Deep compressive sensing network for IoT images and its chaotic encryption protection method

doi:10.11772/j.issn.1001-9081.2025020144

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (1): 144-151.DOI: 10.11772/j.issn.1001-9081.2025020144

• Cyber security • Previous Articles Next Articles

Deep compressive sensing network for IoT images and its chaotic encryption protection method

Yingjie MA, Jingying QIN(), Geng ZHAO, Jing XIAO

Department of Electronic and Communication Engineering，Beijing Electronic Science and Technology Institute，Beijing 100070，China

Received:2025-02-18 Revised:2025-05-25 Accepted:2025-05-28 Online:2026-01-10 Published:2026-01-10
Contact: Jingying QIN
About author:MA Yingjie， born in 1979， Ph. D.， associate professor. Her research interests include chaotic secure communication.
ZHAO Geng， born in 1964， Ph. D.， professor. His research interests include chaotic cryptography.
XIAO Jing， born in 1998， Ph. D. candidate. His research interests include model security.
Supported by:
National Natural Science Foundation of China(62441208);Fundamental Research Funds for the Central Universities(3282024060)

面向物联网图像的深度压缩感知网络及其混沌加密保护方法

马英杰, 覃晶滢(), 赵耿, 肖靖

北京电子科技学院电子与通信工程系，北京 100070

通讯作者: 覃晶滢
作者简介:马英杰（1979—），女，吉林通化人，副教授，博士，主要研究方向：混沌保密通信
赵耿（1964—），男，四川苍溪人，教授，博士，主要研究方向：混沌密码
肖靖（1998—），男，湖南长沙人，博士研究生，主要研究方向：模型安全。
基金资助:
国家自然科学基金资助项目(62441208);中央高校基本科研业务费专项资金资助项目(3282024060)

Abstract

Abstract:

Concerning the problem that the transmission and storage of massive redundant image data in Internet of Things （IoT） lead to high resource consumption and potential privacy leakage， a Deep Compressive Sensing （DCS） network for IoT images and its chaotic encryption protection method were proposed. Firstly， an improved DCS network was proposed to achieve high-quality image compression and reconstruction. In this network， residual blocks in conventional deep reconstruction network were modified using a channel attention mechanism， and a parallel fusion design integrating multi-scale branches and a fusion module was adopted， thereby improving the reconstruction performance of traditional deep reconstruction network based on residual stacking in convolutional layers. Secondly， a multi-cavity chaotic system was proposed to realize spherical cavity expansion in the X， Y， or Z direction — either in one direction or both directions — through spherical coordinate transformation and two sets of parity-controlled step functions. This system has chaotic properties and randomness， making it suitable for image encryption. Finally， based on the proposed DCS network and the multi-cavity chaotic system， encryption and decryption for DCS measured images was designed using chaotic index scrambling and diffusion， and detailed security analysis was conducted， thereby guaranteeing the security of image transmission. Experimental results show that compared with the classical DCS method CSNet+， the proposed network achieves an average increase of 0.606 dB （0.25-1.42 dB） in Peak Signal-to-Noise Ratio （PSNR） and an average 1.11 percentage point （0.69-2.17 percentage point） improvement in Structural Similarity Index Measure （SSIM）.

Key words: Deep Compressive Sensing (DCS), attention mechanism, multi-scale, multi-cavity chaotic system, chaotic encryption

摘要：

针对物联网大量冗余图像数据的传输和存储带来的高资源需求和隐私泄露隐患问题，提出一种面向物联网图像的深度压缩感知（DCS）网络及其混沌加密保护方法。首先，提出一种改进的DCS网络用于图像的高质量压缩重构，该网络通过通道注意力机制改进传统深度重构网络中的残差块，并结合多尺度分支与融合模块进行并行融合设计，改进了传统的基于卷积层残差堆叠的深度重构网络的重构性能；其次，提出一种腔体混沌系统通过球坐标变换和2组奇偶控制的阶梯函数实现球形腔体在X、Y、Z任意单方向或者双方向的腔体拓展，具有较好的混沌特性和随机性，可有效用于图像加密；最后，结合提出的DCS网络和多腔体混沌系统，基于混沌索引置乱和扩散方法对DCS的测量图像进行加解密设计，并进行详细的安全性分析，从而保证图像传输的安全性。实验结果表明，相较于DCS的经典方法CSNet+，该DCS网络重构图像的峰值信噪比（PSNR）平均增长了0.606 dB（0.25~1.42 dB），结构相似性指数（SSIM）平均提高了1.11个百分点（0.69~2.17个百分点）。

