检索结果-南通市图书馆

RWNeRF: Robust Watermarking Scheme for Neural Radiance Fields Based on Invertible Neural Networks

CMC-COMPUTERS MATERIALS & CONTINUA 2024年第3期80卷 4065-4083页

作者： Sun, Wenquan Liu, Jia dong, weina Chen, Lifeng Di, Fuqiang Engn Univ PAP Dept Cryptog Engn Xian 710086 Peoples R China Dept Cryptog Engn Key Lab PAP Cryptol & Informat Secur Xian 710086 Peoples R China

As neural radiance fields continue to advance in 3D content representation, the copyright issues surrounding 3D models oriented towards implicit representation become increasingly pressing. In response to this challenge, this paper treats the embedding and extraction of neural radiance field watermarks as inverse problems of image transformations and proposes a scheme for protecting neural radiance field copyrights using invertible neural network watermarking. Leveraging 2D image watermarking technology for 3D scene protection, the scheme embeds watermarks within the training images of neural radiance fields through the forward process in invertible neural networks and extracts them from images rendered by neural radiance fields through the reverse process, thereby ensuring copyright protection for both the neural radiance fields and associated 3D scenes. However, challenges such as information loss during rendering processes and deliberate tampering necessitate the design of an image quality enhancement module to increase the scheme's robustness. This module restores distorted images through neural network processing before watermark extraction. Additionally, embedding watermarks in each training image enables watermark information extraction from multiple viewpoints. Our proposed watermarking method achieves a PSNR (Peak Signal-to-Noise Ratio) value exceeding 37 dB for images containing watermarks and 22 dB for recovered watermarked images, as evaluated on the Lego, Hotdog, and Chair datasets, respectively. These results demonstrate the efficacy of our scheme in enhancing copyright protection.

关键词： Neural radiance fields 3D scene robust watermarking invertible neural networks IMAGE

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

MarkNeRF:Watermarking for Neural Radiance Field

引用

Computers, Materials & Continua 2024年第7期80卷 1235-1250页

作者： Lifeng Chen Jia Liu Wenquan Sun weina dong Xiaozhong Pan Cryptographic Engineering Department Institute of Cryptographic EngineeringEngineering University of PAPXi’an710086China Key Laboratory of Network and Information Security of PAP Xi’an710086China

This paper presents a novel watermarking scheme designed to address the copyright protection challenges encountered with Neural radiation field(NeRF)*** employ an embedding network to integrate the watermark into the images within the training ***,theNeRFmodel is utilized for *** copyright verification,a secret image is generated by inputting a confidential viewpoint into *** this basis,design an extraction network to extract embedded watermark images fromconfidential *** the event of suspicion regarding the unauthorized usage of NeRF in a black-box scenario,the verifier can extract the watermark from the confidential viewpoint to authenticate the model’s *** experimental results demonstrate not only the production of visually appealing watermarks but also robust resistance against various types of noise attacks,thereby substantiating the effectiveness of our approach in safeguarding NeRF.

关键词： Neural radiation field 3D watermark robustness black box

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

MarkINeRV: A Robust Watermarking Scheme for Neural Representation for Videos Based on Invertible Neural Networks

引用

CMC-COMPUTERS MATERIALS & CONTINUA 2024年第3期80卷 4031-4046页

作者： Sun, Wenquan Liu, Jia Chen, Lifeng dong, weina Di, Fuqiang Engn Univ PAP Dept Cryptog Engn Xian 710086 Peoples R China Key Lab Cryptol & Informat Secur Dept Cryptog Engn Xian 710086 Peoples R China

Recent research advances in implicit neural representation have shown that a wide range of video data distributions are achieved by sharing model weights for Neural Representation for Videos (NeRV). While explicit methods exist for accurately embedding ownership or copyright information in video data, the nascent NeRV framework has yet to address this issue comprehensively. In response, this paper introduces MarkINeRV, a scheme designed to embed watermarking information into video frames using an invertible neural network watermarking approach to protect the copyright of NeRV, which models the embedding and extraction of watermarks as a pair of inverse processes of a reversible network and employs the same network to achieve embedding and extraction of watermarks. It is just that the information flow is in the opposite direction. Additionally, a video frame quality enhancement module is incorporated to mitigate watermarking information losses in the rendering process and the possibility of malicious attacks during transmission, ensuring the accurate extraction of watermarking information through the invertible network's inverse process. This paper evaluates the accuracy, robustness, and invisibility of MarkINeRV through multiple video datasets. The results demonstrate its efficacy in extracting watermarking information for copyright protection of NeRV. MarkINeRV represents a pioneering investigation into copyright issues surrounding NeRV.

