Image information hiding technology can achieve the goals of confidential communication, copyright authentication and other information security protection behaviors during the transmission of pictures by hiding information covertly in images, which is one of the hotspots of current research in the field of information security. Firstly, we discuss the important and difficult problems of image information hiding methods based on deep learning. Secondly, we discuss the deep learning-based image steganography method from three perspectives: structural features, training features and application features. Then, we introduce the main datasets and evaluation criteria related to the domain and summarize the experimental performance. Next, this paper summarizes the applications of image information hiding techniques. Finally, we discuss the research directions of image information hiding techniques to provide insights and suggestions for the further developments in the field.
Zhu等[44]提出了典型的解码器-编码器网络HiDDeN(Hiding data with deep networks)联合训练解码器和编码器,并使用判别器预测给定图像是否包含编码信息。Rahim等[48]使用损失约束编码器-解码器的联合端到端训练,完成了载体为三通道RGB图像,秘密信息的形式为灰度图或RGB的单通道图的高载荷信息隐藏,实现了在图像中隐藏图像的突破。Zhang等[41]提出了一种使用GAN在图像中隐藏任意二进制数据的技术SteganoGAN(High capacity image steganography with GANs)。它通过编码和解码两个操作完成在图像中的数据隐藏,通过计算解码正确率、隐写图像与载体图像之间的相似性和隐写图像的真实性,实现对编码器-解码器网络的迭代优化。Kishore等[49]为解决解码器-编码器网络嵌入容量大但解码错误率高的问题,采用SteganoGAN的解码器与编码器结构并基于神经网络对输入的微小扰动的高度敏感性,提出了一种新的隐写方法FNNS(Fixed neural network steganography),实现了更低的解码错误率。此外,Singh等[42]认为很多基于GAN的方法强调不可感知和提取精度而忽视了统计上的不可检出性,提出了双参与者框架StegGAN(Hiding image within image using conditional generative adversarial networks)。具体而言,StegGAN的嵌入网络和提取网络各自由两个子网络组成,即生成器和判别器。其中,嵌入网络的判别器设置为隐写分析网络XuNet(Structural design of convolutional neural networks for steganalysis)[30],通过将图像区分为载体图像或隐写图像与生成器进行博弈并实现纳什均衡,嵌入网络最终可以生成隐写分析器难以区分且高质量的隐写图像;提取网络的生成器从隐写图像中提取出秘密信息,对应的判别器则对真实秘密信息和提取出的秘密信息进行最大限度区分以形成对抗。最终,提取网络可以更准确地从隐写图像中估计出秘密信息。
(1)人为模拟噪声干扰模块。在训练过程中通过人为添加模拟噪声干扰促进模型鲁棒性的提升是很常见的方法。考虑到隐写图像传输过程中受到的噪声干扰,Zhu等[44]提出可抵抗噪声攻击的模型HiDDeN,在编码器与解码器之间加入噪声层实现多种不同干扰类型的噪声模拟,包含Dropout、Cropout、高斯噪声、JPEG压缩的可微近似等。该方法将隐写图像经由噪声层的模拟攻击生成的含噪隐写图像作为解码器的输入,进行秘密信息提取。这样,即使隐写图像受到一些常见噪声攻击,解码器仍能以高精度恢复秘密信息,同时也证明了可微近似训练可以有效用于鲁棒性模型的训练。Bui等[59]提出了一种使用自编码器的轻量鲁棒隐写方法(Robust steganography using autoencoder latent space,RoSteALS),在图像编码器和秘密解码器之间插入噪声模型,其中包含3种噪声类型:可微加性和线性噪声(亮度、饱和度,对比度)、近似可微噪声(JPEG压缩)、不可微噪声(spatter、飞溅)。