Search

Recent works have demonstrated the great performance of forgery image forensics based on deep learning, but there is still a risk that detectors could be susceptible to unknown illegal attacks, raising growing security concerns. This paper starts from the perspective of reverse forensics and explores the vulnerabilities of current image manipulation detectors to achieve targeted attacks. We present a novel reverse decision aggregate gradient attack under low-frequency constraints (RevAggAL). Specifically, we first propose a novel pixel reverse content decision-making (PRevCDm) loss to optimize perturbation generation with a specific principle more suitable for segmenting manipulated regions. Then, we introduce the low-frequency component to constrain the perturbation into more imperceptible details, significantly avoiding the degradation of image quality. We also consider aggregating gradients on model-agnostic features to enhance the transferability of adversarial examples in black-box scenarios. We evaluate the effectiveness of our method on three representative detectors (ResFCN, MVSSNet, and OSN) with five widely used forgery datasets (COVERAGE, COLUMBIA, CASIA1, NIST 2016, and Realistic Tampering). Experimental results show that our method improves the attack success rate (ASR) while ensuring better image quality. [ABSTRACT FROM AUTHOR]

The color filter array of the camera is an effective fingerprint for digital forensics. Most previous color filter array (CFA)-based forgery localization methods perform under the assumption that the interpolation algorithm is linear. However, interpolation algorithms commonly used in digital cameras are nonlinear, and their coefficients vary with content to enhance edge information. To avoid the impact of this impractical assumption, a CFA-based forgery localization method independent of linear assumption is proposed. The probability of an interpolated pixel value falling within the range of its neighboring acquired pixel values is computed. This probability serves as a means of discerning the presence and absence of CFA artifacts, as well as distinguishing between various interpolation techniques. Subsequently, curvature is employed in the analysis to select suitable features for generating the tampering probability map. Experimental results on the Columbia and Korus datasets indicate that the proposed method outperforms the state-of-the-art methods and is also more robust to various attacks, such as noise addition, Gaussian filtering, and JPEG compression with a quality factor of 90. [ABSTRACT FROM AUTHOR]

Recently, with the emergence of many image editing tools (photoshop, Topaz studio, etc.), the authenticity of images has been severely challenged. However, the performance of some existing traditional feature extraction methods and detection methods based on convolutional neural network (CNN) is poor, and the information provided by the features extracted from the network is limited and single. In this paper, an end-to-end ringed residual U-Net is proposed to detect image splicing forgery by blending features of non-natural regions. Some regions with significant differences from the image background are defined as non-natural regions(such as the irregular border at the splicing of images). In this paper, a feature enhancement module for non-natural regions is constructed, which the image through the pooling of four different scales, and these features are then combined with the original image and input to the backbone network for processing, aiming to highlight regions of the image that differ significantly from the background. Therefore, after adding the feature enhancement module for non-natural regions to the end-to-end ring residual U-Net, more attention will be paid to the tampering regions in the feature extraction stage, image manipulation detection and localization will also become more accurate. Compared with some mainstream methods, this method achieves better performance on the three standard datasets(CASIA2.0, NIST2016, COLUMBIA). In addition, it has excellent robustness under JPEG compression attack and noise corruption attack. [ABSTRACT FROM AUTHOR]

Aiming at the problems that existing methods lose a lot of spatial information and are easily interfered by image content, this paper proposes an end-to-end trainable high-resolution noise artifact tracking network (HRNAT-Net) for image splicing forgery detection. The network adopts HRNet as the network backbone, which can always retain high-resolution features, thereby effectively reducing the loss of important spatial information such as edge features. Besides, the network utilizes dilated convolution, which further preserves rich tampering information. Noise information are used as auxiliary information to build a dual-stream network to exploit visual and noise features simultaneously. Through multiple multi-scale feature fusion, the expressive ability of features is further enhanced. Finally, the visual features and noise features of corresponding resolutions are concatenated, and through multi-scale feature fusion, visual features and noise features are combined to locate the tampered area. The proposed network effectively solves the loss of spatial information, and simultaneously seeks forensic clues from the visual and noise levels. We evaluate the network performance on the CASIA v2.0 dataset and the Columbia dataset using metrics such as pixel-level Precision, Recall, and F1, and the detection accuracy (F1) reaches 0.845 and 0.950, respectively. Experimental results show that the proposed network outperforms state-of-the-art methods and has good robustness to JPEG compression, Gaussian noise, and resizing attacks. [ABSTRACT FROM AUTHOR]