关键词： Invertible neural network neural representations for videos watermarking robustness

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于可逆网络的轻量化图像隐写方案

引用

计算机应用研究 2024年第1期41卷 266-271页

作者：孙文权刘佳钮可董炜娜陈立峰武警工程大学网络与信息安全武警部队重点实验室西安710086

目前,基于深度学习的隐写模型的隐写容量有所提高,但由于网络结构复杂,需要大量的时间来训练。为此,提出轻量化的可逆神经网络结构,并以此设计了高效图像隐写方案,采用基于密集连接的可逆神经网络实现图像的隐藏与恢复,在减少可逆块数... 详细信息

目前,基于深度学习的隐写模型的隐写容量有所提高,但由于网络结构复杂,需要大量的时间来训练。为此,提出轻量化的可逆神经网络结构,并以此设计了高效图像隐写方案,采用基于密集连接的可逆神经网络实现图像的隐藏与恢复,在减少可逆块数量的同时,增加每个可逆块中可逆函数f(·)、r(·)和y(·)的卷积块数量来保证图像质量。这样能够显著降低计算和存储开销,使得模型在计算资源有限的设备上运行更加高效,模型开发和迭代的过程更加高效,有效地节省了宝贵的计算资源。载体图像与秘密图像通过正向隐藏可逆变换生成含密图像,含密图像与随机变量通过反向恢复可逆变换得到恢复图像。实验结果表明,与HiNet算法相比,轻量级网络结构能够得到良好的图像质量且更具安全性,同时训练时间缩短了46%,隐写时间缩短了28%。

关键词：可逆神经网络隐藏恢复隐写效率

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于可逆神经网络的神经辐射场水印

引用

计算机应用研究 2024年第6期41卷 1840-1844页

作者：孙文权刘佳董炜娜陈立峰钮可武警工程大学网络与信息安全武警部队重点实验室西安710086

针对面向隐式表达的神经辐射场的3D模型的版权问题,将神经辐射场水印的嵌入与提取视为一对图像变换的逆问题,提出了一种利用可逆神经网络水印保护神经辐射场版权方案。利用二维图像的水印技术以实现对三维场景的保护,通过可逆网络中的... 详细信息

针对面向隐式表达的神经辐射场的3D模型的版权问题,将神经辐射场水印的嵌入与提取视为一对图像变换的逆问题,提出了一种利用可逆神经网络水印保护神经辐射场版权方案。利用二维图像的水印技术以实现对三维场景的保护,通过可逆网络中的正向过程在神经辐射场的训练图像中嵌入水印,利用逆向过程从神经辐射场渲染出的图像提取水印,实现对神经辐射场以及三维场景的版权保护。但神经辐射场在渲染过程中会造成水印信息丢失,为此设计了图像质量增强模块,将渲染图像通过神经网络进行恢复然后再进行水印提取。同时在每个训练图像中均嵌入水印来训练神经辐射场,实现在多个视角下均可提取水印信息。实验结果表明了提出的水印方案达到版权保护的目的,证明方案的可行性。

关键词：可逆神经网络数字水印神经辐射场渲染

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

基于编码-解码网络的大容量鲁棒图像隐写方案

引用

计算机应用 2024年第3期44卷 772-779页

作者：董炜娜刘佳潘晓中陈立峰孙文权武警工程大学密码工程学院西安710086 网络与信息安全武警部队重点实验室(武警工程大学) 西安710086

针对基于编码-解码网络的大容量隐写模型存在鲁棒性弱、无法抵抗噪声攻击和信道压缩的问题,提出一种基于编码-解码网络的大容量鲁棒图像隐写方案。首先,设计了基于密集连接卷积网络(DenseNet)的编码器、解码器和判别器,编码器将秘密信... 详细信息