解码器可以在各种数据增强下训练,通过反向传播更新编码器。进一步地,Liu等[60]指出在以HiDDeN为例的这种典型编码器-噪声层-解码器结构的单阶段端到端盲水印架构(The one-stage end-to-end training,OET)中,噪声层中的噪声攻击都是以可微方式进行模拟,这在实践中并不适用。面对一种新的噪声时,OET并不能很好地应对。此外,在遭受噪声攻击情况下,OET通常会出现收敛速度慢、隐写图像质量下降的问题。针对这一系列问题,他们提出一种两阶段可分离框架(Two-stage separable deep learning,TSDL)。第一阶段,编码器在没有任何噪声知识的情况下将信息冗余地嵌入载体图像中。第二阶段,解码器在训练时不更新编码器参数,而是在第一阶段基础上根据不同噪声对解码器进行微调。训练期间使用了从COCO数据集中随机选择并用图像批处理软件合成的含5种攻击类型的黑盒噪声数据集,实现对噪声干扰的模拟。类似的,Yu[61]提出的ABDH(Attention based data hiding)使用由原图像和噪声攻击图像混合而成的训练数据集。这种使用带有噪声的样本进行的混合训练,有助于进一步提高鲁棒性。
SteganoGAN[41]使用MSE分析隐写图像和载体图像之间的相似度,利用交叉熵损失优化解码精度,并利用判别网络对隐写图像的真实性进行验证,联合优化以上3个损失,迭代优化编码器-解码器网络和判别网络。HiDDeN[44]为保证编码后的图像在视觉上与载体图像相似,用图像失真损失(隐写图像和载体图像之间的距离)表征相似性。为保证解码后的消息与编码后的消息相同,HiDDeN使用原始消息和解码消息之间的距离施加消息失真损失。通过最小化输入消息和图像分布上的这几种损失实现最终优化。Luo等[46]提出的失真不可知水印框架Distortion Agnostic Deep Watermarking为控制编码图像的感知质量和消息损耗,将图像损失、消息损失分别设置为载体图像和隐写图像、解码消息和输入消息之间的损失。在文献[62]中,原始消息中的每个值都是0或者1,提取出的消息的每个元素都是0~1内的浮点数。为保证秘密信息的准确恢复,该方法使用二值交叉熵损失最小化与之间的差异。在训练完成并实际应用时,再将四舍五入到0或者1构造实数位序列。DeepMIH[56]将正向隐藏损失定义为隐写图像和载体图像之间的一种差值,这种差值可以用或损失衡量;同样反向恢复损失被定义为恢复出的秘密图像和载体图像之间的或损失。RIIS[55]的特殊之处在于恢复网络将载体图像和秘密信息同时恢复,恢复损失设计为:
ImageNet数据集[69]是目前在深度学习图像领域应用最广泛的数据集。至今,ImageNet已经发展成为包含1 400万张图像,2万多个类别的大规模视觉识别数据集,每个类别至少包含500张图像。该数据集涵盖了各种场景和对象,包括动物、植物、人类、日常用品、建筑等,大小约为1 TB。除了提供丰富的视觉数据资源,ImageNet还通过举办挑战赛ILSVRC(ImageNet large scale visual recognition challenge)推动图像分类、目标检测、图像分割等领域的研究。2012年,深度学习方法在ILSVRC上取得显著的突破,这标志着计算机视觉领域的发展进入新阶段。文献[42,48,53,54,56,63,70]等均使用ImageNet数据集或其变体与子集。
3.1.2 MS-COCO
MS-COCO(Microsoft common objects in context)数据集[71]是微软于2014年出资标注的大型物体检测和分割数据集。该数据集被广泛应用于目标检测、图像分割等任务,是目前为止拥有语义分割的最大数据集之一。COCO数据集包含80个类别,每个类别至少包含5张图像。该数据集共有超过33万张图片,其中20万张进行了标注,如物体的边界框、关键点等。整个数据大小约为40 GB,压缩后大小约为25 GB。此外,该数据集附带类别注释和分割注释,并且没有预定义的训练和测试分割。使用者可以根据研究主题和便利性对数据集进行自定义划分。文献[41,42,44,49,53,56,60-62]使用了COCO数据集。
PSNR(Peak signal to noise ratio)即峰值信噪比,是一种评价图像的客观标准。PSNR值表示处理后图像质量情况,单位是dB。PSNR可以用于衡量隐写图像的质量和秘密信息的不可见性。给定宽度为,高度为的两幅图像和,PSNR通过原图与被处理图像之间的均方误差MSE(Mean Square Error)定义,公式如下:
SSIM(Structural similarity index measure)即结构相似性指标,是基于结构信息退化的图像质量评价方法。SSIM公式基于样本图像和之间的3个比较衡量:亮度(luminance)、对比度(contrast)和结构(structure),以更好地适应人类视觉系统,可表示为
ZhangWei-ming, WangHong-xia, LiBin, et al. Overview of steganography on multimedia[J]. Journal of Image and Graphics, 2022, 27(6): 1918-1943.
