{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T04:27:29Z","timestamp":1741753649914,"version":"3.38.0"},"reference-count":58,"publisher":"SAGE Publications","issue":"2","license":[{"start":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:00:00Z","timestamp":1700179200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Computer Security"],"published-print":{"date-parts":[[2024,4,9]]},"abstract":"<jats:p> Traditionally, the mission of intercepting malicious traffic between the Internet and the internal network of entities like organizations and corporations, is largely fulfilled by techniques such as deep packet inspection (DPI). However, steganography, the methodology of hiding secret data in seemingly benign public mediums (e.g., images), has been leveraged by advanced persistent threat (APT) groups in recent years, and is almost impossible to be detected and intercepted by traditional techniques, posing a pervasive and realistic threat to cybersecurity. Additionally, internal networks\u2019 vulnerability to steganography is further exacerbated by the connectivity and large attack surface of the Internet of Things (IoT), whose adoption and deployment are quickly expanding. To protect computer systems against malicious communications that apply steganographic methods potentially unknown to cybersecurity stakeholders, we propose StegEraser, an approach to removing the secret information embedded in public mediums by adversaries, that is fundamentally distinct from existing research which is primarily designed for known steganographic methods. Implemented for images, StegEraser injects an excessively huge amount of random binary data with a novel steganographic method into the images, by utilizing the information-merging capabilities of invertible neural networks (INNs), in order to \u201coverload\u201d adversaries\u2019 steganographic hiding capacity of images transmitted through the firewall performing DPI. In the meantime, StegEraser preserves the perceptual quality of the images. In other words, StegEraser \u201cdefeats unknown steganography with steganography\u201d. Extensive evaluation verifies that StegEraser significantly outperforms state-of-the-art (SOTA) methods in terms of removing secret information embedded with both traditional and neural network-based steganographic methods, while visually maintaining the image quality. <\/jats:p>","DOI":"10.3233\/jcs-220094","type":"journal-article","created":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T16:32:46Z","timestamp":1700238766000},"page":"117-139","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["StegEraser: Defending cybersecurity against malicious covert communications"],"prefix":"10.1177","volume":"32","author":[{"given":"Jianfeng","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}]},{"given":"Wensheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Jingdong","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Nankai University, Tianjin, China"}]}],"member":"179","published-online":{"date-parts":[[2023,11,17]]},"reference":[{"key":"ref001","doi-asserted-by":"crossref","unstructured":"E.\u00a0Agustsson and R.\u00a0Timofte, Ntire 2017 challenge on single image super-resolution: Dataset and study, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2017, pp.\u00a0126\u2013135.","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref002","doi-asserted-by":"publisher","DOI":"10.1109\/TCI.2018.2794065"},{"key":"ref003","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-51935-3_30"},{"key":"ref004","doi-asserted-by":"publisher","DOI":"10.1007\/978-81-322-2674-1_56"},{"key":"ref005","doi-asserted-by":"publisher","DOI":"10.14429\/dsj.66.10797"},{"key":"ref006","doi-asserted-by":"crossref","unstructured":"J.\u00a0Ball\u00e9, V.