针对基于编码-解码网络的大容量隐写模型存在鲁棒性弱、无法抵抗噪声攻击和信道压缩的问题,提出一种基于编码-解码网络的大容量鲁棒图像隐写方案。首先,设计了基于密集连接卷积网络(DenseNet)的编码器、解码器和判别器,编码器将秘密信息和载体图像联合编码成隐写图像,解码器提取秘密信息,判别器用于区分载体图像和隐写图像。在编码器和解码器中间加入噪声层,采用Dropout、JPEG压缩、高斯模糊、高斯噪声和椒盐噪声模拟真实环境下的各类噪声攻击,编码器输出的隐写图像经过不同种类的噪声处理,再由解码器解码;通过训练模型,解码器能够对噪声处理后的隐写图像提取秘密信息,以抵抗噪声攻击。实验结果表明,所提方案在360×360像素的图像上隐写容量达到0.45~0.95 bpp,与次优的鲁棒隐写方案相比,相对嵌入容量提升了2.04倍;解码准确率可达0.72~0.97;与未添加噪声层的隐写方案相比,平均解码准确率提高了44个百分点。所提方案在保证高嵌入量、高编码图片质量的同时具有更强的抗噪声攻击能力。

关键词：深度学习信息隐藏图像隐写大容量鲁棒性编码-解码网络对抗性训练

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

面向神经辐射场的水印算法

引用

计算机应用研究 2024年第7期41卷 2184-2188页

作者：陈立峰刘佳董炜娜孙文权潘晓中武警工程大学网络与信息安全武警部队重点实验室西安710086

针对隐式表示的3D模型的版权保护问题,提出了一种面向神经辐射场(NeRF)的水印算法。该算法通过嵌入网络对训练集中的图像嵌入水印,再利用NeRF模型进行3D模型建模。版权验证方通过给定一个秘密视角作为神经辐射场的输入,生成新视角下的... 详细信息

针对隐式表示的3D模型的版权保护问题,提出了一种面向神经辐射场(NeRF)的水印算法。该算法通过嵌入网络对训练集中的图像嵌入水印,再利用NeRF模型进行3D模型建模。版权验证方通过给定一个秘密视角作为神经辐射场的输入,生成新视角下的图像作为后门图像,接着利用神经网络的过参数化方法设计一个水印提取器,获取该视角下嵌入的水印图像。在黑盒场景下,一旦怀疑3D模型被未经授权地使用,验证方则可以通过秘密视角提取水印以验证网络版权。实验结果表明,所提算法提取水印不仅具有良好的视觉效果,而且对不同类型的噪声攻击具有较好的抵抗能力。

关键词：神经辐射场 3D水印鲁棒性黑盒水印

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Eutrophication of Jiangsu Coastal Water and Its Role in the Formation of Green Tide

引用

Journal of Ocean University of China 2024年第1期23卷 109-118页

作者： XIAO Mingyan SONG weina ZHANG Haibo SHI Xiaoyong SU Rongguo Key Laboratory of Marine Chemistry Theory and Technology Ministry of EducationOcean University of ChinaQingdao 266100China National Marine Environmental Monitoring Center Dalian 116000China National Marine Hazard Mitigation Service Beijing 100194China

Since 2007,the large-scale green tide caused by Ulva prolifera(***)have occurred as a recurrent phenomenon in the southern Yellow Sea of *** surveys and satellite remote sensing showed that the small scattered patches of green tide algae were first observed along the Porphyra agriculture area of the Subei Shoal in late *** this study,we attempted to identify the role of eutrophication in the origin of the green tide in the Subei Shoal and its adjacent *** Shoal and its adjacent area are characterized by rich nutrients,especially NO_(3)^(-)-N,NH_(4)^(+)-N,PO_(4)^(3-)-P,and other bioavailable components(such as urea-N and amino acids).In the spring of 2017,the average concentrations of NO_(3)^(-)-N were 19.01±11.01μmolL^(-1),accounting for 86.68%of the dis-solved inorganic nitrogen(DIN).In addition,the average concentration of NH4^(+)-N was 2.51±1.60μmolL^(-1).PO_(4)^(3-)-P had an average concentration of 0.14±0.13μ*** average concentrations of urea-N and total hydrolyzed amino acids(THAA)were 1.73±1.36μmolL^(-1)and 1.33±0.80μmolL^(-1),*** nutritive substances play a key role in the rapid production of *** and make the Jiangsu coastal water an incubator for green tide.

