{"type":"ScholarlyArticle","title":"Robust Steganography without Embedding Based on Secure Container Synthesis and Iterative Message Recovery","authors":[{"name":"Ziping Ma","slug":"ziping-ma","given":"Ziping","family":"Ma","affiliation":"Communication and Information Security Lab , Shenzhen Graduate School , Peking University"},{"name":"Yuesheng Zhu","slug":"yuesheng-zhu","given":"Yuesheng","family":"Zhu","affiliation":"Communication and Information Security Lab , Shenzhen Graduate School , Peking University"},{"name":"Guibo Luo","slug":"guibo-luo","given":"Guibo","family":"Luo","affiliation":"Communication and Information Security Lab , Shenzhen Graduate School , Peking University"},{"name":"Xiyao Liu","slug":"xiyao-liu","given":"Xiyao","family":"Liu","affiliation":"School of Computer Science and Engineering , Central South University"},{"name":"Gerald Schaefer","slug":"gerald-schaefer","given":"Gerald","family":"Schaefer","affiliation":"Department of Computer Science , Loughborough University"},{"name":"Hui Fang","slug":"hui-fang","given":"Hui","family":"Fang","affiliation":"Department of Computer Science , Loughborough University"}],"abstract":"Synthesis-based steganography without embedding (SWE) methods transform secret messages to container images synthesised by generative networks, which eliminates distortions of container images and thus can fundamentally resist typical steganalysis tools. However, existing methods suffer from weak message recovery robustness, synthesis fidelity, and the risk of message leakage. To address these problems, we propose a novel robust steganography without embedding method in this paper. In particular, we design a secure weight modulation-based generator by introducing secure factors to hide secret messages in synthesised container images. In this manner, the synthesised results are modulated by secure factors and thus the secret messages are inaccessible when using fake factors, thus reducing the risk of message leakage. Furthermore, we design a difference predictor via the reconstruction of tampered container images together with an adversarial training strategy to iteratively update the estimation of hidden messages. This ensures robustness of recovering hidden messages, while degradation of synthesis fidelity is reduced since the generator is not included in the adversarial training. Extensive experimental results convincingly demonstrate that our proposed method is effective in avoiding message leakage and superior to other existing methods in terms of recovery robustness and synthesis fidelity.","doi":"10.24963/ijcai.2023/538","url":"https://ijcai.org/proceedings/2023/538","pdf":"https://ijcai.org/proceedings/2023/0538.pdf","markdown":"https://ijcai.org/proceedings/2023/538.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/538","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":538,"pages":{"first":4838,"last":4846},"keywords":["Computer Vision: CV: Applications","Multidisciplinary Topics and Applications: MDA: Security and privacy","Computer Vision: CV: Neural generative models, auto encoders, GANs"],"videos":[],"references":[{"position":1,"raw":"[Baluja, 2017] Shumeet Baluja. Hiding images in plain sight: Deep steganography. Advances in Neural Informa- tion Processing Systems, 30:2069-2079, 2017.","title":"Hiding images in plain sight: Deep steganography","authors":"Shumeet Baluja, Baluja","year":"2017","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Baluja, 2019] Shumeet Baluja. Hiding images within im- ages. IEEE Transactions on Pattern Analysis and Machine Intelligence, 42(7):1685-1697, 2019.","title":"Hiding images within images","authors":"Baluja","year":"2019","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bandyopadhyay et al., 2008] Samir K Bandyopadhyay, Debnath Bhattacharyya, Debashis Ganguly, Swarnendu Mukherjee, and Poulami Das. A tutorial review on steganography. In International Conference on Con- temporary Computing, volume 101, pages 105-114, 2008.","title":"A tutorial review on steganography","authors":"Debnath Samir K Bandyopadhyay, Debashis Bhattacharyya, Swarnendu Ganguly, Poulami Mukherjee, Das","year":"2008","venue":"International Conference on Contemporary Computing","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Boehm, 2014] Benedikt Boehm. StegExpose -a tool for detecting LSB steganography. arXiv preprint arXiv:1410.6656, 2014.","title":"StegExpose -a tool for detecting LSB steganography","authors":"Benedikt Boehm","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Cheddad et al., 2010] Abbas Cheddad, Joan Condell, Kevin Curran, and Paul Mc Kevitt. Digital image steganography: Survey and analysis of current methods. Signal Process- ing, 90(3):727-752, 2010.","title":"Digital image steganography: Survey and analysis of current methods","authors":"Cheddad","year":"2010","venue":"Signal Processing","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Goodfellow et al., 