\u00a0Laparra and E.P.\u00a0Simoncelli, End-to-end optimization of nonlinear transform codes for perceptual quality, in: 2016 Picture Coding Symposium (PCS), IEEE, 2016, pp.\u00a01\u20135.","DOI":"10.1109\/PCS.2016.7906310"},{"key":"ref007","unstructured":"S.\u00a0Baluja, Hiding images in plain sight: Deep steganography, in: Advances in Neural Information Processing Systems (NeurIPS), 2017."},{"key":"ref008","doi-asserted-by":"publisher","DOI":"10.1016\/j.csi.2008.09.031"},{"key":"ref009","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2018.2871749"},{"key":"ref010","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2018.2802903"},{"key":"ref011","doi-asserted-by":"crossref","unstructured":"K.L.\u00a0Cheng, Y.\u00a0Xie and Q.\u00a0Chen, IICNet: A generic framework for reversible image conversion, in: IEEE\/CVF International Conference on Computer Vision (ICCV), 2021, pp.\u00a01991\u20132000.","DOI":"10.1109\/ICCV48922.2021.00200"},{"key":"ref012","unstructured":"I.\u00a0Corley, J.\u00a0Lwowski and J.\u00a0Hoffman, Destruction of image steganography using generative adversarial networks, 2019, arXiv preprint arXiv:1912.10070."},{"key":"ref013","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref014","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref015","unstructured":"L.\u00a0Dinh, D.\u00a0Krueger and Y.\u00a0Bengio, Nice: Non-linear independent components estimation, 2014, arXiv preprint arXiv:1410.8516."},{"key":"ref016","unstructured":"L.\u00a0Dinh, D.\u00a0Krueger and Y.\u00a0Bengio, NICE: Non-linear independent components estimation, in: Workshop of the International Conference on Learning Representations ICLR, 2015."},{"key":"ref017","unstructured":"L.\u00a0Dinh, J.\u00a0Sohl-Dickstein and S.\u00a0Bengio, Density estimation using real NVP, 2016, arXiv preprint arXiv:1605.08803."},{"key":"ref018","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3007577"},{"key":"ref019","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2011.2174231"},{"key":"ref020","doi-asserted-by":"crossref","unstructured":"J.\u00a0Fridrich, M.\u00a0Goljan and D.\u00a0Hogea, Steganalysis of JPEG images: Breaking the F5 algorithm, in: International Workshop on Information Hiding, Springer, 2002, pp.\u00a0310\u2013323.","DOI":"10.1007\/3-540-36415-3_20"},{"key":"ref021","unstructured":"J.\u00a0Gu, H.\u00a0Cai, C.\u00a0Dong, J.S.\u00a0Ren, R.\u00a0Timofte, Y.\u00a0Gong, S.\u00a0Lao, S.\u00a0Shi, J.\u00a0Wang, S.\u00a0Yang et al., NTIRE 2022 challenge on perceptual image quality assessment, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp.\u00a0951\u2013967."},{"key":"ref022","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2021.3053595"},{"key":"ref023","doi-asserted-by":"publisher","DOI":"10.1186\/1687-417X-2014-1"},{"key":"ref024","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2016.2598528"},{"key":"ref025","doi-asserted-by":"crossref","unstructured":"G.\u00a0Huang, Z.\u00a0Liu, L.\u00a0Van Der Maaten and K.Q.\u00a0Weinberger, Densely connected convolutional networks, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp.\u00a04700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref026","doi-asserted-by":"crossref","unstructured":"IBM, Cost of a data breach report, 2022. https:\/\/www.ibm.com\/security\/data-breach.","DOI":"10.12968\/S1353-4858(22)70049-9"},{"key":"ref027","unstructured":"J.H.\u00a0Jacobsen, A.\u00a0Smeulders and E.\u00a0Oyallon, i-RevNet: Deep invertible networks, in: International Conference on Learning Representations (ICLR), Vancouver, Canada, 2018, https:\/\/hal.archives-ouvertes.fr\/hal-01712808."},{"key":"ref028","unstructured":"D.\u00a0Jung, H.\u00a0Bae, H.S.\u00a0Choi and S.\u00a0Yoon, PixelSteganalysis: Pixel-wise hidden information removal with low visual degradation, IEEE Transactions on Dependable and Secure Computing (2021)."