检索结果-南通市图书馆

A Generative Method for Steganography by Cover Synthesis with Auxiliary Semantics

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2020年第4期25卷 516-527页

作者： Zhuo Zhang Guangyuan Fu rongrong ni Jia Liu Xiaoyuan Yang Rocket Force University of Engineering Xi’an 710025China the Key Laboratory of Network and Information Security of PAP Engineering University of PAPXi’an 710086China the Institute of Information Science Beijing Jiaotong UniversityBeijing 100044China

Traditional steganography is the practice of embedding a secret message into an image by modifying the information in the spatial or frequency domain of the cover *** this method has a large embedding capacity,it inevitably leaves traces of rewriting that can eventually be discovered by the *** method of Steganography by Cover Synthesis(SCS)attempts to construct a natural stego image,so that the cover image is not modified;thus,it can overcome detection by a steganographic *** to the difficulty in constructing natural stego images,the development of SCS is *** this paper,a novel generative SCS method based on a Generative Adversarial Network(GAN)for image steganography is *** our method,we design a GAN model called Synthetic Semantics Stego Generative Adversarial Network(SSS-GAN)to generate stego images from secret *** establishing a mapping relationship between secret messages and semantic category information,category labels can generate pseudo-real images via the generative ***,the receiver can recognize the labels via the classifier network to restore the concealed information in *** trained the model on the MIniST,CIFAR-10,and CIFAR-100 image *** show the feasibility of this *** security,capacity,and robustness of the method are analyzed.

关键词： information hiding steganography steganography without modification Steganography by Cover Synthesis(SCS) generative adversarial networks

Watermark Embedding for Direct Binary Searched Halftone Images by Adopting Visual Cryptography

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2018年第5期55卷 255-265页

作者： Yangyang Wang rongrong ni Yao Zhao Min Xian Beijing Key Laboratory of Advanced Information Science and Network Technology Institute of Information ScienceBeijing Jiaotong UniversityBeijing 100044China Department of Computer Science University of IdahoIdaho FallsID 83402United States

In this paper,two methods are proposed to embed visual watermark into direct binary search(DBS)halftone images,which are called Adjusted Direct Binary Search(ADBS)and Dual Adjusted Direct Binary Search(DADBS).DADBS is an improved version of *** using the proposed methods,the visual watermark will be embedded into two halftone images separately,thus,the watermark can be revealed when these two halftone images are *** results show that both methods can achieve excellent image visual quality and decoded visual patterns.

关键词： Data hiding halftone direct binary search visual watermark.

A channel selection rule for YASS

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

Science China(Information Sciences) 2014年第8期57卷 156-165页

作者： YU LiFang ZHAO Yao ni rongrong CAO Gang Institute of Information Science Beijing Jiaotong University School of Computer Science Communication University of China

In this paper,a channel selection rule for YASS(Yet-Another-Secure-Steganography)is *** message embedding imposes distortion to the cover *** larger the distortion,the less secure the steganographic *** channel selection rule engages in minimizing this distortion brought in by *** our rule,the distortion caused by unit change on each quantized DCT(Discrete Cosine Transformation)component is computed,and the components with smaller unit change distortion are selected with higher *** channel selection rule reduces distortion to the medium spatial domain image and the final JPEG *** results show that our improved YASS scheme outperforms original YASS scheme on the aspects of both perception and *** new channel selection rule can also be combined with other enhancements in YASS framework to further boost the performance.

关键词： steganography steganalysis YASS channel selection DC components embedding distortion

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

针对人脸识别模型的自适应对抗攻击

兰州交通大学学报 2024年第5期43卷 61-69页

作者：李澳赵耀倪蓉蓉加小红北京交通大学计算机科学与技术学院北京100044 兰州交通大学电子与信息工程学院兰州730070

深度神经网络容易受到对抗样本的攻击,这种攻击通过对输入数据(如图像数据)的微小修改而使得AI系统分类错误。目前的许多攻击方法容易导致图像出现噪声和伪影等问题,攻击方法的泛化性较差。本文提出了一种针对人脸识别模型的对抗攻击方... 详细信息