关键词: 深度压缩感知, 注意力机制, 多尺度, 多腔体混沌系统, 混沌加密

CLC Number:

TP309.7

Yingjie MA, Jingying QIN, Geng ZHAO, Jing XIAO. Deep compressive sensing network for IoT images and its chaotic encryption protection method[J]. Journal of Computer Applications, 2026, 46(1): 144-151.

马英杰, 覃晶滢, 赵耿, 肖靖. 面向物联网图像的深度压缩感知网络及其混沌加密保护方法[J]. 《计算机应用》唯一官方网站, 2026, 46(1): 144-151.

Figures/Tables 19

References 31

[1]	LV T， LIN Z， HUANG P， et al. Optimization of the energy-efficient relay-based massive IoT network ［J］. IEEE Internet of Things Journal， 2018， 5（4）： 3043-3058.
[2]	LI X， XU L D. A review of Internet of Things — resource allocation ［J］. IEEE Internet of Things Journal， 2021， 8（1）： 8657-8666.
[3]	LI S， XU L D， WANG X. Compressed sensing signal and data acquisition in wireless sensor networks and Internet of Things ［J］. IEEE Transactions on Industrial Informatics， 2013， 9（4）： 2177-2186.
[4]	LI Z， HUANG H， MISRA S. Compressed sensing via dictionary learning and approximate message passing for multimedia Internet of Things ［J］. IEEE Internet of Things Journal， 2017， 4（2）： 502-512.
[5]	YAMAÇ M， AHISHALI M， PASSALIS N， et al. Multi-level reversible data anonymization via compressive sensing and data hiding ［J］. IEEE Transactions on Information Forensics and Security， 2021， 16： 1014-1028.
[6]	SUO Z， XIA C， JIANG D， et al. Multitiered reversible data privacy protection scheme for IoT based on compression sensing and digital watermarking ［J］. IEEE Internet of Things Journal， 2024， 11（7）： 11524-11539.
[7]	SHEN M， GAN H， NING C， et al. TransCS： a Transformer-based hybrid architecture for image compressed sensing ［J］. IEEE Transactions on Image Processing， 2022， 31： 6991-7005.
[8]	ZHANG J， GHANEM B. ISTA-Net： interpretable optimization-inspired deep network for image compressive sensing ［C］// Proceedings of the 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE， 2018： 1828-1837.
[9]	SHI W， JIANG F， LIU S， et al. Image compressed sensing using convolutional neural network ［J］. IEEE Transactions on Image Processing， 2020， 29： 375-388.
[10]	YOU D， XIE J， ZHANG J. ISTA-Net⁺⁺： flexible deep unfolding network for compressive sensing ［C］// Proceedings of the 2021 IEEE International Conference on Multimedia and Expo. Piscataway： IEEE， 2021： 1-6.
[11]	ZHANG M， ZHANG H， YUAN D， et al. Learning-based sparse data reconstruction for compressed data aggregation in IoT networks ［J］. IEEE Internet of Things Journal， 2021， 8（14）： 11732-11742.
[12]	ZHANG M， ZHANG H， ZHANG C， et al. Communication-efficient quantized deep compressed sensing for edge-cloud collaborative industrial IoT networks ［J］. IEEE Transactions on Industrial Informatics， 2023， 19（5）： 6613-6623.
[13]	CHANG Q， TAO D， WANG J， et al. Deep compressed sensing based data imputation for urban environmental monitoring ［J］. ACM Transactions on Sensor Networks， 2024， 20（1）： No.17.
[14]	CHEN B， TANG D， HUANG Y， et al. CMCL： cross-modal compressive learning for resource-constrained intelligent IoT systems ［J］. IEEE Internet of Things Journal， 2024， 11（15）： 25534-25542.
[15]	WANG M， WANG X， WANG C， et al. Spatiotemporal chaos in cross coupled map lattice with dynamic coupling coefficient and its application in bit-level color image encryption ［J］. Chaos， Solitons and Fractals， 2020， 139： No.110028.