[3]
SubramanianN, ElharroussO, AlmaadeedS, et al. Image steganography: a review of the recent advances[J]. IEEE Access, 2021, 9: 23409-23423.
[4]
TsaiP, HuY C, YehH L. Reversible image hiding scheme using predictive coding and histogram shifting[J]. Signal Processing, 2009, 89(6): 1129-1143.
[5]
PanF, LiJ, YangX. Image steganography method based on PVD and modulus function[C]∥2011 International Conference on Electronics, Communications and Control (ICECC), Ningbo, China, 2011: 282-284.
SunXi, ZhangWei-ming, YuNeng-hai, et al. Steganography based on parameters' disturbance of spatial image transform[J]. Journal on Communications, 2017, 38 (10): 166-174.
[8]
RustadS, SyukurA, AndonoP N. Inverted LSB image steganography using adaptive pattern to improve imperceptibility[J]. Journal of King Saud University-Computer and Information Sciences, 2022, 34(6): 3559-3568.
[9]
FazliS, MoeiniM. A robust image watermarking method based on DWT, DCT, and SVD using a new technique for correction of main geometric attacks[J]. Optik-International Journal for Light and Electron Optics, 2016, 127(2): 964-972.
[10]
AbadiR Y, MoallemP. Robust and optimum color image watermarking method based on a combination of DWT and DCT[J]. Optik, 2022, 261: No.169146.
ZhaoYao-yao, LiWan-she. Color image watermarking algorithm based on discrete wavelet transform and discrete cosine transform[J]. Advances in Applied Mathematics, 2021,10: No.1096.
[13]
WangR Z, LinC F, LinJ C. Image hiding by optimal LSB substitution and genetic algorithm[J]. Pattern Recognition, 2001, 34(3): 671-683.
[14]
FridrichJ, GoljanM, DuR. Detecting LSB steganography in color, and gray-scale images[J]. IEEE Multimedia, 2001, 8(4): 22-28.
[15]
MandalP C, MukherjeeI, PaulG, et al. Digital image steganography: a literature survey[J]. Information Sciences, 2022, 609: 1451-1488.
[16]
ChhikaraS, KumarR. Information theoretic steganalysis of processed image LSB steganography[J]. Multimedia Tools and Applications, 2023, 82(9): 13595-13615.
FuZhang-jie, LiEn-lu, ChengXu, et al. Recent advances in image steganography based on deep learning[J]. Journal of Computer Research and Development, 2021, 58(3): 548-568.
[19]
EhrlichM, DavisL, LimS N, et al. Analyzing and mitigating jpeg compression defects in deep learning[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021: 2357-2367.
[20]
KhayamS A. The discrete cosine transform (DCT): theory and application[J]. Journal of Michigan State University, 2003, 114(1): 1-31.
[21]
PoyuehP Y, LinH J. A DWT based approach for image steganography[J]. International Journal of Applied Science and Engineering, 2006, 4(3): 275-290.
[22]
RuanaidhJ, DowlingW J, BolandF M. Phase watermarking of digital images[J]. Proceedings of 3rd IEEE International Conference on Image Processing, 1996, 3: 239-242.
[23]
LiY. Research and application of deep learning in image recognition[C]∥2022 IEEE 2nd International Conference on Power, Electronics and Computer Applications (ICPECA), Shenyang, China, 2022: 994-999.
XuTao, MaKe, LiuCai-hua. Multi object pedestrian tracking based on deep learning[J]. Journal of Jilin University (Engineering and Technology Edition), 2021, 51(1): 27-38.
[26]
LopezM M, KalitaJ. Deep learning applied to NLP[J/OL]. [2024-04-01].
[27]
ZhangZ, GeigerJ, PohjalainenJ, et al. Deep learning for environmentally robust speech recognition: an overview of recent developments[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2018, 9(5): 1-28.
