:2307.03444"},{"key":"1076_CR21","doi-asserted-by":"crossref","unstructured":"Li G, Li S, Li M et\u00a0al (2023c) Steganography of steganographic networks. In: Proceedings of the AAAI conference on artificial intelligence, pp 5178\u20135186","DOI":"10.1609\/aaai.v37i4.25647"},{"key":"1076_CR22","doi-asserted-by":"crossref","unstructured":"Li G, Li S, Luo Z et\u00a0al (2024) Purified and unified steganographic network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 27569\u201327578","DOI":"10.1109\/CVPR52733.2024.02603"},{"issue":"7","key":"1076_CR23","doi-asserted-by":"publisher","first-page":"10189","DOI":"10.1109\/TITS.2025.3550267","volume":"26","author":"Y Liu","year":"2025","unstructured":"Liu Y, Wang X, Hu E et al (2025) Vndhr: Variational single nighttime image dehazing for enhancing visibility in intelligent transportation systems via hybrid regularization. IEEE Trans Intell Transp Syst 26(7):10189\u20131020. https:\/\/doi.org\/10.1109\/TITS.2025.3550267","journal-title":"IEEE Trans Intell Transp Syst"},{"issue":"3","key":"1076_CR24","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1007\/s00530-026-02242-9","volume":"32","author":"Y Lu","year":"2026","unstructured":"Lu Y, Liu J, Wang Q et al (2026) Multi-image steganography via function extension of implicit neural representation. Multimedia Syst 32(3):184","journal-title":"Multimedia Syst"},{"key":"1076_CR25","doi-asserted-by":"crossref","unstructured":"Luo Z, Li S, Li G et\u00a0al (2023) Securing fixed neural network steganography. In: Proceedings of the 31st ACM international conference on multimedia, pp 7943\u20137951","DOI":"10.1145\/3581783.3611920"},{"issue":"2","key":"1076_CR26","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.26599\/TST.2025.9010030","volume":"31","author":"P Luo","year":"2025","unstructured":"Luo P, Liu J, Ke Y et al (2025) Hiding functions within functions: Steganography by implicit neural representations. Tsinghua Sci Technol 31(2):1058\u20131074. https:\/\/doi.org\/10.26599\/TST.2025.9010030","journal-title":"Tsinghua Sci Technol"},{"issue":"253","key":"1076_CR27","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1080\/01621459.1951.10500769","volume":"46","author":"FJ Massey Jr","year":"1951","unstructured":"Massey FJ Jr (1951) The kolmogorov-smirnov test for goodness of fit. J Am Stat Assoc 46(253):68\u201378. https:\/\/doi.org\/10.1080\/01621459.1951.10500769","journal-title":"J Am Stat Assoc"},{"key":"1076_CR28","doi-asserted-by":"crossref","unstructured":"Mildenhall B, Srinivasan PP, Tancik M (2020) Nerf: Representing scenes as neural radiance fields for view synthesis. In: European Conference on Computer Vision (ECCV)","DOI":"10.1007\/978-3-030-58452-8_24"},{"key":"1076_CR29","doi-asserted-by":"publisher","first-page":"161825","DOI":"10.1109\/ACCESS.2020.3021356","volume":"8","author":"RJ Mstafa","year":"2020","unstructured":"Mstafa RJ, Younis YM, Hussein HI et al (2020) A new video steganography scheme based on shi-tomasi corner detector. IEEE Access 8:161825\u2013161837","journal-title":"IEEE Access"},{"key":"1076_CR30","unstructured":"Ochs V, Bieder F, Se H (2025) Tabinr: An implicit neural representation framework for tabular data imputation. arXiv preprint arXiv:2510.01136"},{"key":"1076_CR31","doi-asserted-by":"publisher","unstructured":"Pearson K (1901) Liii. on lines and planes of closest fit to systems of points in space. London Edinburgh Dublin Philosophic Magaz J Sci 2(11):559\u2013572. https:\/\/doi.org\/10.1080\/14786440109462720","DOI":"10.1080\/14786440109462720"},{"key":"1076_CR32","unstructured":"Peng L, Wu A, Li W (2025) Pixel to gaussian: Ultra-fast continuous super-resolution with 2d gaussian modeling. arXiv preprint arXiv:2503.06617"},{"key":"1076_CR33","doi-asserted-by":"crossref","unstructured":"Rao L, Zhang X, Huang Y (2025) Implicit neural representation-based mri reconstruction method with sensitivity map constraints. arXiv preprint arXiv:2506.06043","DOI":"10.1109\/TIM.2026.3662877"},{"key":"1076_CR34","unstructured":"Sitzmann V, Martel J, Bergman A et al (2020) Implicit neural representations with periodic activation functions. Adv Neural Inf Process Syst 33:7462\u20137473"},{"key":"1076_CR35","unstructured":"Song Q (2023) Unified steganography via implicit neural representation. arXiv:2312.05496"},{"key":"1076_CR36","doi-asserted-by":"crossref","unstructured":"Song S, Yang S, Yoo CD (2024) Implicit steganography beyond the constraints of modality. In: European conference on computer vision. Springer, pp 289\u2013304","DOI":"10.1007\/978-3-031-73016-0_17"},{"issue":"3","key":"1076_CR37","first-page":"64","volume":"5","author":"LN Vaserstein","year":"1969","unstructured":"Vaserstein LN (1969) Markov processes over denumerable products of spaces, describing large systems of automata. Problemy