Steganography algorithms recognition based on match image and deep features verification

Steganography algorithms recognition is a sub-section of steganalysis. Analysis shows when a steganalysis detector trained on one cover source is applied to images from an unseen source, generally the detection performance decreases. To tackle with this problem, this paper proposes a steganalytic scheme for steganography algorithms recognition. For a given testing image, a match image of the testing image is achieved. The match image is generated by performing a Gaussian filtering on the testing image to remove the possible stego signal. Then the match image is embedded in with recognized steganography algorithms. A CNN model trained on a training set is used to extract deep features from testing image and match images. Computing similarity between features with inner product operation or weighted-χ², the final decision is made according to similarity between testing feature and each class of match feature. The proposed scheme can also detect steganography algorithms unknown in training set. Experiments show that, comparing with directly used CNN model, the proposed scheme achieves considerable improvement on testing accuracy when detecting images come from unseen source.     

用于失配隐写分析的对抗子领域自适应网络

当训练集数据和测试集数据来自不同的载体源时,即在载体源失配的条件下,通常会使一个表现优异的隐写分析器检测准确率下降。在实际应用中,隐写分析人员往往需要处理从互联网上采集的图像。然而,与训练集数据相比,这些可疑图像很可能具有完全不同的捕获和处理历史,导致隐写分析模型可能出现不同程度的检测性能下降,这也是隐写分析工具在现实应用中很难成功部署的原因。为了提高基于深度学习的隐写分析方法的实际应用价值,对测试样本信息加以利用,使用领域自适应方法来解决载体源失配问题,将训练集数据作为源领域,将测试集数据作为目标领域,通过最小化源领域与目标领域之间的特征分布差异来提高隐写分析器在目标领域的检测性能,提出了一种对抗子领域自适应网络（ASAN,adversarial subdomain adaptation network）。一方面从生成特征的角度出发,要求隐写分析模型生成的源领域特征和目标领域特征尽可能相似,使判别器分辨不出特征来自哪一个领域;另一方面从减小域间特征分布差异的角度出发,采用子领域自适应方法来减少相关子领域分布的非期望变化,有效地扩大了载体与载密样本之间的距离,有利于分类精度的提高。通过...     

针对特定测试样本的隐写分析方法

现今主流的图像隐写分析方法主要聚焦于设计检测特征,用以提高通用盲检测（UBD,Universal Blind Detection）模型的检测准确率,这类检测方法与待测图像无关,难以做到精准检测。本文在拥有大数据训练资源的前提下,研究了隐写对图像特征的影响,找出了隐写分析与图像特征之间的重要关系,基于此提出了一种为测试样本选择专用训练集的隐写分析方法。以经典的JPEG隐写算法nsF5和主流的JPEG隐写分析特征（CC-PEV、CC-Chen、CF^*、DCTR和GFR）为例组织实验,结果表明本文方法的检测准确率高于其他同类方法。     

JPEG隐密分析中的重压缩检测

重压缩检测是多级隐密分析中关键的预处理部分,高准确率的重压缩检测是隐密分析获得更高性能的重要前提条件.深入研究了重压缩对于JPEG图像各种特征的影响,基于此提出了一种融合直方图分布特征、Benford特征、DFT特征的重压缩检测算法.仿真实验表明,该算法具有更高的检测率,能够适用于JPEG多级隐密分析中的重压缩检测.     

基于优化Faster-RCNN的遥感影像飞机检测

针对传统飞机检测算法特征学习能力较弱,在背景复杂、目标密集、成像质量较差的遥感影像上检测精度较低的问题,提出了 一种基于Faster-RCNN(Faster-Regions with Convolutional Neural Network)框架的遥感影像飞机检测优化算法.以ResNet50为基础特征提取网络,引入空洞...     

