{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:05:16Z","timestamp":1775228716659,"version":"3.50.1"},"reference-count":32,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T00:00:00Z","timestamp":1764633600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020YFA0712300"],"award-info":[{"award-number":["2020YFA0712300"]}]},{"name":"Shanghai Sailing Program","award":["24YF2730200"],"award-info":[{"award-number":["24YF2730200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62471294"],"award-info":[{"award-number":["62471294"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62231022"],"award-info":[{"award-number":["62231022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62502312"],"award-info":[{"award-number":["62502312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Image steganography is crucial for secure communication, enabling covert data embedding within cover images. While traditional methods such as LSB embedding are vulnerable to detection, deep learning techniques like GANs and autoencoders have improved performance, yet they still struggle with dynamic adaptation to diverse secret data types, limited training datasets, and resilience to distortions. To address these issues, we propose a flexible framework with adaptive multi-encoder\u2013decoder pairs, extensive dataset training, and an optimized architecture with specialized components. Our model achieves significant improvements in Secret Recovery Accuracy (SRA), Stego-Image Quality (SSIM, PSNR), and robustness to noise, with SSIM of 0.99 and recovery accuracy over 98%. It also reduces the detection rate, with an AUC approaching 0.5 in steganalysis. These results set a new benchmark for secure image transmission and privacy-preserving communication.<\/jats:p>","DOI":"10.3390\/e27121223","type":"journal-article","created":{"date-parts":[[2025,12,2]],"date-time":"2025-12-02T12:39:43Z","timestamp":1764679183000},"page":"1223","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Deep Learning-Based Image Steganography with Latent Space Embedding and Smart Decoder Selection"],"prefix":"10.3390","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-0182-805X","authenticated-orcid":false,"given":"Yiqiao","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China"}]},{"given":"Na","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China"}]},{"given":"Xiaolong","family":"Hong","sequence":"additional","affiliation":[{"name":"School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China"}]},{"given":"Yanchun","family":"Peng","sequence":"additional","affiliation":[{"name":"School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2872-795X","authenticated-orcid":false,"given":"Shuo","family":"Shao","sequence":"additional","affiliation":[{"name":"Department of System Science, University of Shanghai for Science and Technology, Shanghai 200093, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"e1481","DOI":"10.1002\/widm.1481","article-title":"Deep learning based image steganography: A review","volume":"13","author":"Wani","year":"2023","journal-title":"Wiley Interdiscip. Rev. Data Min. Knowl. Discov."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"124390","DOI":"10.1016\/j.eswa.2024.124390","article-title":"A survey on deep-learning-based image steganography","volume":"254","author":"Song","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"4775","DOI":"10.1007\/s11831-022-09749-0","article-title":"A systematic review of computational image steganography approaches","volume":"29","author":"Kaur","year":"2022","journal-title":"Arch. Comput. Methods Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/j.neucom.2018.06.075","article-title":"Comprehensive survey of image steganography: Techniques, evaluations, and trends in future research","volume":"335","author":"Kadhim","year":"2019","journal-title":"Neurocomputing"},{"key":"ref_5","unstructured":"Wang, Z., Byrnes, O., Wang, H., Sun, R., Ma, C., Chen, H., Wu, Q., and Xue, M. (2021). Data hiding with deep learning: A survey unifying digital watermarking and steganography. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Prabakaran, G.K., and Bhavani, R. (2012, January 21\u201322). A modified secure digital image steganography based on discrete wavelet transform. Proceedings of the 2012 International Conference on Computing, Electronics and Electrical Technologies (ICCEET), Nagercoil, India.","DOI":"10.1109\/ICCEET.2012.6203811"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"e30","DOI":"10.1561\/116.20240038","article-title":"A Comprehensive Survey of Digital Image Steganography and Steganalysis","volume":"13","author":"Luo","year":"2024","journal-title":"APSIPA Trans. Signal Inf. Process."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Liu, L., Tang, L., and Zheng, W. (2022). Lossless Image Steganography Based on Invertible Neural Networks. Entropy, 24.","DOI":"10.3390\/e24121762"},{"key":"ref_9","first-page":"2069","article-title":"Hiding images in plain sight: Deep steganography","volume":"30","author":"Baluja","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"},{"key":"ref_10","unstructured":"Zhang, K.A., Cuesta-Infante, A., Xu, L., and Veeramachaneni, K. (2019). SteganoGAN: High capacity image steganography with GANs. arXiv."},{"key":"ref_11","first-page":"103631","article-title":"Image steganography based on smooth cycle-consistent generative adversarial network","volume":"79","author":"Abdollahi","year":"2023","journal-title":"J. Inf. Secur. Appl."