Spatial Color Image Steganalysis Based on Central Difference Convolution and Attention
Author:
Affiliation:

Clc Number:

TP391

  • Article
  • | |
  • Metrics
  • |
  • Reference [45]
  • |
  • Related
  • | | |
  • Comments
    Abstract:

    Currently, most of the published image steganalysis methods are designed for grayscale images, which cannot effectively detect color images widely used in social media. To solve this problem, this study proposes a color image steganalysis method based on central difference convolution and attention enhancement. The proposed method first designs a backbone flow consisting of three stages: preprocessing, feature extraction, and feature classification. In the preprocessing stage, the input color image is color channel-separated, and the residual images after SRM filtering are concatenated through each channel. In the feature extraction stage, the study constructs three convolutional blocks based on central difference convolution to extract deeper steganalysis feature maps. In the classification stage, the study uses global covariance pooling and two fully connected layers with dropout operation to classify the cover and stego images. Additionally, to further enhance the feature expression ability of the backbone flow at different stages, it introduces a residual spatial attention enhancement module and a channel attention enhancement module at the early and late stages of the backbone flow, respectively. Specifically, the residual spatial attention enhancement module first uses Gabor filter kernels to perform channel-separated convolution on the input image and then obtains the effective information of the residual feature map through the spatial attention mechanism. The channel attention enhancement module enhances the final feature classification ability of the model by obtaining the dependence relationship between channels. A large number of comparative experiments have been conducted, and the results show that the proposed method can significantly improve the detection performance of color image steganography and achieve the best results currently. In addition, the study also conducts corresponding ablation experiments to verify the rationality of the proposed network architecture.