[16]	CHEN D， SUN Z， MA X， et al. Circuit implementation and model of a new multiscroll chaotic system ［J］. International Journal of Circuit Theory and Applications， 2014， 42（4）： 407-424.
[17]	BOUALLEGUE K. Generation of multi-scroll chaotic attractors from fractal and multi-fractal processes ［C］// Proceedings of the 4th International Workshop on Chaos-Fractals Theories and Applications. Piscataway： IEEE， 2011： 398-402.
[18]	HE S， BANERJEE S. Multicavity formations and complexity modulation in a hyperchaotic discrete system ［J］. Physica A： Statistical Mechanics and its Applications， 2018， 490： 366-377.
[19]	摆玉龙，杨阳，唐丽红.一个新多涡卷混沌系统的设计及在图像加密中的应用［J］.电子与信息学报， 2021， 43（2）： 436-444.
	BAI Y L， YANG Y， TANG L H. Design of a multi-scroll chaotic system and its application to image encryption ［J］. Journal of Electronics and Information Technology， 2021， 43（2）： 436-444.
[20]	徐昌彪，黎金龙，许浩南.一种基于Logistic电平脉冲的多涡卷系统及其图像加密应用［J］.电子与信息学报， 2022， 44（12）： 4328-4336.
	XU C B， LI J L， XU H N. A multi-scroll system and its application for image encryption based on logistic level pulse ［J］. Journal of Electronics and Information Technology， 2022， 44（12）： 4328-4336.
[21]	刘思洋，安新磊，施倩倩，等.一类多涡卷Chua系统及其在图像加密中的应用［J］.复杂系统与复杂性科学， 2024， 21（3）： 85-92.
	LIU S Y， AN X L， SHI Q Q， et al. A multi-scroll Chua system and its application in image encryption ［J］. Complex Systems and Complexity Science， 2024， 21（3）： 85-92.
[22]	赵耿，马英杰.混沌应用密码学［M］.北京：科学出版社， 2021.
	ZHAO G， MA Y J. Chaos applied cryptography ［M］. Beijing： Science Press， 2021.
[23]	ZHANG Y， TANG Y. A plaintext-related image encryption algorithm based on chaos ［J］. Multimedia Tools and Applications， 2018， 77（6）： 6647-6669.
[24]	LIU W， SUN K， HE S. SF-SIMM high-dimensional hyperchaotic map and its performance analysis ［J］. Nonlinear Dynamics， 2017， 89（4）： 2521-2532.
[25]	XIAO Y， SUN K， HE S. Constructing chaotic map with multi-cavity ［J］. European Physical Journal Plus， 2020， 135： No.21.
[26]	WU C， SUN K， XIAO Y. A hyperchaotic map with multi-elliptic cavities based on modulation and coupling ［J］. The European Physical Journal Special Topics， 2021， 230： 2011-2020.
[27]	MUN S， FOWLER J E. Block compressed sensing of images using directional transforms ［C］// Proceedings of the 16th IEEE International Conference on Image Processing. Piscataway： IEEE， 2009： 3021-3024.
[28]	CHEN C， TRAMEL E W， FOWLER J E. Compressed-sensing recovery of images and video using multihypothesis predictions ［C］// Proceedings of the 45th Asilomar Conference on Signals， Systems and Computers. Piscataway： IEEE， 2011： 1193-1198.
[29]	马英杰，肖靖，赵耿，等.可控网格多涡卷混沌系统族及其硬件电路实现［J］.计算机应用， 2023， 43（3）： 956-961.
	MA Y J， XIAO J， ZHAO G， et al. Controllable grid multi-scroll chaotic system family and its hardware circuit implementation ［J］. Journal of Computer Applications， 2023， 43（3）： 956-961.
[30]	潘涛，佟晓筠，张淼，等.基于压缩感知和超混沌系统的图像压缩加密方法［J］.计算机科学， 2023， 50（6A）： No.220200121.
	PAN T， TONG X J， ZHANG M， et al. Image compression and encryption method based on compressed sensing and hyperchaotic system ［J］. Computer Science， 2023， 50（6A）： No.220200121.
[31]	范海菊，岳爽，窦育强，等.基于新型混沌系统和二进制块压缩感知的图像加密算法［J/OL］.计算机科学［2025-05-07］. .
	FAN H J， YUE S， DOU Y Q， et al. Image encryption algorithm based on a novel chaotic system and binary block compressed sensing ［J/OL］. Computer Science ［2025-05-07］. .