分类与分割相结合的JPEG图像隐写分析

目的 隐写分析研究现状表明,与秘密信息的嵌入过程相比,图像内容和统计特性差异对隐写检测特征分布会造成更大的影响,这导致图像隐写分析成为了一个"相同类内特征分布分散、不同类间特征混淆严重"的分类问题。针对此问题,提出了一种更加有效的JPEG图像隐写检测模型。方法 通过对隐写检测常用的分类器进行分析,从降低隐写检测特征类内离散度的角度入手,将基于图像内容复杂度的预分类和图像分割相结合,根据图像内容复杂度对图像进行分类、分割,然后分别对每一类子图像提取高维富模型隐写检测特征,构建分类器进行训练和测试,并通过加权融合得到最终的检测结果。结果 在实验部分,对具有代表性的隐写检测特征集提取了两类可分性判据,对本文算法的各类别、区域所提取特征的可分性均得到明显提高,证明了模型的有效性。同时在训练、测试图像库匹配和不匹配的情况下,对算法进行了二分类测试,并与其他算法进行了性能比较,本文算法的检测性能均有所提高,性能提升最高接近10%。结论 本文算法能够有效提高隐写检测性能,尤其是在训练、测试图像库统计特性不匹配的情况下,本文算法性能提升更加明显,更适合于实际复杂网络下的应用。     

Surface defect detection of voltage-dependent resistors using convolutional neural networks

Surface defect detection is an important way to improve the production quality of voltage-dependent resistors (VDRs). To improve the accuracy and efficiency of VDR surface quality detection, an end-to-end surface quality detection method based on deep convolutional neural networks (CNNs) was proposed. The method includes four stages: data preparation, convolution neural network design, CNN training, and testing. First, images of VDRs were acquired from three perspectives, i.e., the front, back, and side, and then training, validation and testing sets were obtained. Second, the proposed CNN models for VDR surface defect detection were constructed. Third, during the training stage, the images with class labels from the established training sets were input to the proposed network for training and validation. Finally, in the testing stage, test images from a total of 408 samples of two VDR models were used to test the trained network. The sensitivity, specificity, accuracy, precision and F measure of the proposed algorithm were compared with those of state-of-the-art methods, and the experimental results showed that the proposed method has a high recognition speed and accuracy and meets the requirements of online real-time detection.

     

Feature mining and pattern classification for steganalysis of LSB matching steganography in grayscale images

In this paper, we present a scheme based on feature mining and pattern classification to detect LSB matching steganography in grayscale images, which is a very challenging problem in steganalysis. Five types of features are proposed. In comparison with other well-known feature sets, the set of proposed features performs the best. We compare different learning classifiers and deal with the issue of feature selection that is rarely mentioned in steganalysis. In our experiments, the combination of a dynamic evolving neural fuzzy inference system (DENFIS) with a feature selection of support vector machine recursive feature elimination (SVMRFE) achieves the best detection performance. Results also show that image complexity is an important reference to evaluation of steganalysis performance.     

基于少样本学习的通用隐写分析方法

近年来,深度学习在图像隐写分析任务中表现出了优越的性能.目前,大多数基于深度学习的图像隐写分析模型为专用型隐写分析模型,只适用于特定的某种隐写术.使用专用隐写分析模型对其他隐写算法的隐写图像进行检测,则需要该隐写算法的大量载密图像作为数据集对模型进行重新训练.但在实际的通用隐写分析任务中,隐写算法的大量载密图像数据集是难以得到的.如何在极少隐写图像样本的情况下训练通用隐写分析模型是一个极大的挑战.对此,受少样本学习领域研究成果的启发,提出了基于转导传播网络的通用隐写分析方法.首先,在已有的少样本学习分类框架上改进了特征提取部分,设计了多尺度特征融合网络,使少样本分类模型能够提取到更多的隐写分析特征,使其可用于基于秘密噪声残差等弱信息的分类任务;其次,针对少样本隐写分析模型难收敛的问题,提出了预训练初始化的方式得到具有先验知识的初始模型;然后,分别训练了频域和空域的少样本通用隐写分析模型,通过自测和交叉测试,结果表明,检测平均准确率在80%以上;接着,在此基础上,采用数据集增强的方式重新训练了频域、空域少样本通用隐写分析模型,使少样本通用隐写分析模型检测准确率与之前相比提高到87%以上;...     

Digital image steganalysis based on the reciprocal singular value curve

Embedding secret messages in steganographic approaches is similar to adding some weak noises to the original media. One of the traditional ways for image steganalysis is computing a feature sets using noise residuals. From another perspective, the disturbance of natural image statistics can be explored to extract the feature vector for steganalysis. In fact, the alteration of natural scene statistics can be investigated to reveal the presence of secret messages embedded in images. Hence, the feature vectors can be constructed using such changes. In the proposed scheme, the alteration of singular value curve is used to construct the steganalysis feature vector. Two spatial and JPEG based feature vectors are extracted in the proposed statistical exploitation. The experimental results illustrate the acceptable performance of the proposed feature vectors for both universal and JPEG based steganalysis methods.