HuangLi-wei, JiangBi-tao, Shou-yeLyu, et al. Survey on deep learning based recommender systems[J]. Chinese Journal of Computers, 2018, 41(7): 1619-1647.
[30]
HeatonJ B, PolsonN G, WitteJ H. Deep learning for finance: deep portfolios[J]. Applied Stochastic Models in Business and Industry, 2017, 33(1): 3-12.
ShenQuan-you, ZhangXiao-bo, LiWen-hao, et al. Progress of U-Net applications to lung nodule segmentation[J]. Journal of Computer Applications, 2023,43(Sup.1): 250-257.
[33]
AlomM Z, YakopcicC, HasanM, et al. Recurrent residual U-Net for medical image segmentation[J]. Journal of Medical Imaging, 2019, 6(1): No.014006.
FuZhang-jie, WangFan, SunXing-ming, et al. Research on steganography of digital images based on deep learning[J]. Chinese Journal of Computers, 2020,43(9): 1656-1672.
[36]
张茹, 刘建毅, 刘功申, 数字内容安全[M]. 北京: 北京邮电大学出版社, 2017.
[37]
SaraU, AkterM, UddinM S. Image quality assessment through FSIM, SSIM, MSE and PSNR—a comparative study[J]. Journal of Computer and Communications, 2019, 7(3): 8-18.
[38]
XuG, WuH Z, ShiY Q. Structural design of convolutional neural networks for steganalysis[J]. IEEE Signal Processing Letters, 2016, 23(5): 708-712.
[39]
GengL, ZhangW, ChenH, et al. Real-time attacks on robust watermarking tools in the wild by CNN[J]. Journal of Real-Time Image Processing, 2020, 17: 631-641.
[40]
WeiP, ZhuZ, LuoG, et al. Breaking robust data hiding in online social networks[J]. IEEE Signal Processing Letters, 2022, 29: 2682-2686.
[41]
ChaumontM. Deep Learning in Steganography and Steganalysis[M]. New York: Academic Press, 2020.
XiaDao-xun, WangLin-na, SongYun-fei, et al. Review of deep neural network digital watermarking technology[J]. Science Technology and Engineering, 2023, 23(5): 1799-1811.
[44]
DenisR, MadhubalaP. Hybrid data encryption model integrating multi-objective adaptive genetic algorithm for secure medical data communication over cloud-based healthcare systems[J]. Multimedia Tools and Applications, 2021, 80: 21165-21202.
[45]
JiangX H. Digital watermarking and its application in image copyright protection[C]∥2010 International Conference on Intelligent Computation Technology and Automation, Changsha, China, 2010: 114-117.
[46]
MegíasD, MazurczykW, KuribayashiM. Data hiding and its applications: digital watermarking and steganography[J]. Applied Sciences, 2021, 11(22): No.10928.
ZhaoJie, ZouTian-yu, HuangZhan-peng, et al. Research on copyright protection of medical images based on handwritten digital watermarking[J]. Chinese Medical Equipment Journal, 2016, 37(6): 36-38.
ZhouNa, ChengMing, JiaMeng-lin, et al. Medical image privacy protection based on thumbnail encryption and distributed storage[J]. Journal of Computer Applications, 2023, 43(10): 3149-3155.
LiuJia, KeYan, LeiYu, et al. Application of generative adversarial networks in image steganography[J]. Journal of Wuhan University (Science Edition), 2019, 65 (2): 139-152.
[53]
ZhangK A, CuestaI A, XuL, et al. SteganoGAN: high capacity image steganography with GANs[J/OL].[2024-04-01].
[54]
SinghB, SharmaP K, HuddedarS A, et al. StegGAN: hiding image within image using conditional generative adversarial networks[J]. Multimedia Tools and Applications, 2022, 81(28): 40511-40533.
[55]
WangZ, GaoN, WangX, et al. SSteGAN: self-learning steganography based on generative adversarial networks[C]∥Neural Information Processing: 25th International Conference, Siem Reap, Cambodia, 2018: 253-264.
[56]
ZhuJ, KaplanR, JohnsonJ, et al. Hidden: hiding data with deep networks[C]∥Proceedings of the European conference on computer vision (ECCV), Munich, Germany, 2018: 657-672.