With the increasing technology, digital images have become a widely used data type in crucial areas such as medical journalism and law. Since it is used in such important areas, it has become questionable whether digital images are original or not. Image splicing forgery is one of the most common forgery types applied to digital images. This work proposes a new image splicing detection and localization method. Our motivation is to reveal the boundaries of forgery by using statistical features of the image blocks. The proposed method has two main stages: training and localizing. In both phases, image blocks that contain edge information are used because the splicing operation causes some inconsistency on the edges. In the training stage, original blocks are selected from the regions that include original boundaries, and forged blocks are selected from the areas that contain splicing operation-induced edges. Transition probability matrices are calculated in eight directions to obtain the correlation of the borders between the neighbor blocks on original and splicing edges. These matrices are used as a feature for each block. The blocks are classified as authentic and spliced using SVM. A new post-processing step has been proposed to eliminate the false positives that may occur due to the presence of original regions that are likely to be detected as spliced edges in the image. The publicly available Columbia dataset has been used to show the effectiveness of the state-of-the-art and proposed method. The results indicate that the proposed method has performed well even under JPEG compression and Gaussian blurring attacks. [ABSTRACT FROM AUTHOR]

The detection and location of image splicing forgery are a challenging task in the field of image forensics. It is to study whether an image contains a suspicious tampered area pasted from another image. In this paper, we propose a new image tamper location method based on dual-channel U-Net, that is, DCU-Net. The detection framework based on DCU-Net is mainly divided into three parts: encoder, feature fusion, and decoder. Firstly, high-pass filters are used to extract the residual of the tampered image and generate the residual image, which contains the edge information of the tampered area. Secondly, a dual-channel encoding network model is constructed. The input of the model is the original tampered image and the tampered residual image. Then, the deep features extracted from the dual-channel encoding network are fused for the first time, and then the tampered features with different granularity are extracted by dilation convolution, and then, the secondary fusion is carried out. Finally, the fused feature map is input into the decoder, and the predicted image is decoded layer by layer. The experimental results on Casia2.0 and Columbia datasets show that DCU-Net performs better than the latest algorithm and can accurately locate tampered areas. In addition, the attack experiments show that DCU-Net model has good robustness and can resist noise and JPEG recompression attacks. [ABSTRACT FROM AUTHOR]

The fake images and visuals can easily spread among social media users and they largely impact decisionmaking in society. Image forgery has become increasingly common as more non-professionals have access to image manipulation tools. These fake images are so sneaky that an ordinary person cannot guess them. Through social media, such photos are utilized to promote erroneous information in society. Image forgery detection is about segmenting the forged part from the images, primarily a region of interest. This paper suggests a unique method that depends on a dual attention network to detect forged segments. This network contains self-attention modules that contribute to extracting and matching features in the channel and spatial domains. These features help locate and identify the forged portions of digital images at various scales and channels. This experimental study uses typical datasets such as CASIA V1.0, CASIA V2.0, and Columbia. Proposed IFLNet technique outperforms other advanced techniques with a precision of 96 %, recall rate of 95 %, accuracy rate of 98 %, F1-score of 96 % and IoU score of 92 % for Columbia dataset and correspondingly other two datasets also. [ABSTRACT FROM AUTHOR]

Today, image forgery is common due to the massification of low-cost/high-resolution digital cameras, along with the accessibility of computer programs for image processing. All media is affected by this issue, which makes the public doubt the news. Though image modification is a typical process in entertainment, when images are taken as evidence in a legal process, modification cannot be considered trivial. Digital forensics has the challenge of ensuring the accuracy and integrity of digital images to overcome this issue. This investigation introduces an algorithm to detect the main types of pixel-based alterations such as copy-move forgery, resampling, and splicing in digital images. For the evaluation of the algorithm, CVLAB, CASIA V1, Columbia, and Columbia Uncompressed datasets were used. Of 7100 images evaluated, 3666 were unaltered, 791 had resampling, 2213 had splicing, and 430 had copy-move forgeries. The algorithm detected all proposed forgery pixel methods with an accuracy of 91%. The main novelties of the proposal are the reduced number of features needed for identification and its robustness for the file format and image size. [ABSTRACT FROM AUTHOR]

