{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T13:09:40Z","timestamp":1771679380631,"version":"3.50.1"},"reference-count":29,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T00:00:00Z","timestamp":1727136000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"The Henan Province Science Foundation for Youths","award":["No. 222300420058"],"award-info":[{"award-number":["No. 222300420058"]}]},{"DOI":"10.13039\/501100001809","name":"The National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62002103"],"award-info":[{"award-number":["No. 62002103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The Key Research Project for Higher Education Institutions in Henan Province","award":["No. 24A520019"],"award-info":[{"award-number":["No. 24A520019"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:sec>\n               <jats:title>Background<\/jats:title>\n               <jats:p>With the development of steganography technology, lawbreakers can implement covert communication in social networks more easily, exacerbating network security risks. Sterilization of image steganography methods can eliminate secret messages to block the transmission of illegal covert communication. However, existing methods overly rely on cover-stego image pairs and are unable to sanitize unknown image, which reduces stego image blocking rate in social networks.<\/jats:p>\n            <\/jats:sec>\n            <jats:sec>\n               <jats:title>Methods<\/jats:title>\n               <jats:p>To address the above problems, this paper proposes an effective sterilization of image steganography method using self-supervised convolutional neural network (SS-Net), which does not require any prior knowledge of image steganography schemes. SS-Net includes a purification module and a refinement module. Firstly, the pixel-shuffle down-sampling in purification module is adopted to reduce the spatial correlation of pixels in the stgeo image, and improve the learning mode from supervised learning to self-supervised learning. Secondly, centrally masked convolutions and dilated convolution residual blocks are merged to eliminate secret messages and avoid image quality degradation. Finally, a refinement module is employed to improve image texture details and boundaries.<\/jats:p>\n            <\/jats:sec>\n            <jats:sec>\n               <jats:title>Results<\/jats:title>\n               <jats:p>A series of experiments show that SS-Net from BOSSbase test sets is able to balance the destruction of secret messages with image quality, achieving 100% blocking rate of stego image. Meanwhile, our method outperforms the state-of-the-art methods in secret messages elimination ability and image quality preserving ability.<\/jats:p>\n            <\/jats:sec>","DOI":"10.7717\/peerj-cs.2330","type":"journal-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T07:30:01Z","timestamp":1727163001000},"page":"e2330","source":"Crossref","is-referenced-by-count":2,"title":["Sterilization of image steganography using self-supervised convolutional neural network"],"prefix":"10.7717","volume":"10","author":[{"given":"Jinjin","family":"Liu","sequence":"first","affiliation":[{"name":"Software College of Software, Henan Normal University, Xinxiang, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuyong","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Henan Normal University, Xinxiang, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingao","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Henan Normal University, Xinxiang, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianwei","family":"Xin","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Henan Normal University, Xinxiang, Henan, China"},{"name":"Engineering Lab of Intelligence Business & Internet of Things, Henan Normal University, Xinxiang, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keren","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Henan Normal University, Xinxiang, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanyuan","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Computer and Information Engineering, Henan Normal University, Xinxiang, Henan, China"},{"name":"Engineering Lab of Intelligence Business & Internet of Things, Henan Normal University, Xinxiang, Henan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"4443","published-online":{"date-parts":[[2024,9,24]]},"reference":[{"issue":"5","key":"10.7717\/peerj-cs.2330\/ref-1","first-page":"498","article-title":"Real time implementation of stegofirewall system","volume":"8","author":"Al-Sultan","year":"2019","journal-title":"International Journal of Computing and Digital Systems"},{"key":"10.7717\/peerj-cs.2330\/ref-2","first-page":"453","article-title":"Optimal image steganography content destruction techniques","author":"Ameen","year":"2021","journal-title":"International Journal of Computers and Communications"},{"key":"10.7717\/peerj-cs.2330\/ref-3","doi-asserted-by":"publisher","first-page":"e356","DOI":"10.7717\/peerj-cs.356","article-title":"Efficient steganalysis using convolutional auto encoder network to ensure original image quality","volume":"7","author":"Ayaluri","year":"2021","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2330\/ref-4","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1007\/978-3-642-24178-9_5","article-title":"Break our steganographic system: the ins and outs of organizing BOSS","volume-title":"Information Hiding","author":"Bas","year":"2011"},{"key":"10.7717\/peerj-cs.2330\/ref-5","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":"\u00c7ift\u00e7i","year":"2022","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2330\/ref-6","article-title":"Feature restoration and distortion metrics","author":"Chonev","year":"2011","journal-title":"Electronic Imaging"},{"key":"10.7717\/peerj-cs.2330\/ref-7","first-page":"1","article-title":"ALASKA#2: challenging academic research on steganalysis with realistic images","author":"Cogranne","year":"2020"},{"key":"10.7717\/peerj-cs.2330\/ref-8","first-page":"161","article-title":"Steganography by minimizing statistical detectability: the cases of JPEG and color images","author":"Cogranne","year":"2020"},{"key":"10.7717\/peerj-cs.2330\/ref-9","doi-asserted-by":"publisher","first-page":"264","DOI":"10.5755\/j01.itc.50.2.27461","article-title":"Nested two-layer RGB based reversible image steganography method","volume":"50","author":"Durdu","year":"2021","journal-title":"Information Technology and