[57]
SunW, ZhouJ, LiY, et al. Robust high-capacity watermarking over online social network shared images[J]. IEEE Transactions on Circuits and Systems for Video Technology, 2020, 31(3): 1208-1221.
[58]
LuoX, ZhanR, ChangH, et al. Distortion agnostic deep watermarking[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, USA, 2020: 13548-13557.
[59]
ZhangH, WangH, CaoY, et al. Robust data hiding using inverse gradient attention[J/OL]. [2024-04-01].
[60]
RahimR, NadeemS. End-to-end trained CNN encoder-decoder networks for image steganography[C]∥Proceedings of the European Conference on Computer Vision (ECCV) Workshops, Munich, Germany, 2018: 723-729.
[61]
KishoreV, ChenX, WangY, et al. Fixed neural network steganography: train the images, not the network[C]∥International Conference on Learning Representations, Vienna, Austria, 2021: 1-10.
ArdizzoneL, KruseJ, WirkertS, et al. Analyzing inverse problems with invertible neural networks[J/OL]. [2024-04-01].
[64]
DinhL, SohlD J, BengioS. Density estimation using real NVP[C]∥ICLR 2017-Conference Track Proceedings, Toulon, France, 2019: No.160508803.
[65]
JingJ, DengX, XuM, et al. HiNet: deep image hiding by invertible network[C]∥Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, Canada, 2021: 4733-4742.
[66]
LuS P, WangR, ZhongT, et al. Large-capacity image steganography based on invertible neural networks[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Nashville, USA, 2021: 10816-10825.
[67]
XuY, MouC, HuY, et al. Robust invertible image steganography[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 7875-7884.
[68]
GuanZ, JingJ, DengX, et al. DeepMIH: deep invertible network for multiple image hiding[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 45(1): 372-390.
[69]
YangH, XuY, LiuX, et al. PRIS: practical robust invertible network for image steganography[J/OL]. [2024-04-01].
[70]
MouC, XuY, SongJ, et al. Large-capacity and flexible video steganography via invertible neural network[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, 2023: 22606-22615.
[71]
BuiT, AgarwalS, YuN, et al. Rosteals: robust steganography using autoencoder latent space[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Vancouver, Canada, 2023: 933-942.
[72]
LiuY, GuoM, ZhangJ, et al. A novel two-stage separable deep learning framework for practical blind watermarking[C]∥Proceedings of the 27th ACM International Conference on Multimedia,Nice, France, 2019: 1509-1517.
[73]
YuC. Attention based data hiding with generative adversarial networks[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(1): 1120-1128.
[74]
TanJ, LiaoX, LiuJ, et al. Channel attention image steganography with generative adversarial networks[J]. IEEE Transactions on Network Science and Engineering, 2021, 9(2): 888-903.
[75]
CuiJ, ZhangP, LiS, et al. Multitask identity-aware image steganography via minimax optimization[J]. IEEE Transactions on Image Processing, 2021, 30: 8567-8579.
[76]
TancikM, MildenhallB, NgR. Stegastamp: invisible hyperlinks in physical photographs[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition,Seattle, USA, 2020: 2117-2126.
[77]
WeiP, LiS, ZhangX, et al. Generative steganography network[C]∥Proceedings of the 30th ACM International Conference on Multimedia, New York, USA, 2022: 1621-1629.
[78]
LiuX, MaZ, MaJ, et al. Image disentanglement autoencoder for steganography without embedding[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, USA, 2022: 2303-2312.
[79]
YouZ, YingQ, LiS, et al. Image generation network for covert transmission in online social network[C]∥Proceedings of the 30th ACM International Conference on Multimedia, New York, USA, 2022: 2834-2842.
[80]
HuD, DetoneD, MalisiewiczT. Deep charuco: dark charuco marker pose estimation[C]∥Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Long Beach, USA, 2019: 8436-8444.
[81]
DengJ, DongW, SocherR, et al. Imagenet: a large-scale hierarchical image database[C]∥IEEE Conference on Computer Vision and Pattern Recognition, Miami, USA, 2009: 248-255.