    Reference
    [1] 黄殿中, 张静飞, 张茹, 李鹏超, 郭云彪. 基于大数据环境的多模态信息隐藏新体系. 电子学报, 2017, 45(2): 477–484.
    Huang DZ, Zhang JF, Zhang R, Li PC, Guo YB. New system of multi-modal information hiding based on big data environment. Acta Electronica Sinica, 2017, 45(2): 477–484 (in Chinese with English abstract).
    [2] Holub V, Fridrich J, Denemark T. Universal distortion function for steganography in an arbitrary domain. EURASIP Journal on Information Security, 2014, 2014(1): 1.
    [3] Li B, Wang M, Huang JW, Li XL. A new cost function for spatial image steganography. In: Proc. of the 2014 IEEE Conf. on Image Processing. Paris: IEEE, 2014. 4206–4210.
    [4] Liu ML, Fan HY, Wei KK, Luo WQ, Lu W. Adversarial robust image steganography against lossy JPEG compression. Signal Processing, 2022, 200: 108668.
    [5] Wang YF, Zhang WM, Li WX, Yu XZ, Yu NH. Non-additive cost functions for color image steganography based on inter-channel correlations and differences. IEEE Trans. on Information Forensics and Security, 2020, 15: 2081–2095.
    [6] Liao X, Yu YB, Li B, Li ZP, Qin Z. A new payload partition strategy in color image steganography. IEEE Trans. on Circuits and Systems for Video Technology, 2020, 30(3): 685–696.
    [7] Tang WX, Li B, Luo WQ, Huang JW. Clustering steganographic modification directions for color components. IEEE Signal Processing Letters, 2016, 23(2): 197–201.
    [8] Fridrich J, Kodovsky J. Rich models for steganalysis of digital images. IEEE Trans. on Information Forensics and Security, 2012, 7(3): 868–882.
    [9] Tan SQ, Li B. Stacked convolutional auto-encoders for steganalysis of digital images. In: Proc. of the 2014 Signal and Information Processing Association Annual Summit and Conf. Siem Reap: IEEE, 2014. 1-4.
    [10] Xu GS, Wu HZ, Shi YQ. Structural design of convolutional neural networks for steganalysis. IEEE Signal Processing Letters, 2016, 23(5): 708–712.
    [11] Ye J, Ni JQ, Yi Y. Deep learning hierarchical representations for image steganalysis. IEEE Trans. on Information Forensics and Security, 2017, 12(11): 2545–2557.
    [12] Boroumand M, Chen M, Fridrich J. Deep residual network for steganalysis of digital images. IEEE Trans. on Information Forensics and Security, 2019, 14(5): 1181–1193.
    [13] Deng XQ, Chen BL, Luo WQ, Luo D. Fast and effective global covariance pooling network for image steganalysis. In: Proc. of the 2019 ACM Workshop on Information Hiding and Multimedia Security. Paris: ACM, 2019. 230–234.
    [14] Zhang R, Zhu F, Liu JY, Liu GS. Depth-wise separable convolutions and multi-level pooling for an efficient spatial CNN-based steganalysis. IEEE Trans. on Information Forensics and Security, 2020, 15: 1138–1150.
    [15] 沈军, 廖鑫, 秦拯, 刘绪崇. 基于卷积神经网络的低嵌入率空域隐写分析. 软件学报, 2021, 32(9): 2901–2915. http://www.jos.org.cn/1000-9825/5980.htm
    Shen J, Liao X, Qin Z, Liu XC. Spatial steganalysis of low embedding rate based on convolutional neural network. Ruan Jian Xue Bao/Journal of Software, 2021, 32(9): 2901–2915 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/5980.htm
    [16] 李大秋, 付章杰, 程旭, 宋晨, 孙星明. 基于少样本学习的通用隐写分析方法. 软件学报, 2022, 33(10): 3874–3890. http://www.jos.org.cn/1000-9825/6358.htm
    Li DQ, Fu ZJ, Cheng X, Song C, Sun XM. Universal steganalysis based on few-shot learning. Ruan Jian Xue Bao/Journal of Software, 2022, 33(10): 3874–3890 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6358.htm
    [17] 翟黎明, 嘉炬, 任魏翔, 徐一波, 王丽娜. 深度学习在图像隐写术与隐写分析领域中的研究进展. 信息安全学报, 2018, 3(6): 2–12.
    Zhai LM, Jia J, Ren WX, Xu YB, Wang LN. Recent advances in deep learning for image steganography and steganalysis. Journal of Cyber Security, 2018, 3(6): 2-12 (in Chinese with English abstract).
    [18] 陈君夫, 付章杰, 张卫明, 程旭, 孙星明. 基于深度学习的图像隐写分析综述. 软件学报, 2021, 32(2): 551–578. http://www.jos.org.cn/1000-9825/6135.htm
    Chen JF, Fu ZJ, Zhang WM, Cheng X, Sun XM. Review of image steganalysis based on deep learning. Ruan Jian Xue Bao/Journal of Software, 2021, 32(2): 551–578 (in Chinese with English abstract). http://www.jos.org.cn/1000-9825/6135.htm
    [19] Holub V, Fridrich J. Random projections of residuals for digital image steganalysis. IEEE Trans. on Information Forensics and Security, 2013, 8(12): 1996–2006.
    [20] Goljan M, Fridrich J, Cogranne R. Rich model for steganalysis of color images. In: Proc. of the 2014 IEEE Int’l Workshop on Information Forensics and Security. Atlanta: IEEE, 2014. 185–190.
    [21] Bas P, Filler T, Pevný T. “Break our steganographic system”: The ins and outs of organizing BOSS. In: Proc. of the 13th Int’l Workshop on Information Hiding. Prague: Springer, 2011. 59-70.