2020] Ian Goodfellow, Jean Pouget- Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. Gen- erative adversarial networks. Communications of the ACM, 63(11):139-144, 2020.","title":"Generative adversarial networks","authors":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, Yoshua Bengio","year":"2020","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Holub and Fridrich, 2012] Vojtěch Holub and Jessica Fridrich. Designing steganographic distortion using directional filters. In IEEE International Workshop on Information Forensics and Security, pages 234-239, 2012.","title":"Designing steganographic distortion using directional filters","authors":"Fridrich Holub, Vojtěch Holub, Jessica Fridrich","year":"2012","venue":"IEEE International Workshop on Information Forensics and Security","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Holub et al., 2014] Vojtěch Holub, Jessica Fridrich, and Tomáš Denemark. Universal distortion function for steganography in an arbitrary domain. EURASIP Journal on Information Security, 2014(1):1-13, 2014.","title":"Universal distortion function for steganography in an arbitrary domain","authors":"Vojtěch Holub, Jessica Fridrich, Tomáš Denemark","year":"2014","venue":"EURASIP Journal on Information Security","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Hu et al., 2018] Donghui Hu, Liang Wang, Wenjie Jiang, Shuli Zheng, and Bin Li. A novel image steganography method via deep convolutional generative adversarial net- works. IEEE Access, 6:38303-38314, 2018.","title":"A novel image steganography method via deep convolutional generative adversarial networks","authors":"Donghui Hu, Liang Wang, Wenjie Jiang, Shuli Zheng, Bin Li","year":"2018","venue":"IEEE Access","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Karras et al., 2019] Tero Karras, Samuli Laine, and Timo Aila. A style-based generator architecture for generative adversarial networks. In IEEE/CVF Conference on Com- puter Vision and Pattern Recognition, pages 4401-4410, 2019.","title":"A style-based generator architecture for generative adversarial networks","authors":"Karras","year":"2019","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Karras et al., 2020] Tero Karras, Samuli Laine, Miika Ait- tala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. An- alyzing and improving the image quality of StyleGAN. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 8110-8119, 2020.","title":"Analyzing and improving the image quality of StyleGAN","authors":"Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, Timo Aila","year":"2020","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Kazemi et al., 2019] Hadi Kazemi, Seyed Mehdi Iran- manesh, and Nasser Nasrabadi. Style and content disen- tanglement in generative adversarial networks. In IEEE Winter Conference on Applications of Computer Vision, pages 848-856, 2019.","title":"Style and content disentanglement in generative adversarial networks","authors":"Seyed Hadi Kazemi, Nasser Mehdi Iranmanesh, Nasrabadi","year":"2019","venue":"IEEE Winter Conference on Applications of Computer Vision","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Li et al., 2020] Jun Li, Ke Niu, Liwei Liao, Lijie Wang, Jia Liu, Yu Lei, and Minqing Zhang. A generative steganog- raphy method based on WGAN-GP. In International Con- ference on Artificial Intelligence and Security, pages 386- 397, 2020.","title":"A generative steganog-raphy method based on WGAN-GP","authors":"Jun Li, Ke Niu, Liwei Liao, Lijie Wang, Jia Liu, Yu Lei, Minqing Zhang","year":"2020","venue":"International Conference on Artificial Intelligence and Security","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Liu et al., 2020] Qiang Liu, Xuyu Xiang, Jiaohua Qin, Yun Tan, Junshan Tan, and Yuanjing Luo. Coverless steganog- raphy based on image retrieval of DenseNet features and DWT sequence mapping. Knowledge-Based Systems, 192:105375, 2020.","title":"Coverless steganography based on image retrieval of DenseNet features and DWT sequence mapping","authors":"Qiang Liu, Xuyu Xiang, Jiaohua Qin, Yun Tan, Junshan Tan, Yuanjing Luo","year":"2020","venue":"Knowledge-Based Systems","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Liu et al., 2022] Xiyao Liu, Ziping Ma, Junxing Ma, Jian Zhang, Gerald Schaefer, and Hui Fang. Image disentangle- ment autoencoder for steganography without embedding. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2303-2312, June 2022.","title":"Image disentanglement autoencoder for steganography without embedding","authors":"Liu","year":"2022","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Luo et al., 2020] Yuanjing Luo, Jiaohua Qin, Xuyu Xiang, and Yun Tan. Coverless image steganography based on multi-object recognition. IEEE Transactions on Circuits and Systems for Video Technology, 2020.","title":"Coverless image steganography based on multi-object recognition","authors":"Luo","year":"2020","venue":"IEEE Transactions on Circuits and Systems for Video Technology","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Marvel et al., 1999] Lisa M Marvel, Charles G Boncelet, and Charles T Retter. Spread spectrum image steganogra- phy. IEEE Transactions on Image Processing, 8(8):1075- 1083, 1999.","title":"Spread spectrum image steganography","authors":"Lisa M Marvel, Charles G Boncelet, Charles T Retter","year":"1999","venue":"IEEE Transactions on Image Processing","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Peng et al., 2022] Fei Peng, Guanfu Chen, and Min Long. A robust coverless steganography based on generative ad- versarial networks and gradient descent approximation. IEEE Transactions on Circuits and Systems for Video Technology, 2022.","title":"A robust coverless steganography based on generative adversarial networks and gradient descent approximation","authors":"Fei Peng, Guanfu Chen, Min Long","year":"2022","venue":"IEEE Transactions on Circuits and Systems for Video Technology","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pevnỳ et al., 2010] Tomáš Pevnỳ, Tomáš Filler, and Patrick Bas. Using high-dimensional image models to perform highly undetectable steganography. In International Work- shop on Information Hiding, pages 161-177, 2010.","title":"Using high-dimensional image models to perform highly undetectable steganography","authors":"Pevnỳ","year":"2010","venue":"International Workshop on Information Hiding","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Shaoping et al., 2021] Lu Shaoping, Wang Rong, Zhong Tao, and L. Rosin Paul. Large-capacity image steganog- raphy based on invertible neural networks. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10816-10825, 2021.","title":"Large-capacity image steganography based on invertible neural networks","authors":"Lu Shaoping, Wang Rong, Zhong Tao, L Rosin Paul","year":"2021","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Sharp, 2001] Toby Sharp. An implementation of key-based digital signal steganography. In International Workshop on Information Hiding, pages 13-26, 2001.","title":"An implementation of key-based digital signal steganography","authors":"Toby Sharp","year":"2001","venue":"International Workshop on Information Hiding","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Tang et al., 2017] Weixuan Tang, Shunquan Tan, Bin Li, and Jiwu Huang. Automatic steganographic distortion learning using a generative adversarial network. IEEE Sig- nal Processing Letters, 24(10):1547-1551, 2017.","title":"Automatic steganographic distortion learning using a generative adversarial network","authors":"Tang","year":"2017","venue":"IEEE Signal Processing Letters","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Tang et al., 2020] Weixuan Tang, Bin Li, Mauro Barni, Jin Li, and Jiwu Huang. An automatic cost learning frame- work for image steganography using deep reinforcement learning. IEEE Transactions on Information Forensics and Security, 16:952-967, 2020.","title":"An automatic cost learning framework for image steganography using deep reinforcement learning","authors":"Tang","year":"2020","venue":"IEEE Transactions on Information Forensics and Security","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Van Schyndel et al., 1994] Ron G Van Schyndel, Andrew Z Tirkel, and Charles F Osborne. A digital watermark. In 1st International Conference on Image Processing, volume 2, pages 86-90, 1994.","title":"A digital watermark","authors":"Ron G Van Schyndel, Andrew Z Tirkel, Charles F Osborne","year":"1994","venue":"1st International Conference on Image Processing","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Wang et al., 2018] Zihan Wang, Neng Gao, Xin Wang, Xuexin Qu, and Linghui Li. SSteGAN: Self-learning steganography based on generative adversarial networks. In International Conference on Neural Information Pro- cessing, pages 253-264, 2018.","title":"SSteGAN: Self-learning steganography based on generative adversarial networks","authors":"Zihan Wang, Neng Gao, Xin Wang, Xuexin Qu, Linghui Li","year":"2018","venue":"International Conference on Neural Information Processing","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Wengrowski and Dana, 2019] Eric Wengrowski and Kristin Dana. Light field messaging with deep photographic steganography. In IEEE/CVF Conference on Computer Vi- sion and Pattern Recognition, pages 1515-1524, 2019.","title":"Light field messaging with deep photographic steganography","authors":"Dana ; Wengrowski, Eric Wengrowski, Kristin Dana","year":"2019","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":27,"raw":"[Westfeld and Pfitzmann, 1999] Andreas Westfeld and An- dreas Pfitzmann. Attacks on steganographic systems. In International Workshop on Information Hiding, pages 61- 76, 1999.","title":"Andreas Westfeld and Andreas Pfitzmann","authors":"Pfitzmann Westfeld","year":"1999","venue":"International Workshop on Information