     

A study on Subtractive Pixel Adjacency Matrix features

Subtractive Pixel Adjacency Matrix (SPAM) features perform well in detecting spatial-domain steganographic algorithm. Further, some methods of SPAM features can be applied to rich models and steganalysis based on deep learning. Therefore, this paper presents a study on SPAM features and it is divided into two parts: in the first part, impact of spatial-domain steganographic on difference between adjacent pixels is first analyzed. Then, three SPAM features are proposed with the same range of differences and different orders of Markov chain. Following that, the influences of order of Markov chain and range of differences on SPAM features are analyzed, and we find that detection accuracy of SPAM features increases with the range of differences increasing; in the second part, SPAM feature is first divided into several modules according to the conclusion. Then, taking detection accuracy of support vector machine (SVM) classifier and mutual information as metrics and module as a unit, a Novel Feature Selection (NFS) algorithm and an Improved Feature Selection algorithm are proposed. Experimental results show that the NFS algorithm can achieve higher detection accuracy than several existing algorithms.

     

局部特定空间关系统计特征的RVIN噪声检测器

目的 随机脉冲噪声（random-valued impulse noise，RVIN）检测器将局部图像统计值（local image statistics，LIS）作为图块中心像素点是否为噪声的判断依据，但LIS的描述能力较弱，在不同程度上制约了RVIN检测器的检测正确率，影响了后续开关型降噪模块的修复效果。为此，提出了一种基于局部特定空间关系统计特征的RVIN噪声检测器。方法 以局部中心像素点的8个邻域像素对数差值排序值（rank-ordered logarithmic difference，ROLD）并结合1个最小方向对数差值（minimum orientation logarithmic difference，MOLD）共9个反映局部特定空间关系的LIS统计值构成描述中心像素点是否为RVIN的噪声感知特征矢量，并通过在大量样本图块数据上提取的RVIN噪声感知特征矢量及其对应的噪声标签作为训练对（training pairs），训练获得一个基于多层感知网络（multi-layer perception，MLP）的RVIN噪声检测器。结果 对比实验从检测正确率和实际应用效果2个方面检验所提出的RVIN检测器的有效性，分别在10幅常用图像和50幅BSD （Berkeley segmentation data）纹理图像上进行测试，并与经典的脉冲噪声降噪算法中包含的噪声检测器以及MLPNNC （MLP neural network classifier）噪声检测器相比较，以漏检数、误检数和错检总数作为评价噪声检测正确率的指标。在常用图像集上本文所提RVIN检测器的漏检数和误检数较为平衡，在错检总数上排名处于所有对比算法中的前2名，为后续的降噪模块打下了很好的基础。在BSD纹理图像集上，将本文提出的RVIN检测器和GIRAF （generic iteratively reweighted annihilating filter）算法组合构成一种RVIN噪声降噪算法（proposed-GIRAF），proposed-GIRAF算法在50幅BSD图像上的峰值信噪比（peak signal-to-noise ratio，PSNR）均值在各个噪声比例下均取得了最优结果，与排名第2的对比算法相比，提升了0.471.96 dB。实验数据表明，所提出的RVIN噪声检测器的检测正确率优于现有的检测器，与修复算法联用后即可获得一种降噪效果更佳的开关型RVIN降噪算法。结论 本文提出的RVIN噪声检测器在各个噪声比例下具有鲁棒的预测准确性，配合GIRAF算法使用后，与经典的RVIN降噪算法相比，降噪效果最佳，具有很强的实用性。     

A sub-region one-to-one mapping (SOM) detection algorithm for glass passivation parts wafer surface low-contrast texture defects

