基于卷积神经网络的轻量高效图像隐写

doi:10.3969/j.issn.0255-8297.2025.01.006

应用科学学报 ›› 2025, Vol. 43 ›› Issue (1): 80-93.doi: 10.3969/j.issn.0255-8297.2025.01.006

基于卷积神经网络的轻量高效图像隐写

段新涛^1,2, 白鹿伟¹, 徐凯欧¹, 张萌¹, 保梦茹¹, 武银行¹, 秦川³

1. 河南师范大学计算机与信息工程学院, 河南新乡 453007;
2. 教育人工智能与个性化学习河南省重点实验室, 河南新乡 453007;
3. 上海理工大学光电与计算机工程学院, 上海 200093

收稿日期:2024-07-07 出版日期:2025-01-30 发布日期:2025-01-24
通信作者: 段新涛，副教授，研究方向为信息安全、图像信息隐藏。E-mail:duanxintao@htu.edu.cn E-mail:duanxintao@htu.edu.cn
基金资助:
河南省高等学校重点科研项目（No.23A520006）；河南省科技攻关计划项目（No.222102210199）资助

Lightweight and Efficient Image Steganography Based on Convolutional Neural Network

DUAN Xintao^1,2, BAI Luwei¹, XU Kaiou¹, ZHANG Meng¹, BAO Mengru¹, WU Yinhang¹, QIN Chuan³

1. College of Computer and Information Engineering, Henan Normal University, Xinxiang 453007, Henan, China;
2. Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province, Xinxiang 453007, Henan, China;
3. School of Optical-Electrical and Computer Engineering, University of Shanghai for Science and Technology, Shanghai 200093, China

Received:2024-07-07 Online:2025-01-30 Published:2025-01-24

摘要/Abstract

摘要： 基于深度学习的图像隐写方法，因存在模型参数量和计算量大等问题，而面临高参数和计算负载的挑战，为此提出了一种轻量高效的图像隐写方法。首先在编码器和解码器中引入Ghost模块，降低了编码器和解码器的参数量和计算量。其次提出了一个多尺度特征融合模块，用以捕捉多维数据中的复杂关系。最后提出了一个新颖的混合损失函数，可在保持模型不变的情况下提升图像隐写质量。实验结果表明，所提方法在256×256像素的图像上峰值信噪比达到47.59 dB。与目前最优的图像隐写方法相比，所提方法的隐写质量提升1.7 dB，参数量减少77%，计算量减少91%，在隐写质量上有较优的表现，同时模型的参数量和计算量大大降低，实现了模型的轻量高效化。

关键词: 图像隐写, 深度学习, 多尺度特征融合, 混合损失函数

Abstract: Deep learning-based image steganography often faces challenges due to the large number of model parameters and high computational demands. In response, a lightweight and efficient image steganography method is proposed. Firstly Ghost module is introduced into the encoder and decoder, which reduces the number of parameters and computational complexity. Furthermore, a multi-scale feature fusion module is designed to capture complex relationships within multidimensional data. In addition, a novel hybrid loss function is proposed, which can improve image steganography quality without modifying the model. Experimental results show that the proposed method achieves a peak signal-to-noise ratio (PSNR) of 47.59 dB on a 256×256 pixel image. Compared with the current best image steganography method, the steganography quality is improved by 1.7 dB, the number of parameters is reduced by 77%, and number of computations by 91%. These results confirm that the proposed method effectively enhances steganography quality with reduced number of parameters and computational complexity of the model, achieving a lightweight and efficient model.

Key words: image steganography, deep learning, multi-scale feature fusion, mixed loss function

中图分类号:

TN911.73

段新涛, 白鹿伟, 徐凯欧, 张萌, 保梦茹, 武银行, 秦川. 基于卷积神经网络的轻量高效图像隐写[J]. 应用科学学报, 2025, 43(1): 80-93.