},{"key":"ref029","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.06.075"},{"key":"ref030","doi-asserted-by":"publisher","DOI":"10.1016\/j.jisa.2018.04.005"},{"key":"ref031","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992934"},{"key":"ref032","doi-asserted-by":"crossref","unstructured":"T.Y.\u00a0Lin, M.\u00a0Maire, S.\u00a0Belongie, J.\u00a0Hays, P.\u00a0Perona, D.\u00a0Ramanan, P.\u00a0Doll\u00e1r and C.L.\u00a0Zitnick, Microsoft COCO: Common objects in context, in: European Conference on Computer Vision (ECCV), Springer, 2014, pp.\u00a0740\u2013755.","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref033","doi-asserted-by":"crossref","unstructured":"X.\u00a0Liu, Z.\u00a0Ma, J.\u00a0Ma, J.\u00a0Zhang, G.\u00a0Schaefer and H.\u00a0Fang, Image disentanglement autoencoder for steganography without embedding, in: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp.\u00a02303\u20132312.","DOI":"10.1109\/CVPR52688.2022.00234"},{"key":"ref034","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.09.091"},{"key":"ref035","doi-asserted-by":"crossref","unstructured":"A.\u00a0Lugmayr, M.\u00a0Danelljan, L.V.\u00a0Gool and R.\u00a0Timofte, Srflow: Learning the super-resolution space with normalizing flow, in: European Conference on Computer Vision, Springer, 2020, pp.\u00a0715\u2013732.","DOI":"10.1007\/978-3-030-58558-7_42"},{"key":"ref036","doi-asserted-by":"crossref","unstructured":"J.\u00a0Ma, B.\u00a0Shang, H.\u00a0Song, Y.\u00a0Huang and P.\u00a0Fan, Reliability versus latency in IIoT visual applications: A scalable task offloading framework, IEEE Internet of Things Journal (2022).","DOI":"10.1109\/JIOT.2022.3148115"},{"key":"ref037","doi-asserted-by":"publisher","DOI":"10.3390\/math9212829"},{"key":"ref038","doi-asserted-by":"crossref","unstructured":"S.M.\u00a0Moosavi-Dezfooli, A.\u00a0Fawzi and P.\u00a0Frossard, DeepFool: A simple and accurate method to fool deep neural networks, in: IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp.\u00a02574\u20132582.","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref039","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2019.02.022"},{"key":"ref040","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2020.2976747"},{"key":"ref041","doi-asserted-by":"publisher","DOI":"10.1007\/s42979-020-00382-x"},{"key":"ref042","doi-asserted-by":"crossref","unstructured":"M.\u00a0Sharifzadeh, C.\u00a0Agarwal, M.\u00a0Aloraini and D.\u00a0Schonfeld, Convolutional neural network steganalysis\u2019s application to steganography, in: IEEE Visual Communications and Image Processing (VCIP), IEEE, 2017, pp.\u00a01\u20134.","DOI":"10.1109\/VCIP.2017.8305045"},{"key":"ref043","unstructured":"P.L.\u00a0Shrestha, M.\u00a0Hempel, T.\u00a0Ma, D.\u00a0Peng and H.\u00a0Sharif, A general attack method for steganography removal using pseudo-CFA re-interpolation, in: 2011 International Conference for Internet Technology and Secured Transactions, IEEE, 2011, pp.\u00a0454\u2013459."},{"key":"ref044","unstructured":"The MITRE Corporation, Obfuscated files or information: Steganography, 2022. https:\/\/attack.mitre.org\/techniques\/T1027\/003\/."},{"key":"ref045","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2886192"},{"key":"ref046","unstructured":"US Cybersecurity and Infrastructure Security Agency, Advanced persistent threat compromise of government agencies, critical infrastructure, and private sector organizations, 2020. https:\/\/www.cisa.gov\/uscert\/ncas\/alerts\/aa20-352a."},{"key":"ref047","unstructured":"US Cybersecurity and Infrastructure Security Agency, APT cyber tools targeting ICS\/SCADA devices, 2022. https:\/\/www.cisa.gov\/uscert\/ncas\/alerts\/aa22-103a."