Glass Passivation Parts (GPP) wafer texture defects are one of the most important factors affecting the accuracy of wafer defect detection. Template matching has local errors and low efficiency, and deep learning requires many training samples. In the early stage, defect training sample sets cannot be provided. This paper discusses the design of an effective GPP wafer grain region texture defect detection algorithm using a sub-region one-to-one mapping. A set of standard wafer datum is selected as the reference of grain region segmentation detection, and then the standard wafer images and test GPP wafer images are automatically calibrated and segmented, respectively. Then, a series of pre-processes were performed to equalize the sizes of the two grain-region images. Then the grain region was divided into an equal number of rectangular sub-regions of the same size according to the measurement precision requirement. The correlation degree of each test sub-region is judged by the designed three-channel RGB gray-scale similarity decision functions. Experiments show that the algorithm successfully achieved the necessary calibration and segmentation for the grain region. Compared with the template and histogram matching algorithms, the proposed method does not require a training set, the detection accuracy is significantly improved and the detection efficiency is up to 29.74 times better on average using the proposed algorithm.

     

基于图像复杂度和分类器融合的通用盲检测

现有通用盲检测方法大多没有考虑图像内容对隐写分析性能的影响,对此提出一种利用图像内容复杂度进行预分类和多分类器融合的隐写分析方法。在训练阶段,首先根据图像复杂度把图像分为若干类,然后针对每一类别训练分类器,并计算其模糊测度。在测试阶段,先判断待测图像的类别,然后将其送入到已训练好的各个分类器中,得到多个局部决策值,之后对其进行模糊积分融合得到最终的检测结果。实验结果表明,所提方法提升了通用盲检测算法在混合图像库中的检测性能。     

快速优化筛选多尺度矩形域的二进制描述

目的 为更好地兼顾基于手动设置的二进制特征描述子优越的实时性能和基于优化学习的二进制特征描述子鲁棒的区分性能,提出一种快速优化筛选多尺度矩形域的二进制描述算法(MRFO),运用于识别卫星装配时所需的典型工件目标。方法 按像素的灰度值和梯度方向划分图像并利用不同的高斯核函数进行平滑,建立多尺度的子图像集合;从多尺度的子图像中,快速通过约束条件提取候选矩形域;在训练阶段,通过优化学习计算候选矩形域的相关得分及最优阈值,筛选出其中具有强区分性和低相关性的集合;在测试阶段,计算筛选出的矩形域响应值并利用最优阈值进行二值化,将结果依次串联构成二进制描述向量。结果 实验通过ROC曲线图和80%精确率条件下的召回率统计结果证明MRFO描述算法具有优越的区分性能,平均的精确度能够高出对比算法8%~12%;并在真实的视频图像中利用MRFO描述算法识别出典型工件目标;根据训练阶段的执行时间只有传统优化学习算法的4.35%,只是在测试阶段略高于手动设置的二进制描述算法,证明MRFO描述算法具有优良的实时性能。结论 MRFO描述算法能够更好地克服各种视角、尺度和旋转变换的干扰以及周围相似背景信息的影响,准确识别出典型工件目标,有助于提高卫星的地面装配精度和效率,改善国内相关行业的自动化水平。普遍适用性较强,具有良好的应用前景。     

基于显著性检测的图像隐写分析方法

针对图像隐写分析难度大、现有的检测模型难以对图像隐写区域进行针对性检测的问题,提出了一种基于显著性检测的图像隐写分析方法.该方法利用显著性检测技术引导隐写分析模型更加关注图像隐写区域的特征.首先,显著性检测模块生成图像的显著性区域;其次,区域筛选模块筛选出与隐写区域重合度较高的显著性图,利用图像融合技术与原始图像进行融...     

基于多维梯度能量的空域隐写分析

隐写分析是信息安全领域一个新的研究热点,其中多数为针对特定隐藏算法的隐写分析算法,少数泛盲隐写分析算法又具有复杂度高正检率低的缺点.对图像像素值扣除受隐藏改变很小的高位后剩余的低位图像进行小波变换,恢复载体图像,利用梯度能量之差形成12维特征向量,最后通过支持向量机(SVM)进行训练分类.在3000幅训练图像库和3000幅测试图像库上(没有交集),分别对LSB(least significant bits)、自适应空域和BPCS(bit-plane complexity segmentation)等多种空域隐藏算法进行训练和测试.实验结果表明,算法有很好的检测性能,载密图像和载体图像的平均正检率分别为93.7%和96.2%.     