DUAN Xintao, BAI Luwei, XU Kaiou, ZHANG Meng, BAO Mengru, WU Yinhang, QIN Chuan. Lightweight and Efficient Image Steganography Based on Convolutional Neural Network[J]. Journal of Applied Sciences, 2025, 43(1): 80-93.

参考文献

[1] Fridrich J, Goljan M, Du R. Detecting LSB steganography in color, and gray-scale images [J]. IEEE MultiMedia, 2001, 8(4): 22-28.
[2] Pevný T, Filler T, Bas P. Using high-dimensional image models to perform highly undetectable steganography [C]//12th Information Hiding Conference, 2010: 161-177.
[3] Baluja S. Hiding images in plain sight: deep steganography [C]//31st Annual Conference on Neural Information Processing Systems, 2017: 2070-2080.
[4] Zhang C, Benz P, Karjauv A, et al. UDH: universal deep hiding for steganography, watermarking, and light field messaging [C]//34th Conference on Neural Information Processing Systems, 2020: 10223-10234.
[5] Lu S P, Wang R, Zhong T, et al. Large-capacity image steganography based on invertible neural networks [C]//2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 10811-10820.
[6] Jing J P, Deng X, Xu M, et al. HiNet: deep image hiding by invertible network [C]//IEEE/ CVF International Conference on Computer Vision, 2021: 4713-4722.
[7] Han K, Wang Y H, Tian Q, et al. GhostNet: more features from cheap operations [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 1577-1586.
[8] Holub V, Fridrich J, Denemark T. Universal distortion function for steganography in an arbitrary domain [J]. EURASIP Journal on Information Security, 2014(1): 1-13.
[9] Filler T, Judas J, Fridrich J. Minimizing additive distortion in steganography using syndrome-trellis codes [J]. IEEE Transactions on Information Forensics and Security, 2011, 6(3): 920-935.
[10] Tang W X, Tan S Q, Li B, et al. Automatic steganographic distortion learning using a generative adversarial network [J]. IEEE Signal Processing Letters, 2017, 24(10): 1547-1551.
[11] Goodfellow I, Pouget-Abadie J, Mirza M, et al. Generative adversarial nets [C]//28th Conference on Neural Information Processing Systems, 2014: 2672-2680.
[12] Zhu J R, Kaplan R, Johnson J, et al. HiDDeN: hiding data with deep networks [C]//15th European Conference on Computer Vision, 2018: 682-697.
[13] Guan Z, Jing J, Deng X, et al. DeepMIH: deep invertible network for multiple image hiding [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023, 45(1): 372-390.
[14] Xu Y M, Mou C, Hu Y J, et al. Robust invertible image steganography [C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022: 7875-7884.
[15] Huo L, Huang L, Gan Z, et al. A fitting model with optimal multiple image hiding effect [J]. Neurocomputing, 2024, 571: 127146.
[16] Shi W Z, Caballero J, Huszár F, et al. Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network [C]//2016 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2016: 1874-1883.
[17] Zhao H S, Shi J P, Qi X J, et al. Pyramid scene parsing network [C]//2017 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2017: 6230-6239.
[18] Hou Q B, Zhang L, Cheng M M, et al. Strip pooling: rethinking spatial pooling for scene parsing [C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 4002-4011.
[19] Almohammad A, Ghinea G. Stego image quality and the reliability of PSNR [C]//2010 2nd International Conference on Image Processing Theory, Tools and Applications, 2010: 215-220.
[20] Wang Z, Bovik A C, Sheikh H R, et al. Image quality assessment: from error visibility to structural similarity [J]. IEEE Transactions on Image Processing, 2004, 13(4): 600-612.
[21] Zhang R, Isola P, Efros A A, et al. The unreasonable effectiveness of deep features as a perceptual metric [C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2018: 586-595.
[22] Deng J, Dong W, Socher R, et al. ImageNet: a large-scale hierarchical image database [C]//2009 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2009: 248-255.
[23] Lin T Y, Maire M, Belongie S, et al. Microsoft COCO: common objects in context [C]//13th European Conference on Computer Vision, 2014: 740-755.
[24] Heusel M, Ramsauer H, Unterthiner T, et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium [C]//31st Annual Conference on Neural Information Processing Systems, 2017: 6627-6638.
[25] Xu G S, Wu H Z, Shi Y Q. Structural design of convolutional neural networks for steganalysis [J]. IEEE Signal Processing Letters, 2016, 23(5): 708-712.
[26] Ye J, Ni J Q, Yi Y. Deep learning hierarchical representations for image steganalysis [J]. IEEE Transactions on Information Forensics and Security, 2017, 12(11): 2545-2557.
[27] Zhang R, Zhu F, Liu J Y, et al. Depth-wise separable convolutions and multi-level pooling for an efficient spatial CNN-based steganalysis [J]. IEEE Transactions on Information Forensics and Security, 2020, 15: 1138-1150.