方法	不同采样比r下的PSNR					平均PSNR
方法	r=0.1	r=0.2	r=0.3	r=0.4	r=0.5	平均PSNR
DWT	23.46	27.26	29.23	30.72	32.17	28.568
MH	25.16	28.09	29.85	31.35	32.86	29.462
GSR	25.91	29.18	31.33	33.20	34.94	30.912
CSNet+	28.53	31.05	33.08	34.91	36.68	32.850
本文方法	28.78	32.47	33.42	35.51	37.10	33.456

方法	不同采样比r下的PSNR					平均PSNR
方法	r=0.1	r=0.2	r=0.3	r=0.4	r=0.5	平均PSNR
DWT	23.46	27.26	29.23	30.72	32.17	28.568
MH	25.16	28.09	29.85	31.35	32.86	29.462
GSR	25.91	29.18	31.33	33.20	34.94	30.912
CSNet+	28.53	31.05	33.08	34.91	36.68	32.850
本文方法	28.78	32.47	33.42	35.51	37.10	33.456

方法	不同采样比r下的SSIM					平均SSIM
方法	r=0.1	r=0.2	r=0.3	r=0.4	r=0.5	平均SSIM
DWT	0.634 3	0.751 6	0.810 8	0.852 4	0.886 2	0.787 0
MH	0.667 3	0.774 6	0.830 7	0.869 5	0.901 2	0.808 6
GSR	0.707 1	0.815 6	0.872 3	0.909 6	0.935 9	0.848 1
CSNet+	0.783 4	0.872 1	0.917 1	0.944 3	0.961 8	0.895 7
本文方法	0.805 1	0.883 4	0.924 8	0.952 1	0.968 7	0.906 8

方法	不同采样比r下的SSIM					平均SSIM
方法	r=0.1	r=0.2	r=0.3	r=0.4	r=0.5	平均SSIM
DWT	0.634 3	0.751 6	0.810 8	0.852 4	0.886 2	0.787 0
MH	0.667 3	0.774 6	0.830 7	0.869 5	0.901 2	0.808 6
GSR	0.707 1	0.815 6	0.872 3	0.909 6	0.935 9	0.848 1
CSNet+	0.783 4	0.872 1	0.917 1	0.944 3	0.961 8	0.895 7
本文方法	0.805 1	0.883 4	0.924 8	0.952 1	0.968 7	0.906 8

统计检验	P-value	结果
Frequency	0.678 686	Pass
BlockFrequency	0.816 537	Pass
CumulativeSums1	0.657 933	Pass
CumulativeSums2	0.867 692	Pass
Runs	0.129 620	Pass
LongestRun	0.383 827	Pass
Rank	0.678 686	Pass
FFT	0.304 126	Pass
NonOverlappingTemplate	0.719 747	Pass
OverlappingTemplate	0.171 876	Pass
Universal	0.202 268	Pass
ApproximateEntropy	0.304 126	Pass
RandomExcursions	0.657 933	Pass
RandomExcursionsVariant	0.319 084	Pass
Serial 1	0.699 313	Pass
Serial 2	0.350 485	Pass
LinearComplexity	0.699 313	Pass

Deep compressive sensing network for IoT images and its chaotic encryption protection method

面向物联网图像的深度压缩感知网络及其混沌加密保护方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 19

References 31

Related Articles 15

Recommended Articles

Metrics

采样比	SSIM	PSNR/dB
0.1	0.825 7	29.47
0.2	0.904 9	32.54
0.3	0.940 1	34.71
0.4	0.961 4	36.43
0.5	0.970 8	38.21