With the recent internet connectivity revolution, and the fast-growing prevalence of camera-enabled devices, images play a vital role in several fields of modern life. Photos, which often have been seen as evidence in courts, are nowadays subject to more sophisticated tricky forgery. To detect the image stitching between originally unassociated people/scenes and other combining forgery, an algorithm used to extract multiple specific image features, such as grayscale, complementary color wavelet (CCW) based chroma, sharpness, and natural scene statistics (NSS), is first presented in this paper. It is illustrated that a random forest model can be trained by these extracted features and then be employed to classify the stitching tampered/untampered images. The experimental results show that the proposed algorithm favorably outperforms the techniques reported in the literature, and achieves a state-of-the-art performance with higher accuracy values of 91%, 95.24%, and 88.02% on the Tampering ImageNet, Columbia, and CASIA ITDE V2.0 datasets, respectively. The precision, recall, and F1-score were also improved to a certain extent. [ABSTRACT FROM AUTHOR]

With the technological advancements of the modern era, the easy availability of image editing tools has dramatically minimized the costs, expense, and expertise needed to exploit and perpetuate persuasive visual tampering. With the aid of reputable online platforms such as Facebook, Twitter, and Instagram, manipulated images are distributed worldwide. Users of online platforms may be unaware of the existence and spread of forged images. Such images have a significant impact on society and have the potential to mislead decision-making processes in areas like health care, sports, crime investigation, and so on. In addition, altered images can be used to propagate misleading information which interferes with democratic processes (e.g., elections and government legislation) and crisis situations (e.g., pandemics and natural disasters). Therefore, there is a pressing need for effective methods for the detection and identification of forgeries. Various techniques are currently employed for the identification and detection of these forgeries. Traditional techniques depend on handcrafted or shallow-learning features. In traditional techniques, selecting features from images can be a challenging task, as the researcher has to decide which features are important and which are not. Also, if the number of features to be extracted is quite large, feature extraction using these techniques can become time-consuming and tedious. Deep learning networks have recently shown remarkable performance in extracting complicated statistical characteristics from large input size data, and these techniques efficiently learn underlying hierarchical representations. However, the deep learning networks for handling these forgeries are expensive in terms of the high number of parameters, storage, and computational cost. This research work presents Mask R-CNN with MobileNet, a lightweight model, to detect and identify copy move and image splicing forgeries. We have performed a comparative analysis of the proposed work with ResNet-101 on seven different standard datasets. Our lightweight model outperforms on COVERAGE and MICCF2000 datasets for copy move and on COLUMBIA dataset for image splicing. This research work also provides a forged percentage score for a region in an image. [ABSTRACT FROM AUTHOR]

Digital passive image forgery methods are extensively used to verify the authenticity and integrity of images. Splicing and copy-move are the most common types of passive digital image forgeries. Several approaches have been proposed to detect these forgeries separately, but very few approaches are available that can detect them simultaneously. However, a more efficient method is still in demand to meet the day-to-day challenges to detect these forgeries at the same time. So, a passive hybrid approach based on discrete fractional cosine transform (DFrCT) and local binary pattern (LBP) is proposed to detect copy-move and splicing forgeries simultaneously. The extra parameter i.e. fractional parameter of DFrCT is utilized to enhance the accuracy and LBP is used to highlight the tampering artifacts effectively. Then, a support vector machine (SVM) is employed to categorize the images into authentic, copy-move, and spliced images. Next, localization is performed on both the copy-move and spliced images to localize the duplicated areas in the image. Experiments on six benchmark datasets, namely, CASIA v1.0, GRIP, CASIA v2.0, IMD, COVERAGE, and Columbia, attain accuracy rates of 99.67%, 99.23%, 99.76%, 98.81%, 95%, and 98.17%, respectively. To validate the effectiveness of the proposed method, comparative analysis has been performed with existing methods in terms of ROC, precision, recall, F1 score, F2 score, and accuracy. Moreover, the robustness of the proposed work is tested under rotation attack and better results are attained in comparison to the existing techniques. [ABSTRACT FROM AUTHOR]