关键词： green tide nutrients algae Ulva prolifera eutrophication Subei Shoal

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Combining field data and modeling to better understand maize growth response to phosphorus(P) fertilizer application and soil P dynamics in calcareous soils

引用

Journal of Integrative Agriculture 2024年第3期23卷 1006-1021页

作者： weina Zhang Zhigan Zhao Di He Junhe Liu Haigang Li Enli Wang School of Biological and Food Processing Engineering Huanghuai UniversityZhumadian 463000China Key Laboratory of Plant-Soil Interactions Ministry of Education/College of Resources and Environmental SciencesChina Agricultural UniversityBeijing 100193China Inner Mongolia Key Laboratory of Soil Quality and Nutrient Resources/Key Laboratory of Grassland Resource(IMAU) Ministry of Education/College of GrasslandResources and EnvironmentInner Mongolia Agricultural UniversityHohhot 010018China CSIRO Agriculture and Food CanberraACT 2601Australia

We used field experimental data to evaluate the ability of the agricultural production system model (APSIM) to simulate soil P availability,maize biomass and grain yield in response to P fertilizer applications on a fluvo-aquic soil in the North China *** and soil data from a 2-year experiment with three P fertilizer application rates(0,75 and 300 kg P_(2)O_(5) ha^(–1)) were used to calibrate the *** analysis was carried out to investigate the influence of APSIM SoilP parameters on the simulated P availability in soil and maize *** and soil P parameters were then derived by matching or relating the simulation results to observed crop biomass,yield,P uptake and Olsen-P in *** re-parameterized model was further validated against 2 years of independent data at the same *** re-parameterized model enabled good simulation of the maize leaf area index (LAI),biomass,grain yield,P uptake,and grain P content in response to different levels of P additions against both the calibration and validation *** results showed that APSIM needs to be re-parameterized for simulation of maize LAI dynamics through modification of leaf size curve and a reduction in the rate of leaf senescence for modern staygreen maize cultivars in *** P concentration limits (maximum and minimum P concentrations in organs)at different stages also need to be *** results further showed a curvilinear relationship between the measured Olsen-P concentration and simulated labile P content,which could facilitate the initialization of APSIM P pools in the NCP with Olsen-P measurements in future *** remains difficult to parameterize the APSIM SoilP module due to the conceptual nature of the pools and simplified conceptualization of key P transformation processes.A fundamental understanding still needs to be developed for modelling and predicting the fate of applied P fertilizers in soils with contrasting physical and chemical characteristics.

关键词： maize phosphorus availability modeling APSIM maize APSIM SoilP

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Mechanisms of isomerization and hydration reactions of typicalβ-diketone at the air-droplet interface

引用

Journal of Environmental Sciences 2024年第7期141卷 225-234页

作者： Yuemeng Ji Weiyong Luo Qiuju Shi Xiaohui Ma Ziqi Wu weina Zhang Yanpeng Gao Taicheng An Guangdong-Hong Kong-Macao Joint Laboratory for Contaminants Exposure and Health Guangdong Key Laboratory of Environmental Catalysis and Health Risk ControlInstitute Environmental Health and Pollution ControlGuangdong University of TechnologyGuangzhou 510006China Guangzhou Key Laboratory of Environmental Catalysis and Pollution Control Key Laboratory for City Cluster Environmental Safety and Green Development of the Ministry of EducationSchool of Environmental Science and EngineeringGuangdong University of TechnologyGuangzhou 510006China

Acetylacetone(AcAc)is a typical class ofβ-diketones with broad industrial applications due to the property of the keto-enol isomers,but its isomerization and chemical reactions at the air-droplet interface are still ***,using combined molecular dynamics and quantum chemistry methods,the heterogeneous chemistry of AcAc at the air-droplet interface was investigated,including the attraction of AcAc isomers by the droplets,the distribution of isomers at the air-droplet interface,and the hydration reactions of isomers at the air-droplet *** results reveal that the preferential orientation of two AcAc isomers(keto-and enol-AcAc)to accumulate and accommodate at the acidic air-droplet *** isomerization of two AcAc isomers at the acidic air-droplet interface is more favorable than that at the neutral air-droplet interface because the“water bridge”structure is destroyed by H_(3)O^(+),especially for the isomerization from keto-Ac Ac to *** the acidic air-droplet interface,the carbonyl or hydroxyl O-atoms of two AcAc isomers display an energetical preference to ***-diol is the dominant products to accumulate at the air-droplet interface,and excessive keto-diol can enter the droplet interior to engage in the *** photooxidation reaction of AcAc will increase the acidity of the air-droplet interface,which indirectly facilitate the uptake and formation of more *** results provide an insight into the heterogeneous chemistry ofβ-diketones and their influence on the environment.

关键词： Acetylacetone Air-droplet interface Theoretical simulation Isomerization Hydration reaction mechanism

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：