[82]
ZhangC, BenzP, KarjauvA, et al. Udh: universal deep hiding for steganography, watermarking, and light field messaging[J]. Advances in Neural Information Processing Systems, 2020, 33: 10223-10234.
[83]
LinT Y, MaireM, BelongieS, et al. Microsoft coco: common objects in context[C]∥Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, 2014: 740-755.
[84]
EirikurA, RaduT. NTIRE 2017 challenge on single image super-resolution: dataset and study[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, Honolulu, USA, 2017: 126-135.
[85]
LiuZ, LuoP, WangX, et al. Deep learning face attributes in the wild[C]∥Proceedings of the IEEE International Conference on Computer Vision, Santiago, Chile, 2015: 3730-3738.
[86]
BasP, FillerT, PevnýT. Break our steganographic system: the ins and outs of organizing boss[C]∥International Workshop on Information Hiding, Berlin, Germany, 2011: 59-70.
[87]
DengL. The mnist database of handwritten digit images for machine learning research best of the web [J]. IEEE Signal Processing Magazine, 2012, 29(6): 141-142.
[88]
SetiadiD R I M. PSNR vs SSIM: imperceptibility quality assessment for image steganography[J]. Multimedia Tools and Applications, 2021, 80(6): 8423-8444.
[89]
ZhangR, IsolaP, EfrosA A, et al. The unreasonable effectiveness of deep features as a perceptual metric[C]∥Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, USA, 2018: 586-595.
[90]
ZhangL, ZhangL, MouX, et al. FSIM: a feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8): 2378-2386.
[91]
杨榆, 雷敏. 信息隐藏与数字水印[M]. 北京: 北京邮电大学出版社, 2017.
[92]
PandeyB K, PandeyD, WairyaS, et al. Application of integrated steganography and image compressing techniques for confidential information transmission[J]. Cyber Security and Network Security, 2022, 3: 169-191.
[93]
MorkelT. Image Steganography Applications for Secure Communication[M]. Pretoria: University of Pretoria (South Africa), 2012.
[94]
PandeyD, WairyaS, MahdawiR S, et al. Secret data transmission using advanced steganography and image compression[J]. International Journal of Nonlinear Analysis and Applications, 2021, 12: 1243-1257.
ZhengGang, HuDong-hui, GeHui, et al. End-to-end image steganography and watermarking driven by generative adversarial networks[J]. Chinese Journal of Image and Graphics, 2021, 26(10): 2485-2502.
WuHan-zhou, ZhangJie, LiYue, et al. Research progress of artificial intelligence model watermarking[J]. Journal of Image and Graphics, 2023, 28(6): 1792-1810.
ZhangWen-Fang. Research on medical data watermarking algorithm in remote consultation[D]. Nanjing: School of Computer Science, Nanjing University of Information Engineering, 2023.
[104]
ZengC, LiuJ, LiJ, et al. Multi-watermarking algorithm for medical image based on KAZE-DCT[J]. Journal of Ambient Intelligence and Humanized Computing, 2022, 15: 1735-1743.
LiuYong-bin, XuTao, SuRui-hao, et al. A medical image information hiding system based on digital watermarking[J]. Modern Computer, 2019(20): 42-45.
[107]
AnandA, SinghA K. Watermarking techniques for medical data authentication: a survey[J]. Multimedia Tools and Applications, 2021, 80: 30165-30197.
[108]
KarakusS, AvciE. A new image steganography method with optimum pixel similarity for data hiding in medical images[J]. Medical Hypotheses, 2020, 139: No.109691.
[109]
PriyadharshiniA, UmamaheswariR, JayapandianN, et al. Securing medical images using encryption and LSB steganography[C]∥International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), Bhilai, India, 2021: 1-5.
[110]
BaluS, BabuC N K, AmudhaK. Secure and efficient data transmission by video steganography in medical imaging system[J]. Cluster Computing, 2019, 22(Sup.2): 4057-4063.
[111]
卢臻. AI换脸骗局频现 人工智能出圈后如何监管? [N]. 通信信息报, 2023-06-14.
[112]
LuZhen. How to supervise after AI face changing scam occurs frequently? [N]. Journal of Communication Information, 2023-06-14.