{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T01:27:19Z","timestamp":1783042039453,"version":"3.54.6"},"reference-count":62,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T00:00:00Z","timestamp":1763337600000},"content-version":"unspecified","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":"crossref","award":["62176140"],"award-info":[{"award-number":["62176140"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>Image steganography aims to embed secret information into a cover image in such a manner that the hidden content remains visually imperceptible while still being accurately recoverable when needed. However, traditional image steganography methods often suffer from limited robustness and are highly susceptible to common image distortions such as Gaussian noise, Poisson noise, and lossy compression. To address these limitations, this article proposes DERIS, a robust image steganography model based on invertible neural networks (INNs), which enhances resistance to image distortions through structural design. The model integrates identical denoising enhancement modules both before the discrete wavelet transform (DWT) and after the inverse discrete wavelet transform (IDWT) in the backward extraction pathway, significantly improving the quality of the extracted secret images. Furthermore, a training strategy that incorporates denoising enhancement is employed to ensure the model\u2019s stability and reversibility under various types of image interference. Extensive experiments were conducted primarily on the DIV2K, ImageNet, and COCO datasets, using evaluation metrics including Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Learned Perceptual Image Patch Similarity (LPIPS), and Normalized Cross-correlation (NCC). Experimental results demonstrate that under Gaussian noise (\u03c3 = 10), the proposed method achieves a PSNR of 32.43 dB between cover and container images, and 30.24 dB between secret and extracted images on the DIV2K dataset, representing an improvement of 1.08 dB over Pris. Under JPEG compression (QF = 80), the method achieves PSNR values of 28.63 dB (cover-container) and 27.74 dB (secret-extracted) on the ImageNet dataset, which are 2.11 dB higher than those of Pris. Similarly, on the COCO dataset under the same attack condition, the method achieves PSNR values of 28.44 dB (cover-container) and 26.81 dB (secret-extracted), showing improvements of 0.91 dB over Pris. These results significantly outperform those of current state-of-the-art methods, demonstrating the enhanced robustness and practicality of the proposed approach.<\/jats:p>","DOI":"10.7717\/peerj-cs.3368","type":"journal-article","created":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T08:38:31Z","timestamp":1763368711000},"page":"e3368","source":"Crossref","is-referenced-by-count":2,"title":["Denoising and enhancement for robust image steganography"],"prefix":"10.7717","volume":"11","author":[{"given":"Dapeng","family":"Cheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-8507-4751","authenticated-orcid":true,"given":"Yanyan","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liunian","family":"Bian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2025,11,17]]},"reference":[{"key":"10.7717\/peerj-cs.3368\/ref-1","first-page":"126","article-title":"Ntire 2017 challenge on single image super-resolution: dataset and study","author":"Agustsson","year":"2017"},{"issue":"18","key":"10.7717\/peerj-cs.3368\/ref-2","doi-asserted-by":"publisher","first-page":"113157","DOI":"10.1016\/j.eswa.2019.113157","article-title":"Redmark: framework for residual diffusion watermarking based on deep networks","volume":"146","author":"Ahmadi","year":"2020","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"10.7717\/peerj-cs.3368\/ref-3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/iccv.2019.00325","article-title":"Real image denoising with real noise: a comprehensive study","volume":"130","author":"Anwar","year":"2022","journal-title":"International Journal of Computer Vision"},{"key":"10.7717\/peerj-cs.3368\/ref-4","article-title":"Hiding images in plain sight: deep steganography","volume-title":"Advances in Neural Information Processing Systems 30","author":"Baluja","year":"2017"},{"issue":"1","key":"10.7717\/peerj-cs.3368\/ref-5","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1016\/j.amc.2007.05.063","article-title":"Color image steganography scheme using DFT, SPIHT codec, and modified differential phase-shift keying techniques","volume":"196","author":"Chen","year":"2008","journal-title":"Applied Mathematics and Computation"},{"key":"10.7717\/peerj-cs.3368\/ref-6","first-page":"89","article-title":"Image steganography with enhanced