Figure 1 - uploaded by Akram Hatem Saber
Content may be subject to copyright.
![Figure 1. Categories of image forgeries [17]](profile/Akram-Hatem-Saber-2/publication/342488952/figure/fig3/AS:997242391523330@1614772522504/Categories-of-image-forgeries-17_Q320.jpg)
![Figure 2. Digital watermarking [18]](profile/Akram-Hatem-Saber-2/publication/342488952/figure/fig1/AS:906863445041152@1593224502942/Digital-watermarking-18_Q320.jpg)
![Figure 3 (a). Original image and (b). Duplicated image [32]](profile/Akram-Hatem-Saber-2/publication/342488952/figure/fig2/AS:906863449231363@1593224503053/a-Original-image-and-b-Duplicated-image-32_Q320.jpg)
Similar publications
![Figure 4: Flow of digital watermarking active forensics algorithm [12]](publication/361750934/figure/fig4/AS:11431281113389059@1673892435890/Flow-of-digital-watermarking-active-forensics-algorithm-12_Q320.jpg)
![Figure 5: Flow of digital signature active forensic algorithm [13]](publication/361750934/figure/fig5/AS:11431281113422109@1673892436174/Flow-of-digital-signature-active-forensic-algorithm-13_Q320.jpg)
![Figure 4: The architecture of the proposed 10-layer CNN Wu et al. [110]...](publication/366762561/figure/fig2/AS:11431281110523922@1672594195808/The-architecture-of-the-proposed-10-layer-CNN-Wu-et-al-110-also-proposed-end-to-end_Q320.jpg)
Citations
... Abbas et al., 2021 [21], performed experiments using two deep learning models for copytransfer image forgery: small VGGNet and Mobile Net V2. Saber et al., 2020 [22], investigated all types of forgery (digital watermarks, digital signatures, image linking, image manipulation, and copy-transfer forgery). ...
Currently, video and digital images possess extensive utility, ranging from recreational and social media purposes to verification, military operations, legal proceedings, and penalization. The enhancement mechanisms of this medium have undergone significant advancements, rendering them more accessible and widely available to a larger population. Consequently, this has facilitated the ease with which counterfeiters can manipulate images. Convolutional neural network (CNN)-based feature extraction and detection techniques were used to carry out this task, which aims to identify the variations in image features between modified and non-manipulated areas. However, the effectiveness of the existing detection methods could be more efficient. The contributions of this paper include the introduction of a segmentation method to identify the forgery region in images with the U-Net model’s improved structure. The suggested model connects the encoder and decoder pipeline by improving the convolution module and increasing the set of weights in the U-Net contraction and expansion path. In addition, the parameters of the U-Net network are optimized by using the grasshopper optimization algorithm (GOA). Experiments were carried out on the publicly accessible image tempering detection evaluation dataset from the Chinese Academy of Sciences Institute of Automation (CASIA) to assess the efficacy of the suggested strategy. The results show that the U-Net modifications significantly improve the overall segmentation results compared to other models. The effectiveness of this method was evaluated on CASIA, and the quantitative results obtained based on accuracy, precision, recall, and the F1 score demonstrate the superiority of the U-Net modifications over other models.
... This 55 method enhances or reduces the feature of pixels on the image [13]. Also, it is a popular method in photo editing applications and magazines [2]. This approach makes images more attractive by increasing or decreasing certain features such as pixel color. ...
... Therefore, many studies have been presented to detect a forgery in two main categories: traditional and deep learning meth- 70 ods. Some excellent reviews of the two methods can be found in [2,16]. Despite the appropriate review articles in the forgery detection field, the purpose of our review article is to comprehensively examine two methods of forgery detection to compare and discover their strengths, weaknesses, and challenges. ...
... There are various ways of image tampering, but different tampering methods leave special traces in the image [2]. Digital image forensics technologies determine whether the image has been tampered with by analysing the noise characteristics and statistical characteristics inside the image [3]. According to whether image prepossessing is required, digital image forensics technology can be divided into two categories [2]: active forensics and passive forensics. ...
The architectures of many state‐of‐the‐art local tempering detection models are complexity, and the training process of those models is also time‐consuming. Therefore, this paper constructs a lightweight local tampering detection method based on the convolutional network MobileNetV2 and a dual‐stream network. Specifically, the algorithm first improves the MobileNetv2, which not only reduces the multiple of its downsampling operator to retain richer traces of image tampering, but also introduces the dilated convolution in it to expand the receptive field of feature maps. The dual‐stream network uses RGB stream to extract image tampering features such as strong contrast difference and unnatural tampered boundaries, and implements spatial rich model (SRM) stream to extract image tampered area and noise features of real area. Finally, the features extracted from two streams are fused through an improved attention mechanism called parallel convolutional block attention module (CBAM), which can improve the sensitivity of the model to important features in RGB and SRM. The experimental results show that the proposed algorithm still has higher positioning accuracy than some existing algorithms, while achieving lightweight.
... However, these studies required a manual investigation and extraction of representative hand-crafted image features based on specific characteristics of the dataset under consideration, which was complicated and time-consuming. Some common techniques that are usually used to perform image forgery analysis are local noise estimation, illumination analysis, color filter array (CFA), steganalysis features, and double JPEG localization [7]. For instance, Yao et al. revealed inconsistent noise levels from manipulated regions of RGB images using the noise level function (NLF) approach. ...