    [22] Abdulrahman H, Chaumont M, Montesinos P, Magnier B. Color image steganalysis based on steerable gaussian filters bank. In: Proc. of the 4th ACM Workshop on Information Hiding and Multimedia Security. Vigo Galicia: ACM, 2016. 109–114.
    [23] Zeng JS, Tan SQ, Liu GQ, Li B, Huang JW. WISERNet: Wider separate-then-reunion network for steganalysis of color images. IEEE Trans. on Information Forensics and Security, 2019, 14(10): 2735–2748.
    [24] Wei KK, Luo WQ, Tan SQ, Huang JW. Universal deep network for steganalysis of color image based on channel representation. IEEE Trans. on Information Forensics and Security, 2022, 17: 3022–3036.
    [25] Yu ZT, Zhao CX, Wang ZZ, Qin YX, Su Z, Li XB, Zhou F, Zhao GY. Searching central difference convolutional networks for face anti-spoofing. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 5295–5305.
    [26] Yu ZT, Wan J, Qin YX, Li XB, Li SZ, Zhao GY. NAS-FAS: Static-dynamic central difference network search for face anti-spoofing. IEEE Trans. on Pattern Analysis and Machine Intelligence, 2021, 43(9): 3005–3023.
    [27] Li PH, Xie JT, Wang QL, Gao ZL. Towards faster training of global covariance pooling networks by iterative matrix square root normalization. In: Proc. of the 2018 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Salt Lake City: IEEE, 2018. 947–955.
    [28] Song XF, Liu FL, Yang CF, Luo XY, Zhang Y. Steganalysis of adaptive JPEG steganography using 2D Gabor filters. In: Proc. of the 3rd ACM Workshop on Information Hiding and Multimedia Security. Portland: ACM, 2015. 15–23.
    [29] Woo S, Park J, Lee JY, Kweon IS. CBAM: Convolutional block attention module. In: Proc. of the 15th European Conf. on Computer Vision. Munich: Springer, 2018. 3–19.
    [30] Fu J, Liu J, Tian HJ, Li Y, Bao YJ, Fang ZW, Lu HQ. Dual attention network for scene segmentation. In: Proc. of the 2019 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019. 3141–3149.
    [31] Wang QL, Wu BG, Zhu PF, Li PH, Zuo WM, Hu QH. ECA-Net: Efficient channel attention for deep convolutional neural networks. In: Proc. of the 2020 IEEE/CVF Conf. on Computer Vision and Pattern Recognition. Seattle: IEEE, 2020. 11531–11539.
    [32] Cogranne R, Giboulot Q, Bas P. The ALASKA steganalysis challenge: A first step towards steganalysis. In: Proc. of the 2019 ACM Workshop Information Hiding and Multimedia Security. Paris: ACM, 2019. 125–137.
    [33] He KM, Zhang XY, Ren SQ, Sun J. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In: Proc. of the 2015 IEEE Int’l Conf. on Computer Vision. Santiago: IEEE, 2015. 1026–1034.
    [34] Bengio Y, Louradour J, Collobert R, Weston J. Curriculum learning. In: Proc. of the 26th Annual Int’l Conf. on Machine Learning. Montreal: ACM, 2009. 41–48.
    [35] Yousfi Y, Butora J, Fridrich J, Giboulot Q. Breaking ALASKA: Color separation for steganalysis in JPEG domain. In: Proc. of the 2019 ACM Workshop Information Hiding Multimedia Security. Paris: ACM, 2019. 138–149.
    [36] Yousfi Y, Butora J, Khvedchenya E, Fridrich J. ImageNet pre-trained CNNs for JPEG steganalysis. In: Proc. of the 2020 IEEE Int’l Workshop Information Forensics Security. New York: IEEE, 2020. 1–6.
    [37] Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai XH, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S, Uszkoreit J, Houlsby N. An image is worth 16x16 words: Transformers for image recognition at scale. In: Proc. of the 9th Int’l Conf. on Learning Representations. OpenReview.net, 2021.
    [38] Tsang CF, Fridrich J. Steganalyzing images of arbitrary size with CNNs. Electronic Imaging, 2018, 30(7): 121-1-121-8.
    [39] You WK, Zhang H, Zhao XF. A siamese CNN for image steganalysis. IEEE Trans. on Information Forensics and Security, 2021, 16: 291–306.
    [40] Li H, Wang JW, Xiong N, Zhang Y, Vasilakos AV, Luo XY. A siamese inverted residuals network image steganalysis scheme based on deep learning. ACM Trans. on Multimedia Computing, Communications, and Applications, 2023, 19(6): 214.
    Related
    Cited by
    Comments
    Comments
    分享到微博
    Submit
Get Citation

魏康康,骆伟祺,刘明林.基于中心差分卷积和注意力的空域彩色图像隐写分析.软件学报,2024,35(12):5671-5686

Copy
Share
Article Metrics
  • Abstract:744
  • PDF: 2421
  • HTML: 397
  • Cited by: 0
History
  • Received:April 08,2023
  • Revised:July 06,2023
  • Online: January 24,2024
  • Published: December 06,2024
You are the first2044654Visitors
Copyright: Institute of Software, Chinese Academy of Sciences Beijing ICP No. 05046678-4
Address:4# South Fourth Street, Zhong Guan Cun, Beijing 100190,Postal Code:100190
Phone:010-62562563 Fax:010-62562533 Email:jos@iscas.ac.cn
Technical Support:Beijing Qinyun Technology Development Co., Ltd.

Beijing Public Network Security No. 11040202500063