security using generative adversarial networks","author":"Chen","year":"2023"},{"issue":"3","key":"10.7717\/peerj-cs.3368\/ref-7","doi-asserted-by":"publisher","first-page":"e1062","DOI":"10.7717\/peerj-cs.1062","article-title":"A novel steganography method for binary and color halftone images","volume":"8","author":"\u00c7iftci","year":"2022","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.3368\/ref-8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1410.8516","article-title":"NICE: non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"10.7717\/peerj-cs.3368\/ref-9","doi-asserted-by":"publisher","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 Systems with Applications"},{"key":"10.7717\/peerj-cs.3368\/ref-10","article-title":"High capacity image steganography using wavelet transform and genetic algorithm","volume":"1","author":"Ghasemi","year":"2011"},{"key":"10.7717\/peerj-cs.3368\/ref-11","volume-title":"Digital image processing","author":"Gonzalez","year":"2002","edition":"2"},{"key":"10.7717\/peerj-cs.3368\/ref-12","volume-title":"Digital image processing","author":"Gonzalez","year":"2018","edition":"4"},{"key":"10.7717\/peerj-cs.3368\/ref-13","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014"},{"key":"10.7717\/peerj-cs.3368\/ref-14","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/eSmarTA66764.2025.11132292","article-title":"Securing digital images: a review of modern steganographic techniques","volume-title":"2025 5th International Conference on Emerging Smart Technologies and Applications (eSmarTA)","author":"Hammad","year":"2025"},{"key":"10.7717\/peerj-cs.3368\/ref-15","article-title":"Generating steganographic images via adversarial training","author":"Hayes","year":"2017"},{"issue":"1","key":"10.7717\/peerj-cs.3368\/ref-16","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/83.736686","article-title":"Hidden digital watermarks in images","volume":"8","author":"Hsu","year":"1999","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.7717\/peerj-cs.3368\/ref-17","doi-asserted-by":"publisher","first-page":"8094","DOI":"10.1109\/TIFS.2024.3444311","article-title":"Establishing robust generative image steganography via popular stable diffusion","volume":"19","author":"Hu","year":"2024","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"10.7717\/peerj-cs.3368\/ref-18","first-page":"99","article-title":"Multibit embedding algorithm for steganography of palette-based images","author":"Imaizumi","year":"2014"},{"key":"10.7717\/peerj-cs.3368\/ref-19","first-page":"4733","article-title":"Hinet: deep image hiding by invertible network","author":"Jing","year":"2021"},{"key":"10.7717\/peerj-cs.3368\/ref-20","first-page":"2723","article-title":"StegFormer: rebuilding the glory of autoencoder-based steganography","volume":"38","author":"Ke","year":"2024"},{"key":"10.7717\/peerj-cs.3368\/ref-21","doi-asserted-by":"publisher","first-page":"105","DOI":"10.1016\/j.protcy.2013.12.342","article-title":"A genetic algorithm based steganography using discrete cosine transformation (GASDCT)","volume":"10","author":"Khamrui","year":"2013","journal-title":"Procedia Technology"},{"issue":"8","key":"10.7717\/peerj-cs.3368\/ref-22","doi-asserted-by":"publisher","first-page":"9441","DOI":"10.1007\/s10489-021-02938-7","article-title":"High capacity speech steganography for the g723. 1 coder based on quantised line spectral pairs interpolation and cnn auto-encoding","volume":"52","author":"Kheddar","year":"2022","journal-title":"Applied Intelligence"},{"issue":"4","key":"10.7717\/peerj-cs.3368\/ref-23","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1007\/s00530-024-01427-4","article-title":"GAN-based image steganography by exploiting transform domain knowledge with deep networks","volume":"30","author":"Li","year":"2024","journal-title":"Multimedia Systems"},{"key":"10.7717\/peerj-cs.3368\/ref-24","first-page":"740","article-title":"Microsoft COCO: common objects in context","author":"Lin","year":"2014"},{"issue":"2","key":"10.7717\/peerj-cs.3368\/ref-25","doi-asserted-by":"publisher","first-page":"109822","DOI":"10.1016\/j.patcog.2023.109822","article-title":"Unpaired image super-resolution using a lightweight invertible neural network","volume":"144","author":"Liu","year":"2023","journal-title":"Pattern Recognition"},{"issue":"12","key":"10.7717\/peerj-cs.3368\/ref-26","doi-asserted-by":"publisher","first-page":"1762","DOI":"10.3390\/e24121762","article-title":"Lossless image steganography based on invertible neural networks","volume":"24","author":"Liu","year":"2022","journal-title":"Entropy"},{"key":"10.7717\/peerj-cs.3368\/ref-27","first-page":"12345","article-title":"Reinforced residual encoder-decoder network for