With the rapid development of image processing technology, it has become increasingly easy to manipulate images, which poses a threat to the stability and security of people's lives. Recent methods have proposed the fusion of RGB and noise features to uncover tampering traces. However, these approaches overlook the characteristics of features at different levels, leading to insufficient feature fusion. To address this problem, this paper proposes a double-stream multilevel feature fusion network (DMFF-Net). Unlike the traditional feature fusion approach, DMFF-Net adopts a graded feature fusion strategy. It classifies features into primary, intermediate, and advanced levels and introduces the Primary Feature Fusion Module (PFFM) and the Advanced Feature Fusion Module (AFFM) to achieve superior fusion results. Additionally, a multisupervision strategy is employed to decode the fused features into level-specific masks, including boundary, regular, and refined masks. The DMFF-Net is validated on publicly available datasets, including CASIA, Columbia, COVERAGE, and NIST16, as well as a real-life manipulated image dataset, IMD20, and achieves AUCs of 84.7%, 99.6%, 86.6%, 87.4% and 82.8%, respectively. Extensive experiments show that our DMFF-Net outperforms state-of-the-art methods in terms of image manipulation localization accuracy and exhibits improved robustness. [Display omitted] • RGB features are fused with other modal features in a way to better explore the traces of tampering. • Failure to consider the characteristics of different levels of features may lead to inadequate feature fusion. • The features are classified into three levels: primary, intermediate and advanced. • Based on the features at different levels, two feature fusion modules are proposed to achieve better feature fusion. • The multi-supervision strategy decodes the fused features into corresponding masks by level to obtain boundary masks, regular masks, and refined masks. [ABSTRACT FROM AUTHOR]

With the technology progress, a plethora of freely accessible software has questioned the authenticity of digital images. This field is continuously creating challenges for researchers to ascertain the integrity of images. Hence, there is a need to improve the performance of forgery detection algorithms from time to time. This paper is focused on the detection of splicing forgery because it is one of the most frequently used image manipulation techniques. In the proposed scheme, Markov features in both Discrete Wavelet Transform (DWT) and Local Binary Pattern (LBP) domains are extracted and combined for the detection of image splicing. Three-level DWT is applied to the source image by the means of discrete Haar wavelet. The image is split in to high and low-frequency sub-bands after applying one level DWT. Furthermore, low-frequency sub-band is decomposed twice to obtain three-level DWT, which leads to more information and less amount of noise. The efficacy of the proposed scheme has been appraised on six benchmark datasets i.e. CASIA v2.0, DVMM, IFS-TC, CASIA v1.0, Columbia, and DSO-1. Moreover, the SVM classifier is trained to classify the images as tampered or authentic. The effectiveness of the proposed scheme is evaluated based on various performance parameters such as accuracy, sensitivity, specificity, and informedness. The proposed results show improved accuracy i.e. 99.69%, 99.76%, 97.80%, 98.61%, 96.90%, and 92.50% on CASIA v1.0, CASIA v2.0, DVMM, Columbia, IFS-TC, and DSO-1, respectively, in comparison to other existing approaches. [ABSTRACT FROM AUTHOR]

Manipulating digital images is not often a difficult task due to the rapid development of software and image manipulation techniques. Hence, there is no need for professional skills or training. When used as an artistic tool, it is completely harmless, but when these images can be presented in judicial system as evidence or for the creation of political associations, as well as, using them in legal documents, electronic money circulation or press; in these cases, the distinction between an original image and a forgery image is very important. In order to solve the problem in this research using a Discrete Wavelet Transform (DWT), which is performed by decomposing a signal into smaller and smaller details, as well as, the use of periodic patterns in the histogram generated by double compression with different coefficients, significant improvements were made in terms of reducing computations and increasing the detection rate of forging areas. Many of the proposed methods for detecting image forgery use a feature extraction model from a valid and manipulated dataset and then classify them using machine learning with the aim of optimizing the accuracy. In this research, following the extraction of features in the proposed method, using the SVM classification identifies image forgery and then identifies the forging area after it detects the falsification or originality of the image. The results of this study indicate 97.98% accuracy in the Columbia database and 98.1% in the IFS-TC database. [ABSTRACT FROM AUTHOR]

Powerful image editing software makes the process of image manipulation easy, which increases security risks. Therefore, it is urgent to locate the tampered region to uncover the processing history. However, previous research has mainly focused on feature extraction, with little discussion on classifiers for classifying original and tampered regions. We improve the splicing forgery localization method from a statistical perspective. The refined color filter array feature provides sufficient data for statistical analysis, and the geometric mean is used to eliminate anomalous data. Subsequently, a classifier that combines the expectation–maximization algorithm and Bayesian theory is proposed to binarize the original and tampered regions. The two steps of feature extraction and feature classification are associated from a statistical perspective, which ultimately improve the performance of the method effectively. Extensive experimental results demonstrate that the refined feature used for classification has several advantages, and the proposed classifier is appropriate for handling complex image manipulation across different statistical distributions. The proposed method outperforms the reference methods in both the Columbia and Korus datasets. [ABSTRACT FROM AUTHOR]