Control"},{"key":"10.7717\/peerj-cs.2330\/ref-10","doi-asserted-by":"publisher","first-page":"103586","DOI":"10.1016\/j.jisa.2023.103586","article-title":"Stegano-Purge: an integer wavelet transformation based adaptive universal image sterilizer for steganography removal","volume":"78","author":"Ganguly","year":"2023","journal-title":"Journal of Information Security and Applications"},{"key":"10.7717\/peerj-cs.2330\/ref-11","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1016\/j.patrec.2021.04.026","article-title":"Steganogram removal using multidirectional diffusion in fourier domain while preserving perceptual image quality","volume":"147","author":"Geetha","year":"2021","journal-title":"Pattern Recognition Letters"},{"key":"10.7717\/peerj-cs.2330\/ref-12","doi-asserted-by":"publisher","first-page":"2669","DOI":"10.1109\/TIFS.2015.2473815","article-title":"Using statistical image model for JPEG steganography: uniform embedding revisited","volume":"10","author":"Guo","year":"2015","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"10.7717\/peerj-cs.2330\/ref-13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1687-417X-2014-1","article-title":"Universal distortion function for steganography in an arbitrary domain","volume":"2014","author":"Holub","year":"2014","journal-title":"EURASIP Journal on Information Security"},{"key":"10.7717\/peerj-cs.2330\/ref-14","doi-asserted-by":"publisher","first-page":"800","DOI":"10.1049\/el:20080522","article-title":"Scope of validity of PSNR in image\/video quality assessment","volume":"44","author":"Huynh-Thu","year":"2008","journal-title":"Electronics Letters"},{"key":"10.7717\/peerj-cs.2330\/ref-15","doi-asserted-by":"publisher","first-page":"e380","DOI":"10.7717\/peerj-cs.380","article-title":"Steganography in color images with random order of pixel selection and encrypted text message embedding","volume":"7","author":"Kordov","year":"2021","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2330\/ref-16","first-page":"2124","article-title":"Noise2Void\u2014learning denoising from single noisy images","author":"Krull","year":"2018"},{"key":"10.7717\/peerj-cs.2330\/ref-17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TCSVT.2023.3295364","article-title":"Steganalysis feature selection with multidimensional evaluation & dynamic threshold allocation","author":"Ma","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"},{"key":"10.7717\/peerj-cs.2330\/ref-18","doi-asserted-by":"publisher","first-page":"118973","DOI":"10.1016\/j.ins.2023.118973","article-title":"Adaptive feature selection for image steganalysis based on classification metrics","volume":"644","author":"Ma","year":"2023","journal-title":"Information Sciences"},{"key":"10.7717\/peerj-cs.2330\/ref-19","doi-asserted-by":"publisher","first-page":"e865","DOI":"10.7717\/peerj-cs.865","article-title":"Self-supervised recurrent depth estimation with attention mechanisms","volume":"8","author":"Makarov","year":"2022","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2330\/ref-20","doi-asserted-by":"publisher","first-page":"e1157","DOI":"10.7717\/peerj-cs.1157","article-title":"An efficient and secure technique for image steganography using a hash function","volume":"8","author":"Nezami","year":"2022","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2330\/ref-21","doi-asserted-by":"publisher","first-page":"e451","DOI":"10.7717\/peerj-cs.451","article-title":"Strategy to improve the accuracy of convolutional neural network architectures applied to digital image steganalysis in the spatial domain","volume":"7","author":"Tabares-Soto","year":"2021","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2330\/ref-22","doi-asserted-by":"publisher","first-page":"e616","DOI":"10.7717\/peerj-cs.616","article-title":"Sensitivity of deep learning applied to spatial image steganalysis","volume":"7","author":"Tabares-Soto","year":"2021","journal-title":"PeerJ Computer Science"},{"key":"10.7717\/peerj-cs.2330\/ref-23","doi-asserted-by":"publisher","first-page":"2682","DOI":"10.1109\/LSP.2022.3233539","article-title":"Breaking robust data hiding in online social networks","volume":"29","author":"Wei","year":"2022","journal-title":"IEEE Signal Processing Letters"},{"key":"10.7717\/peerj-cs.2330\/ref-24","doi-asserted-by":"publisher","first-page":"107343","DOI":"10.1016\/j.sigpro.2019.107343","article-title":"Robust adaptive steganography based on generalized dither modulation and expanded embedding domain","volume":"168","author":"Yu","year":"2020","journal-title":"Signal Processing"},{"key":"10.7717\/peerj-cs.2330\/ref-25","doi-asserted-by":"publisher","first-page":"17913","DOI":"10.1007\/s11042-017-4506-3","article-title":"Dither modulation based adaptive steganography resisting jpeg compression and statistic detection","volume":"77","author":"Zhang","year":"2018","journal-title":"Multimedia Tools and Applications"},{"key":"10.7717\/peerj-cs.2330\/ref-26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Zhou","year":"2004","journal-title":"IEEE Transactions on Image Processing"},{"issue":"07","key":"10.7717\/peerj-cs.2330\/ref-27","doi-asserted-by":"crossref","first-page":"13074","DOI":"10.1609\/aaai.v34i07.7009","article-title":"When AWGN-based denoiser meets real noises","volume":"34","author":"Zhou","year":"2019","journal-title":"AAAI Conference on Artificial Intelligence"},{"key":"10.7717\/peerj-cs.2330\/ref-28","doi-asserted-by":"publisher","first-page":"605","DOI":"10.1016\/j.ins.2021.10.023","article-title":"Destroying robust steganography in online social networks","volume":"581","author":"Zhu","year":"2021","journal-title":"Information Sciences"},{"key":"10.7717\/peerj-cs.2330\/ref-29","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1109\/TCSVT.2022.3224243","article-title":"Image sanitization in online social networks: a general framework for breaking robust information hiding","volume":"33","author":"Zhu","year":"2023","journal-title":"IEEE Transactions on Circuits and Systems for Video Technology"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2330.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2330.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2330.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2330.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T07:30:22Z","timestamp":1727163022000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2330"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,24]]},"references-count":29,"alternative-id":["10.7717\/peerj-cs.2330"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2330","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,24]]},"article-number":"e2330"}}