image denoising via deeper encoding and balanced skip connections","author":"Liu","year":"2022a"},{"key":"10.7717\/peerj-cs.3368\/ref-28","first-page":"12345","article-title":"Convolutional neural network-based image steganography with enhanced security","author":"Liu","year":"2022b"},{"key":"10.7717\/peerj-cs.3368\/ref-29","first-page":"10816","article-title":"Large-capacity image steganography based on invertible neural networks","author":"Lu","year":"2021"},{"key":"10.7717\/peerj-cs.3368\/ref-30","first-page":"13548","article-title":"Distortion agnostic deep watermarking","author":"Luo","year":"2020"},{"issue":"22","key":"10.7717\/peerj-cs.3368\/ref-31","doi-asserted-by":"publisher","first-page":"10928","DOI":"10.3390\/app112210928","article-title":"Data hiding and its applications: digital watermarking and steganography","volume":"11","author":"Meg\u00edas","year":"2021","journal-title":"Applied Sciences"},{"key":"10.7717\/peerj-cs.3368\/ref-32","first-page":"61","article-title":"Multi bit plane image steganography","author":"Nguyen","year":"2006"},{"key":"10.7717\/peerj-cs.3368\/ref-33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.13846","article-title":"Understanding SSIM","author":"Nilsson","year":"2020"},{"key":"10.7717\/peerj-cs.3368\/ref-34","first-page":"282","article-title":"Image steganography method based on pvd and modulus function","author":"Pan","year":"2011"},{"issue":"3","key":"10.7717\/peerj-cs.3368\/ref-35","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","article-title":"ImageNet large scale visual recognition challenge","volume":"115","author":"Russakovsky","year":"2015","journal-title":"International Journal of Computer Vision"},{"issue":"3","key":"10.7717\/peerj-cs.3368\/ref-36","doi-asserted-by":"publisher","first-page":"108908","DOI":"10.1016\/j.sigpro.2022.108908","article-title":"Digital image steganography survey and investigation (goal, assessment, method, development, and dataset)","volume":"206","author":"Rustad","year":"2023","journal-title":"Signal Processing"},{"issue":"1","key":"10.7717\/peerj-cs.3368\/ref-37","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1515\/comp-2020-0136","article-title":"Digital image steganography and steganalysis: a journey of the past three decades","volume":"10","author":"Sahu","year":"2020","journal-title":"Open Computer Science"},{"issue":"1","key":"10.7717\/peerj-cs.3368\/ref-38","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1609\/aaai.v38i1.27776","article-title":"StegastyleGAN: towards generic and practical generative image steganography","volume":"38","author":"Su","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"10.7717\/peerj-cs.3368\/ref-39","doi-asserted-by":"publisher","DOI":"10.36227\/techrxiv.171467876.66249301\/v1","article-title":"A conditional invertible neural network-based fault detection","author":"Sun","year":"2024"},{"key":"10.7717\/peerj-cs.3368\/ref-40","first-page":"2117","article-title":"StegaStamp: invisible hyperlinks in physical photographs","author":"Tancik","year":"2020"},{"issue":"6","key":"10.7717\/peerj-cs.3368\/ref-41","doi-asserted-by":"publisher","first-page":"1129","DOI":"10.1016\/j.sigpro.2008.12.017","article-title":"Reversible image hiding scheme using predictive coding and histogram shifting","volume":"89","author":"Tsai","year":"2009","journal-title":"Signal Processing"},{"key":"10.7717\/peerj-cs.3368\/ref-42","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3430546","article-title":"Deep learning-based robust image steganography under noisy environments","volume":"12","author":"Venugopalan","year":"2024","journal-title":"IEEE Access"},{"key":"10.7717\/peerj-cs.3368\/ref-43","doi-asserted-by":"publisher","DOI":"10.1117\/12.2275157","article-title":"Image quality assessment for determining efficacy and limitations of super-resolution convolutional neural network (SRCNN)","author":"Wang","year":"2019"},{"issue":"3","key":"10.7717\/peerj-cs.3368\/ref-44","doi-asserted-by":"publisher","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 Interdisciplinary Reviews: Data Mining and Knowledge Discovery"},{"key":"10.7717\/peerj-cs.3368\/ref-45","first-page":"87","article-title":"High-capacity convolutional video steganography with temporal residual modeling","author":"Weng","year":"2019"},{"issue":"4","key":"10.7717\/peerj-cs.3368\/ref-46","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/tgrs.2023.3264777","article-title":"Fast Bayesian inversion of airborne electromagnetic data based on the invertible neural network","volume":"61","author":"Wu","year":"2023","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"issue":"6","key":"10.7717\/peerj-cs.3368\/ref-47","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/fi10060054","article-title":"StegNet: mega image steganography capacity with deep convolutional networks","volume":"10","author":"Wu","year":"2018","journal-title":"MDPI Information"},{"key":"10.7717\/peerj-cs.3368\/ref-48","first-page":"7875","article-title":"Robust invertible image steganography","author":"Xu","year":"2022"},{"key":"10.7717\/peerj-cs.3368\/ref-49","doi-asserted-by":"publisher","first-page":"38031","DOI":"10.3389\/frai.2025.1532895","article-title":"Deep learning for steganalysis: evaluating model robustness and generalization","volume":"8","author":"Xu","year":"2025","journal-title":"Frontiers in Artificial Intelligence"},{"issue":"1","key":"10.7717\/peerj-cs.3368\/ref-50","doi-asserted-by":"publisher","first-page":"566","DOI":"10.1016\/j.ins.2023.02.013","article-title":"Invertible mask network for face privacy preservation","volume":"629","author":"Yang","year":"2023","journal-title":"Information Sciences"},{"issue":"4","key":"10.7717\/peerj-cs.3368\/ref-51","doi-asserted-by":"publisher","first-page":"107148","DOI":"10.1016\/j.neunet.2025.107148","article-title":"DKiS: decay weight invertible image steganography with private key","volume":"185","author":"Yang","year":"2025","journal-title":"Neural Networks"},{"issue":"7253","key":"10.7717\/peerj-cs.3368\/ref-52","doi-asserted-by":"publisher","first-page":"108419","DOI":"10.1016\/j.engappai.2024.108419","article-title":"PRIS: practical robust invertible network for image steganography","volume":"133","author":"Yang","year":"2024","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"4","key":"10.7717\/peerj-cs.3368\/ref-53","doi-asserted-by":"publisher","first-page":"123540","DOI":"10.1016\/j.eswa.2024.123540","article-title":"High invisibility image steganography with wavelet transform and generative adversarial network","volume":"249","author":"Yao","year":"2024","journal-title":"Expert Systems with Applications"},{"key":"10.7717\/peerj-cs.3368\/ref-54","first-page":"2183","article-title":"Yedroudj-Net: an efficient CNN for spatial steganalysis","author":"Yedroudj","year":"2018"},{"key":"10.7717\/peerj-cs.3368\/ref-55","article-title":"Cross: diffusion model makes controllable, robust and secure image steganography","volume-title":"Advances in Neural Information Processing Systems 36 (NeurIPS 2023)","author":"Yu","year":"2023"},{"key":"10.7717\/peerj-cs.3368\/ref-56","first-page":"2460","article-title":"Restormer: efficient transformer for high-resolution image restoration","author":"Zamir","year":"2022"},{"key":"10.7717\/peerj-cs.3368\/ref-57","first-page":"586","article-title":"The unreasonable effectiveness of deep features as a perceptual metric","author":"Zhang","year":"2018"},{"issue":"3","key":"10.7717\/peerj-cs.3368\/ref-58","doi-asserted-by":"publisher","first-page":"117022","DOI":"10.1016\/j.image.2023.117022","article-title":"Joint adjustment image steganography networks","volume":"118","author":"Zhang","year":"2023","journal-title":"Signal Processing: Image Communication"},{"issue":"7","key":"10.7717\/peerj-cs.3368\/ref-59","doi-asserted-by":"publisher","first-page":"6927","DOI":"10.1109\/tip.2017.2662206","article-title":"Beyond the DnCNN: residual learning of deep fully convolutional network for image denoising","volume":"30","author":"Zhang","year":"2021","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.7717\/peerj-cs.3368\/ref-60","doi-asserted-by":"publisher","first-page":"104474","DOI":"10.1016\/j.jvcir.2025.104474","article-title":"Image steganography based on wavelet transform and Generative Adversarial Networks","author":"Zhao","year":"2025","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"10.7717\/peerj-cs.3368\/ref-61","first-page":"657","article-title":"Hidden: hiding data with deep networks","author":"Zhu","year":"2018"},{"key":"10.7717\/peerj-cs.3368\/ref-62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1807.11428","article-title":"Efficient feature learning and multi-size image steganalysis based on convolutional neural networks","author":"Zhu","year":"2020"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-3368.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3368.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3368.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-3368.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,17]],"date-time":"2025-11-17T08:38:36Z","timestamp":1763368716000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-3368"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,17]]},"references-count":62,"alternative-id":["10.7717\/peerj-cs.3368"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.3368","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,17]]},"article-number":"e3368"}}