},{"key":"ref048","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2963764"},{"key":"ref049","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Xu, C.\u00a0Mou, Y.\u00a0Hu, J.\u00a0Xie and J.\u00a0Zhang, Robust invertible image steganography, in: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp.\u00a07875\u20137884.","DOI":"10.1109\/CVPR52688.2022.00772"},{"key":"ref050","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Xu, T.\u00a0Mauldin, Z.\u00a0Yao, S.\u00a0Pei, T.\u00a0Wei and Q.\u00a0Yang, A bus authentication and anti-probing architecture extending hardware trusted computing base off CPU chips and beyond, in: ACM\/IEEE 47th Annual International Symposium on Computer Architecture (ISCA), IEEE, 2020, pp.\u00a0749\u2013761.","DOI":"10.1109\/ISCA45697.2020.00067"},{"key":"ref051","unstructured":"C.\u00a0Zhang, P.\u00a0Benz, A.\u00a0Karjauv, G.\u00a0Sun and I.S.\u00a0Kweon, UDH: Universal deep hiding for steganography, watermarking, and light field messaging, in: Advances in Neural Information Processing Systems (NeurIPS), 2020."},{"key":"ref052","unstructured":"K.A.\u00a0Zhang, A.\u00a0Cuesta-Infante, L.\u00a0Xu and K.\u00a0Veeramachaneni, SteganoGAN: High capacity image steganography with GANs, 2019, arXiv preprint arXiv:1901.03892."},{"key":"ref053","doi-asserted-by":"crossref","unstructured":"R.\u00a0Zhang, P.\u00a0Isola, A.A.\u00a0Efros, E.\u00a0Shechtman and O.\u00a0Wang, The unreasonable effectiveness of deep features as a perceptual metric, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018, pp.\u00a0586\u2013595.","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref054","doi-asserted-by":"crossref","unstructured":"H.\u00a0Zhao, W.\u00a0Zhou, D.\u00a0Chen, T.\u00a0Wei, W.\u00a0Zhang and N.\u00a0Yu, Multi-attentional deepfake detection, in: The IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2021, pp.\u00a02185\u20132194.","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"ref055","unstructured":"Y.\u00a0Zhao, T.\u00a0Pang, C.\u00a0Du, X.\u00a0Yang, N.M.\u00a0Cheung and M.\u00a0Lin, A recipe for watermarking diffusion models, 2023, arXiv preprint arXiv:2303.10137."},{"key":"ref056","doi-asserted-by":"crossref","unstructured":"Z.\u00a0Zhou, Y.\u00a0Su, J.\u00a0Li, K.\u00a0Yu, Q.J.\u00a0Wu, Z.\u00a0Fu and Y.\u00a0Shi, Secret-to-image reversible transformation for generative steganography, IEEE Transactions on Dependable and Secure Computing (2022).","DOI":"10.1109\/TDSC.2022.3217661"},{"key":"ref057","doi-asserted-by":"crossref","unstructured":"J.\u00a0Zhu, R.\u00a0Hou, X.\u00a0Wang, W.\u00a0Wang, J.\u00a0Cao, B.\u00a0Zhao, Z.\u00a0Wang, Y.\u00a0Zhang, J.\u00a0Ying, L.\u00a0Zhang et al., Enabling rack-scale confidential computing using heterogeneous trusted execution environment, in: IEEE Symposium on Security and Privacy (SP), IEEE, 2020, pp.\u00a01450\u20131465.","DOI":"10.1109\/SP40000.2020.00054"},{"key":"ref058","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.10.023"}],"container-title":["Journal of Computer Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JCS-220094","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JCS-220094","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JCS-220094","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T08:43:00Z","timestamp":1741682580000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JCS-220094"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,17]]},"references-count":58,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2024,4,9]]}},"alternative-id":["10.3233\/JCS-220094"],"URL":"https:\/\/doi.org\/10.3233\/jcs-220094","relation":{},"ISSN":["0926-227X","1875-8924"],"issn-type":[{"type":"print","value":"0926-227X"},{"type":"electronic","value":"1875-8924"}],"subject":[],"published":{"date-parts":[[2023,11,17]]}}}