Peredachi Informatsii 5(3):64\u201372","journal-title":"Problemy Peredachi Informatsii"},{"key":"1076_CR38","unstructured":"Vaswani A, Shazeer N, Parmar N (2017) Attention is all you need. Adv Neural Inf Process Syst 30"},{"issue":"4","key":"1076_CR39","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang Z, Bovik AC, Sheikh HR et al (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600\u2013612","journal-title":"IEEE Trans Image Process"},{"key":"1076_CR40","doi-asserted-by":"publisher","unstructured":"Wang Q, Liu J, Lu Y et\u00a0al (2026) Functa hiding: Steganography via modulated implicit representations. Comput Mater Continua. https:\/\/doi.org\/10.32604\/cmc.2026.081589","DOI":"10.32604\/cmc.2026.081589"},{"key":"1076_CR41","unstructured":"Wilk MB, Gnanadesikan R (1966) Probability plotting methods for the analysis of data. Citeseer"},{"key":"1076_CR42","doi-asserted-by":"crossref","unstructured":"Xu H, Zhang X, Wu X (2024) Fast point cloud geometry compression with context-based residual coding and inr-based refinement. In: European conference on computer vision. Springer, pp 270\u2013288","DOI":"10.1007\/978-3-031-73113-6_16"},{"key":"1076_CR43","unstructured":"Yang S et\u00a0al (2023) Flexible cross-modal steganography via implicit representations. arXiv preprint arXiv:2312.05496. Accessed 2024"},{"issue":"4","key":"1076_CR44","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1109\/LSP.2011.2114651","volume":"18","author":"X Zhang","year":"2011","unstructured":"Zhang X (2011) Reversible data hiding in encrypted image. IEEE Signal Process Lett 18(4):255\u2013258. https:\/\/doi.org\/10.1109\/LSP.2011.2114651","journal-title":"IEEE Signal Process Lett"},{"key":"1076_CR45","unstructured":"Zhang KA, Cuesta-Infante A, Xu L (2019) Steganogan: High capacity image steganography with gans. arXiv preprint arXiv:1901.03892"},{"issue":"7","key":"1076_CR46","doi-asserted-by":"publisher","first-page":"3287","DOI":"10.1109\/TKDE.2023.3295601","volume":"36","author":"S Zhang","year":"2023","unstructured":"Zhang S, Yuan W, Yin H (2023) Comprehensive privacy analysis on federated recommender system against attribute inference attacks. IEEE Trans Knowl Data Eng 36(7):3287\u20133301. https:\/\/doi.org\/10.1109\/TKDE.2023.3295601","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1076_CR47","doi-asserted-by":"crossref","unstructured":"Zhang S, Liu K, Gu J et\u00a0al (2024a) Attention beats linear for fast implicit neural representation generation. In: European conference on computer vision. Springer, pp 1\u201318","DOI":"10.1007\/978-3-031-73668-1_1"},{"key":"1076_CR48","doi-asserted-by":"publisher","unstructured":"Zhang S, Zhang X, Wan S et al (2024b) Generative adversarial and self-supervised dehazing network. IEEE Trans Industr Inf 20(3):4187\u2013419. https:\/\/doi.org\/10.1109\/TII.2023.3316180","DOI":"10.1109\/TII.2023.3316180"},{"issue":"6","key":"1076_CR49","doi-asserted-by":"publisher","first-page":"063043","DOI":"10.1117\/1.JEI.33.6.063043","volume":"33","author":"Y Zhong","year":"2024","unstructured":"Zhong Y, Ke Y, Liu M et al (2024) Image steganography based on generative implicit neural representation. J Electron Imaging 33(6):063043\u2013063043","journal-title":"J Electron Imaging"},{"issue":"20","key":"1076_CR50","doi-asserted-by":"publisher","first-page":"11041","DOI":"10.3390\/app152011041","volume":"15","author":"Y Zhong","year":"2025","unstructured":"Zhong Y, Liu J, Luo P et al (2025) Generative implicit steganography via message mapping. Appl Sci 15(20):11041","journal-title":"Appl Sci"},{"key":"1076_CR51","doi-asserted-by":"crossref","unstructured":"Zhu J, Kaplan R, Johnson J (2018) Hidden: Hiding data with deep networks. In: Proceedings of the European conference on computer vision (ECCV). pp 657\u2013672","DOI":"10.1007\/978-3-030-01267-0_40"}],"container-title":["Journal of King Saud University Computer and Information Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-01076-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44443-026-01076-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44443-026-01076-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T09:27:09Z","timestamp":1786958829000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44443-026-01076-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,17]]},"references-count":51,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["1076"],"URL":"https:\/\/doi.org\/10.1007\/s44443-026-01076-9","relation":{},"ISSN":["1319-1578","2213-1248"],"issn-type":[{"value":"1319-1578","type":"print"},{"value":"2213-1248","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,17]]},"assertion":[{"value":"2 June 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","label":"Ethics declaration","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"655"}}