深度神经网络容易受到对抗样本的攻击,这种攻击通过对输入数据(如图像数据)的微小修改而使得AI系统分类错误。目前的许多攻击方法容易导致图像出现噪声和伪影等问题,攻击方法的泛化性较差。本文提出了一种针对人脸识别模型的对抗攻击方法,利用身份解耦技术自适应提取对人脸识别模型的判别最重要且能很好保持原始视觉效果的人脸身份特征,并利用其引导优化在StyleGAN隐空间和像素空间上进行的对抗攻击。在典型人脸识别模型和商业人脸识别系统上的攻击实验证明,本文方法生成的对抗性人脸图像在攻击成功率上比现有最优方法平均提高11%,视觉质量提高约3%。

关键词：对抗攻击人脸识别模型身份特征身份解耦

CNN-Based Forensic Method on Contrast Enhancement with JPEG Post-Processing

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2021年第12期69卷 3205-3216页

作者： Ziqing Yan Pengpeng Yang rongrong ni Yao Zhao Hairong Qi Institute of Information Science Beijing Jiaotong UniversityBeijing100044China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing Jiaotong UniversityBeijing100044China Electrical Engineering and Computer Science Department University of Tennessee KnoxvilleKnoxville37996TNUSA

As one of the most popular digital image manipulations,contrast enhancement(CE)is frequently applied to improve the visual quality of the forged images and conceal traces of forgery,therefore it can provide evidence of tampering when verifying the authenticity of digital *** enhancement forensics techniques have always drawn significant attention for image forensics community,although most approaches have obtained effective detection results,existing CE forensic methods exhibit poor performance when detecting enhanced images stored in the JPEG *** detection of forgery on contrast adjustments in the presence of JPEG post processing is still a challenging *** this paper,we propose a new CE forensic method based on convolutional neural network(CNN),which is robust to JPEG *** proposed network relies on a Xception-based CNN with two preprocessing ***,unlike the conventional CNNs which accepts the original image as its input,we feed the CNN with the gray-level co-occurrence matrix(GLCM)of image which contains CE fingerprints,then the constrained convolutional layer is used to extract high-frequency details in GLCMs under JPEG compression,finally the output of the constrained convolutional layer becomes the input of Xception to extract multiple features for further *** results show that the proposed detector achieves the best performance for CE forensics under JPEG post-processing compared with the existing methods.

关键词： Contrast enhancement forensics convolutional neural networks robust forensics JPEG compression

Attacking contrast enhancement forensics in digital images

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

Science China(Information Sciences) 2014年第5期57卷 170-182页

作者： CAO Gang ZHAO Yao ni rongrong TIAN HuaWei YU LiFang School of Computer Science Communication University of China Institute of Information Science Beijing Jiaotong University People's Public Security University of China

Currently,plenty of digital image forensic techniques have been proposed and used as diagnostic *** is urgent and significant to assess the reliability of such techniques applied in practical *** this paper,we investigate the security of existing digital image contrast enhancement(CE)forensic *** the standpoint of attackers,we propose two types of attacks,CE trace hiding attack and CE trace forging attack,which could invalidate the forensic detector and fabricate two types of forensic errors,*** CE trace hiding attack is implemented by integrating local random dithering into the design of pixel value *** CE trace forging attack is proposed by modifying the gray level histogram of a target pixel region to counterfeit peak/gap *** trace forging attack is typically applied to create sophisticated composite images which could deceive the prior CE-based composition *** experimental results demonstrate the efficacy of our proposed CE anti-forensic schemes.