Hiding","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Xu et al., 2016] Guanshuo Xu, Han-Zhou Wu, and Yun- Qing Shi. Structural design of convolutional neural net- works for steganalysis. IEEE Signal Processing Letters, 23(5):708-712, 2016.","title":"Structural design of convolutional neural networks for steganalysis","authors":"Xu","year":"2016","venue":"IEEE Signal Processing Letters","doi":null,"url":null,"internal_url":null},{"position":29,"raw":"[Xu et al., 2022] Youmin Xu, Chong Mou, Yujie Hu, Jingfen Xie, and Jian Zhang. Robust invertible image steganogra- phy. In IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7875-7884, 2022.","title":"Robust invertible image steganography","authors":"Youmin Xu, Chong Mou, Yujie Hu, Jingfen Xie, Jian Zhang","year":"2022","venue":"IEEE/CVF Conference on Computer Vision and Pattern Recognition","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Ye et al., 2017] Jian Ye, Jiangqun Ni, and Yang Yi. Deep learning hierarchical representations for image steganaly- sis. IEEE Transactions on Information Forensics and Se- curity, 12(11):2545-2557, 2017.","title":"Deep learning hierarchical representations for image steganalysis","authors":"Jian Ye, Jiangqun Ni, Yang Yi","year":"2017","venue":"IEEE Transactions on Information Forensics and Security","doi":null,"url":null,"internal_url":null},{"position":31,"raw":"[You et al., 2022] Zhengxin You, Qichao Ying, Sheng Li, Zhenxing Qian, and Xinpeng Zhang. Image generation network for covert transmission in online social network. In 30th ACM International Conference on Multimedia, pages 2834-2842, 2022.","title":"Image generation network for covert transmission in online social network","authors":"Zhengxin You, Qichao Ying, Sheng Li, Zhenxing Qian, Xinpeng Zhang","year":"2022","venue":"30th ACM International Conference on Multimedia","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Yu et al., 2015] Fisher Yu, Ari Seff, Yinda Zhang, Shu- ran Song, Thomas Funkhouser, and Jianxiong Xiao. LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365, 2015.","title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","authors":"Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, Jianxiong Xiao","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Yu et al., 2021a] Cong Yu, Donghui Hu, Shuli Zheng, Wen- jie Jiang, Meng Li, and Zhong-qiu Zhao. An im- proved steganography without embedding based on atten- tion GAN. Peer-to-Peer Networking and Applications, 14(3):1446-1457, 2021.","title":"An improved steganography without embedding based on attention GAN","authors":"Yu","year":"2021","venue":"Peer-to-Peer Networking and Applications","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Yu et al., 2021b] Ning Yu, Guilin Liu, Aysegul Dundar, An- drew Tao, Bryan Catanzaro, Larry S Davis, and Mario Fritz. Dual contrastive loss and attention for GANs. In IEEE/CVF International Conference on Computer Vision, pages 6731-6742, 2021.","title":"Dual contrastive loss and attention for GANs","authors":"Yu","year":"2021","venue":"IEEE/CVF International Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zheng et al., 2017] Shuli Zheng, Liang Wang, Baohong Ling, and Donghui Hu. Coverless information hiding based on robust image hashing. In International Confer- ence on Intelligent Computing, pages 536-547, 2017.","title":"Coverless information hiding based on robust image hashing","authors":"Shuli Zheng, Liang Wang, Baohong Ling, Donghui Hu","year":"2017","venue":"International Conference on Intelligent Computing","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhou et al., 2015] Zhili Zhou, Huiyu Sun, Rohan Harit, Xi- anyi Chen, and Xingming Sun. Coverless image steganog- raphy without embedding. In International Conference on Cloud Computing and Security, pages 123-132, 2015.","title":"Coverless image steganography without embedding","authors":"Zhili Zhou, Huiyu Sun, Rohan Harit, Xianyi Chen, Xingming Sun","year":"2015","venue":"International Conference on Cloud Computing and Security","doi":null,"url":null,"internal_url":null},{"position":37,"raw":"[Zhu et al., 2018] Jiren Zhu, Russell Kaplan, Justin Johnson, and Li Fei-Fei. HiDDeN: Hiding data with deep networks. In European Conference on Computer Vision, pages 657- 672, 2018.","title":"HiDDeN: Hiding data with deep networks","authors":"Zhu","year":"2018","venue":"European Conference on Computer Vision","doi":null,"url":null,"internal_url":null},{"position":38,"raw":"[Zou et al., 2022] Liming Zou, Jing Li, Wenbo Wan, QM Jonathan Wu, and Jiande Sun. Robust coverless image steganography based on neglected coverless image dataset construction. IEEE Transactions on Multimedia, 2022.","title":"Robust coverless image steganography based on neglected coverless image dataset construction","authors":"Liming Zou, Jing Li, Wenbo Wan, Jonathan Wu, Jiande Sun","year":"2022","venue":"IEEE Transactions on Multimedia","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}