方法	PSNR/dB	加密图像信息熵	加密图像相邻像素相关性
方法	PSNR/dB	加密图像信息熵	水平方向	垂直方向	对角线方向
文献［30］方法	30.64	7.994 8	-0.017 5	0.005 9	-0.018 5
文献［31］方法	34.37	7.998 6	-0.001 7	0.007 2	-0.000 9
本文方法	41.57	7.993 5	0.000 4	-0.007 9	0.005 1

[1]	Yanan LI, Mengyang GUO, Guojun DENG, Yunfeng CHEN, Jianji REN, Yongliang YUAN. Method for life prediction of parallel branching engine based on multi-modal fusion features [J]. Journal of Computer Applications, 2026, 46(1): 305-313.
[2]	Lifang WANG, Wenjing REN, Xiaodong GUO, Rongguo ZHANG, Lihua HU. Trident generative adversarial network for low-dose CT image denoising [J]. Journal of Computer Applications, 2026, 46(1): 270-279.
[3]	Chaoyun MAI, Hongyi ZHANG, Chuanbo QIN, Junying ZENG, Dong WANG. Multi-scale and spatial frequency feature-based image segmentation network for pheochromocytoma [J]. Journal of Computer Applications, 2026, 46(1): 280-288.
[4]	Tingting WANG, Tingshun LI, Wen TAN, Bo LYU, Yixuan CHEN. Cable temperature prediction model based on multi-scale patch and convolution interaction [J]. Journal of Computer Applications, 2026, 46(1): 314-321.
[5]	Jinggang LYU, Shaorui PENG, Shuo GAO, Jin ZHOU. Speech enhancement network driven by complex frequency attention and multi-scale frequency enhancement [J]. Journal of Computer Applications, 2025, 45(9): 2957-2965.
[6]	Yiming LIANG, Jing FAN, Wenze CHAI. Multi-scale feature fusion sentiment classification based on bidirectional cross attention [J]. Journal of Computer Applications, 2025, 45(9): 2773-2782.
[7]	Weigang LI, Jiale SHAO, Zhiqiang TIAN. Point cloud classification and segmentation network based on dual attention mechanism and multi-scale fusion [J]. Journal of Computer Applications, 2025, 45(9): 3003-3010.
[8]	Xiang WANG, Zhixiang CHEN, Guojun MAO. Multivariate time series prediction method combining local and global correlation [J]. Journal of Computer Applications, 2025, 45(9): 2806-2816.
[9]	Jin ZHOU, Yuzhi LI, Xu ZHANG, Shuo GAO, Li ZHANG, Jiachuan SHENG. Modulation recognition network for complex electromagnetic environments [J]. Journal of Computer Applications, 2025, 45(8): 2672-2682.
[10]	Chengzhi YAN, Ying CHEN, Kai ZHONG, Han GAO. 3D object detection algorithm based on multi-scale network and axial attention [J]. Journal of Computer Applications, 2025, 45(8): 2537-2545.
[11]	Haifeng WU, Liqing TAO, Yusheng CHENG. Partial label regression algorithm integrating feature attention and residual connection [J]. Journal of Computer Applications, 2025, 45(8): 2530-2536.
[12]	Chao JING, Yutao QUAN, Yan CHEN. Improved multi-layer perceptron and attention model-based power consumption prediction algorithm [J]. Journal of Computer Applications, 2025, 45(8): 2646-2655.
[13]	Jinhao LIN, Chuan LUO, Tianrui LI, Hongmei CHEN. Thoracic disease classification method based on cross-scale attention network [J]. Journal of Computer Applications, 2025, 45(8): 2712-2719.
[14]	Chen LIANG, Yisen WANG, Qiang WEI, Jiang DU. Source code vulnerability detection method based on Transformer-GCN [J]. Journal of Computer Applications, 2025, 45(7): 2296-2303.
[15]	Liang CHEN, Xuan WANG, Kun LEI. Helmet wearing detection algorithm for complex scenarios based on cross-layer multi-scale feature fusion [J]. Journal of Computer Applications, 2025, 45(7): 2333-2341.