关键词： digital forensics anti-forensics attack contrast enhancement composite image histogram

Lossless data hiding based on prediction-error adjustment

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science in China(Series F) 2009年第2期52卷 269-275页

作者： WENG ShaoWei ZHAO Yao ni rongrong PAN Jeng-Shyang Institute of Information Science Beijing Jiaotong University Beijing 100044 China Department of Electronic Engineering Kaohsiung University of Applied Sciences Kaohsiung 80778

A novel Iossless data hiding scheme based on a combination of prediction and the prediction-error adjustment （PEA） is presented in this paper. For one pixel, its four surrounding neighboring pixels are used to predict it and 1-bit watermark information is embedded into the prediction-error. In traditional approaches, for the purpose of controlling embedding distortion, only pixels with small predictionerrors are used for embedding. However, when the threshold is small, it is difficult to efficiently compress the location map which is used to identify embedding locations. Thus, PEA is introduced to make large prediction-error available for embedding while causing low embedding distortions, and accordingly, the location map can be compressed well. As a result, the hiding capacity is largely increased. A series of experiments are conducted to verify the effectiveness and advantages of the proposed approach.

关键词： reversible watermarking prediction PEA

Detection of Interpolation Using Correlation Coefficients 11th

在线全文

学校读者我要写书评

暂无评论

Detection of Interpolation Using Correlation Coefficients

门诊患者就医体验现状及满意评价——以某军队三甲医院为例

2012 IEEE 11th International Conference on Signal Processing(ICSP 2012)

作者： Hongjian Cao Yao Zhao rongrong ni Institute of information science Beijing Jiaotong University

ISBN: (纸本)9781467321969

Resampling detection is a very useful tool in digital image forensic. In this paper, we propose a new algorithm for detecting interpolation by using the periodicity characteristics hidden among the rows（or columns） of the image. The core of our algorithm is the use of correlation coefficients based on the observation that the correlation coefficients of the row（or column） vectors vary periodically in resampled image. In some images, the image contents themselves correlate periodically. To reduce this kind of interference and enhance the detection efficiency, we use the first derivatives signals and detect the image both horizontally and vertically under some condition. As experiments show, the proposed algorithm works well, and most of the resampling factors can be correctly determined with high accuracy.

关键词： correlation methods image sampling interpolation

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

中华灾害救援医学 2024年第1期11卷 11-15页

作者：何娟玲倪荣容吴思峰王红迁罗旭中国人民解放军陆军军医大学重庆400038 中国人民解放军陆军军医大学第一附属医院重庆400038 中国人民解放军陆军军医大学第一附属医院江北院区重庆400000

目的探究现阶段医院门诊患者就医体验满意度及其相关影响因素.方法问卷调查2023年1月、6月、9月就诊于重庆市某军队三甲医院的门诊患者,共收集到2517份有效问卷,使用EXCEL、SPSS软件进行数据统计和分析.结果门诊患者对医院门诊的满意度... 详细信息

目的探究现阶段医院门诊患者就医体验满意度及其相关影响因素.方法问卷调查2023年1月、6月、9月就诊于重庆市某军队三甲医院的门诊患者,共收集到2517份有效问卷,使用EXCEL、SPSS软件进行数据统计和分析.结果门诊患者对医院门诊的满意度调查显示,医疗技术、诊疗性价比及总体满意度得分最高,为16.81分(84.05%),就诊设施与环境满意度评分为24.76分(82.53%),各环节工作人员服务态度满意度评分为20.48分(81.92%),各检查候诊环节满意度评分为21.91分(62.60%).其中,放射检查出报告时间和门诊超声科检查等候时间的满意度评分较低.就诊设施与环境满意度中,医院公布的投诉部门、接待时间及联系电话等信息清晰度评价较低.药房人员向患者介绍药物用法、用量、注意事项等的满意度评分也较低;"导诊人员为您提供的指引服务满意度""就诊等候区秩序满意度""药房人员向您介绍药物用法、用量、注意事项等满意度""医生向您询问病情和进行身体检查的耐心细致程度满意度"对本次总体评价满意度有明显影响(P<0.05).结论门诊患者的就医体验满意感知是一个多维度的概念,医疗机构应从医生专业水平、服务态度、医疗技术信任度和环境设施等方面全面提升服务质量.同时,医疗机构应定期开展患者满意度调查,及时了解患者需求和反馈,有针对性地改进服务质量,以满足患者日益增长的健康需求.

关键词：门诊就医满意