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"90574","DOI":"10.1109\/ACCESS.2019.2920956","article-title":"A steganography algorithm based on CycleGAN for covert communication in the Internet of Things","volume":"7","author":"Meng","year":"2019","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"023006","DOI":"10.1117\/1.JEI.30.2.023006","article-title":"Robust image steganography framework based on generative adversarial network","volume":"30","author":"Li","year":"2021","journal-title":"J. Electron. Imaging"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhu, J., Kaplan, R., Johnson, J., and Fei-Fei, L. (2018, January 8\u201314). HiDDeN: Hiding data with deep networks. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.","DOI":"10.1007\/978-3-030-01267-0_40"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"2909","DOI":"10.1109\/TCSVT.2020.3027843","article-title":"Secure Robust JPEG Steganography Based on AutoEncoder with Adaptive BCH Encoding","volume":"31","author":"Lu","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, Z., Zhang, X., Zhang, X., and Zhang, H. (2022). Deep Image Steganography Using Transformer and Recursive Permutation. Entropy, 24.","DOI":"10.3390\/e24070878"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Fan, H., Jin, C., and Li, M. (2025). AGASI: A Generative Adversarial Network-Based Approach to Strengthening Adversarial Image Steganography. Entropy, 27.","DOI":"10.3390\/e27030282"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"219","DOI":"10.1016\/j.neunet.2023.03.037","article-title":"Robust data hiding for JPEG images with invertible neural network","volume":"163","author":"Shang","year":"2023","journal-title":"Neural Netw."},{"key":"ref_19","unstructured":"Peng, Y., Wang, Y., Hu, D., Chen, K., Rong, X., and Zhang, W. (November, January 28). LDStega: Practical and robust generative image steganography based on latent diffusion models. Proceedings of the 32nd ACM International Conference on Multimedia, Melbourne, VIC, Australia."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"120416","DOI":"10.1016\/j.eswa.2023.120416","article-title":"Robust Image Steganography Against Lossy JPEG Compression Based on Embedding Domain Selection and Adaptive Error Correction","volume":"229","author":"Duan","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1007\/978-3-642-16435-4_13","article-title":"Using high-dimensional image models to perform highly undetectable steganography","volume":"Volume 6387","author":"Filler","year":"2010","journal-title":"Information Hiding (IH)"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Holub, V., and Fridrich, J. (2012, January 2\u20135). Designing steganographic distortion using directional filters. Proceedings of the IEEE International Workshop on Information Forensics and Security (WIFS), Costa Adeje, Spain.","DOI":"10.1109\/WIFS.2012.6412655"},{"key":"ref_23","unstructured":"Zhu, H., Zhang, T., and Li, B. (2022). Hiding data in colors: Secure and lossless image steganography via conditional invertible neural networks. arXiv."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1007\/s11760-025-03818-0","article-title":"Research on image steganography based on a conditional invertible neural network","volume":"19","author":"Liu","year":"2025","journal-title":"Signal Image Video Process."},{"key":"ref_25","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q.V., Hinton, G., and Dean, J. (2017, January 24\u201326). Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. Proceedings of the International Conference on Learning Representations (ICLR), Toulon, France."},{"key":"ref_26","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume":"35","author":"Zhou","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"125829","DOI":"10.1016\/j.eswa.2024.125829","article-title":"Image progressive steganography based on multi-frequency fusion deep network with dynamic sensing","volume":"264","author":"Li","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Xu, Y., Mou, C., Hu, Y., Xie, J., and Zhang, J. (2022, January 18\u201324). Robust invertible image steganography. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.00772"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Jing, J., Deng, X., Xu, M., Wang, J., and Guan, Z. (2021, January 11\u201317). HiNet: Deep image hiding by invertible network. Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Montreal, QC, Canada.","DOI":"10.1109\/ICCV48922.2021.00469"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Chen, Z., Liu, T., Huang, J.-J., Zhao, W., Bi, X., and Wang, M. (2024, January 14\u201319). Invertible mosaic image hiding network for very large capacity image steganography. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea.","DOI":"10.1109\/ICASSP48485.2024.10448382"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Bui, T.-V., Agarwal, S., Yu, N., and Collomosse, J. (2023, January 18\u201322). RoSteALS: Robust steganography using autoencoder latent space. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Vancouver, BC, Canada.","DOI":"10.1109\/CVPRW59228.2023.00100"},{"key":"ref_32","first-page":"10223","article-title":"UDH: Universal deep hiding for steganography, watermarking, and light field messaging","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst. (NeurIPS)"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/12\/1223\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T05:17:31Z","timestamp":1764825451000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/27\/12\/1223"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,2]]},"references-count":32,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["e27121223"],"URL":"https:\/\/doi.org\/10.3390\/e27121223","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,2]]}}}