基于多样性特征的JPEG图像隐写分析

随着隐写分析技术的发展,新的特征提取算法不断出现,但目前还没有一种较好的通用特征能对JPEG图像进行有效的隐写分析。针对上述问题,提出一种从多域空间提取特征的通用隐写分析算法。采用残差共生矩阵与直方图统计函数计算DCT域、空域、小波域各域系数(像素)之间的依赖性关系,并结合校准方式从中提取特征。对多样性特征维数高的问题,采用前向选择与穷举结合的方法对其降维,以提高分类精度与节约分类时间。对4种典型的JPEG隐写算法在小嵌入率下进行实验,结果表明,与已有的检测方法相比,多域空间提取的多样性特征检测准确率能提高2%以上,适应性更广。     

数字视频区域篡改的检测与定位

目的 数字视频区域篡改是指视频帧图像的某个关键区域被覆盖或被替换,经过图像编辑和修补之后,该关键区域的修改痕迹很难通过肉眼来分辨。视频图像的关键区域承载了视频序列的关键语义信息。如果该篡改操作属于恶意的伪造行为,将产生非常严重的影响和后果。因此,视频区域篡改的检测与定位研究具有重要的研究价值和应用前景。方法 数字图像的复制粘贴篡改检测已经取得较大的研究进展,相关研究成果也很多。但是,数字视频区域篡改的检测与定位不能直接采用数字图像的复制—粘贴篡改取证算法。数字视频区域篡改检测与定位是数字视频被动取证研究领域中的一个新兴的研究方向,近年来越来越多的学者在该领域开展研究工作。目前,数字视频的区域篡改检测与定位研究还缺少完善的理论支撑和通用的检测与定位算法。在广泛调研最近几年的最新研究成果的基础上,对数字视频区域篡改的被动取证概念及重要性进行了介绍,将现有的数字视频区域篡改被动取证算法分为4类：基于噪声模式的算法、基于像素相关性的算法、基于视频内容特征的算法和基于抽象统计特征的算法。然后,对这些区域篡改检测与定位的算法进行对比分析,并介绍现有的视频区域篡改软件和算法,以及篡改检测算法的测试数据库。最后,对本研究领域存在的问题和挑战进行总结,并对未来的研究趋势进行展望。结果 选取了20篇文献中的18种算法,分别介绍每种算法的算法原理,并对这些算法进行对比分析。大部分的算法都宣称可以检测并定位出篡改可疑区域,但是检测和定位的精度、计算复杂度都各有差异。其中,基于时空域的像素相关性分析的算法具有较好的检测和定位效果,并且支持运动背景视频中的运动目标删除篡改检测和定位。基于光流平滑性异常的算法和基于运动目标检测的算法都是基于公开的视频篡改测试库进行比较测试的,两种算法都具有较好的检测和定位效果。基于隐写分析特征提取的集成分类算法虽然只能实现时域上的篡改定位,不能实现更精细的空域篡改定位,但是该算法为基于机器学习的大规模视频篡改取证研究提供了新思路和可能的发展方向,具有较大的指导意义。结论 由于视频编码压缩引入噪声,以及视频区域篡改软件工具和技术的改进,视频区域篡改检测和定位仍是一个极具挑战的课题。未来几年,基于视频内容特征和抽象统计特征的视频区域篡改检测和定位算法,有可能结合深度学习算法,得到进一步的研究和发展;相关的理论算法、系统模型和评价标准等研究成果将逐步完善。     

Image steganalysis with entropy hybridized with chaotic grasshopper optimizer

We propose a hybrid grasshopper optimizer to reduce the size of the feature set in the steganalysis process using information theory and other stochastic optimization techniques. This paper results from the stagnancy of local minima and slow convergence rate by the grasshopper algorithm in optimization problems. Therefore, we enhance the grasshopper optimization (GOA) performance with chaotic maps to make it Chaotic GOA (CGOA). Then, we combine the CGOA with adaptive particle swarm optimization (APSO) to make it Chaotic Particle-Swarm Grasshopper Optimization Algorithm (CPGOA). Next, we use the proposed optimizer with entropy to find the best feature subset of the original Subtractive Pixel Adjacency Model (SPAM) and Spatial Rich Model (SRM) feature set. Finally, the proposed technique is experimented with to detect the spatial domain steganography with different embedding rates on the BOSSbase 1.01 grayscale image database. The results show the improved results from the proposed hybrid optimizer compared to the original GOA and other state-of-the-art feature selection methods in steganalysis.