基于卷积神经网络的轻量高效图像隐写

Lightweight and Efficient Image Steganography Based on Convolutional Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	王冰轮, 方巍. 基于U-Net改进的日平均2 m气温订正方法[J]. 应用科学学报, 2025, 43(1): 51-65.
[2]	贾志洋, 许兆, 冷艳梅, 闻新, 龚浩宇. 基于并行优化CBAM的轻量级故障诊断模型[J]. 应用科学学报, 2025, 43(1): 94-109.
[3]	刘珈宁, 张思佳, 张正龙, 王祎涵, 安宗诗. 基于多跳机制的扩散图谱推荐模型[J]. 应用科学学报, 2025, 43(1): 123-136.
[4]	王莹笑, 杨彦红, 谭云峰. 面向视频的人脸特征计算方法[J]. 应用科学学报, 2025, 43(1): 137-153.
[5]	胡汪鑫, 成英超, 何玉林, 黄哲学, 蔡占川. 脉冲神经网络基准测试及类脑训练框架性能评估[J]. 应用科学学报, 2025, 43(1): 169-182.
[6]	贺加贝, 周菊香, 甘健侯, 吴迪, 温晓宇. 基于多任务学习的课堂表情分类模型[J]. 应用科学学报, 2024, 42(6): 947-961.
[7]	唐意恒, 王永雄, 王哲, 张晓理. 基于子领域适应和时空学习的脑电情感识别[J]. 应用科学学报, 2024, 42(6): 1016-1026.
[8]	王子驰, 李斌, 冯国瑞, 张新鹏. 数字图像隐写分析综述[J]. 应用科学学报, 2024, 42(5): 723-732.
[9]	栗莎, 王永雄, 王哲, 陈旭, 何嘉欣. 融合局部和全局特征的铸件缺陷检测[J]. 应用科学学报, 2024, 42(5): 757-768.
[10]	王娜, 朱会娟, 宋香梅, 冯霞. 一种基于领域自适应的智能合约安全分析框架[J]. 应用科学学报, 2024, 42(4): 585-597.
[11]	苑紫烨, 邱宝林, 叶妤, 温文, 化定丽, 张玉书. 面向编码伪装的鲁棒无载体图像隐写方法[J]. 应用科学学报, 2024, 42(3): 469-485.
[12]	李子杰, 张姝, 欧阳昭相, 王俊, 吴迪. 基于场因子分解的xDeepFM推荐模型[J]. 应用科学学报, 2024, 42(3): 513-524.
[13]	沈坤烨, 周晓飞, 费晓波, 陈雨中, 张继勇, 颜成钢. 基于边缘感知深度残差网络的带钢表面缺陷检测[J]. 应用科学学报, 2023, 41(6): 978-988.
[14]	黄显培, 孟庆祥. 基于多特征卷积神经网络的哨兵二号影像地物分类[J]. 应用科学学报, 2023, 41(5): 766-776.
[15]	张春森, 朱江乐, 张学芬, 刘旭东, 史书. 融合自注意力机制与生成对抗网络的DEM空洞填充[J]. 应用科学学报, 2023, 41(5): 789-800.