Image manipulation of the human face is a trending topic of image forgery, which is done by transforming or altering face regions using a set of techniques to accomplish desired outputs. Manipulated face images are spreading on the internet due to the rise of social media, causing various societal threats. It is challenging to detect the manipulated face images effectively because (i) there has been a limited number of manipulated face datasets because most datasets contained images generated by GAN models; (ii) previous studies have mainly extracted handcrafted features and fed them into machine learning algorithms to perform manipulated face detection, which was complicated, error-prone, and laborious; and (iii) previous models failed to prove why their model achieved good performances. In order to address these issues, this study introduces a large face manipulation dataset containing vast variations of manipulated images created and manually validated using various manipulation techniques. The dataset is then used to train a fine-tuned RegNet model to detect manipulated face images robustly and efficiently. Finally, a manipulated region analysis technique is implemented to provide some in-depth insights into the manipulated regions. The experimental results revealed that the RegNet model showed the highest classification accuracy of 89% on the proposed dataset compared to standard deep learning models.
... As a result, image forgery detection techniques are gaining concern and importance in society [11]. Two incidences of image forgery are discussed in Figs. 1 [90] and 2 [7] and are included here to describe the severity of the issue (Fig. 2). ...
The digital image proves critical evidence in the fields like forensic investigation, criminal investigation, intelligence systems, medical imaging, insurance claims, and journalism to name a few. Images are an authentic source of information on the internet and social media. But, using easily available software or editing tools such as Photoshop, Corel Paint Shop, PhotoScape, PhotoPlus, GIMP, Pixelmator, etc. images can be altered or utilized maliciously for personal benefits. Various active, passive and other new deep learning technology like GAN approaches have made photo-realistic images difficult to distinguish from real images. Digital image tamper detection now focuses on determining the authenticity and consistency of digital photos. The major research problems use generic solutions and strategies, such as standardized data sets, benchmarks, evaluation criteria and generalized approaches.This paper overviews the evaluation of various image tamper detection methods. A brief discussion of image datasets and a comparative study of image criminological (forensic) methods are included in this paper. Furthermore, recently developed deep learning techniques along with their limitations have also been addressed. This study aims to comprehensively analyze image forgery detection methods using conventional and advanced deep learning approaches.
... Standardized evaluation procedures and benchmarks [90], [94]- [96], [98], [100], [101], [104], [109]- [114], [116], [117], [123] Explore the use of novel AI methods and novel data types [88], [91], [93], [95], [99], [100], [103], [104], [106], [107], [109], [110], [112], [113], [115], [118], [121]- [124] Robust pre-processing and feature extraction [90], [91], [94], [97], [99], [101], [102], [105], [106], [109], [115], [117], [118], [121], [123], [124] Reduce training and data acquisition overheads [89], [91], [93], [95], [106], [110]- [112], [114], [118], [119], [121] More comprehensive outcome readability [90], [93], [99], [101], [111], [115], [116] Increased effort to circumventing antiforensic techniques [87], [90], [91], [96], [101], [109], [111], [115], [118], [120], [123] Rigorous mechanisms to ensure protection/watermarking [96], [104] Analyse multiple threats/tampering at once [90]- [92], [95], [96], [107], [108], [110], [112], [113], [116], [119], [123] Reliable detection with real data and dynamic contexts [91], [110], [120] ...
Due to its critical role in cybersecurity, digital forensics has received significant attention from researchers and practitioners alike. The ever increasing sophistication of modern cyberattacks is directly related to the complexity of evidence acquisition, which often requires the use of several technologies. To date, researchers have presented many surveys and reviews on the field. However, such articles focused on the advances of each particular domain of digital forensics individually. Therefore, while each of these surveys facilitates researchers and practitioners to keep up with the latest advances in a particular domain of digital forensics, the global perspective is missing. Aiming to fill this gap, we performed a qualitative review of all the relevant reviews in the field of digital forensics, determined the main topics on digital forensics topics and identified their main challenges. Despite the diversity of topics and methods, there are several common problems that are faced by almost all of them, with most of them residing in evidence acquisition and pre-processing due to counter analysis methods and difficulties of collecting data from devices, the cloud etc. Beyond pure technical issues, our study highlights procedural issues in terms of readiness, reporting and presentation, as well as ethics, highlighting the European perspective which is traditionally stricter in terms of privacy. Our extensive analysis paves the way for closer collaboration among researcher and practitioners among different topics of digital forensics.
... Dixit and Bag [32] proposed a complex framework that utilized keypoints matching using K-nearest neighbor via K-d tree to detect forged images. Abbas et al. [33]performed experiments using two deep learning models; smaller VGGNet and Mobile Net V2 for copy-move image forgery.In another survey,Saber et al. [34]discussedall types of forgeries, i.e., digital watermarking, digital signature, image splicing, image retouching and copy-move forgery. They discussed deep learning and CNNbased techniques. ...
In this digital era, forgery in images is very common, where copy-move and splicing forgery are the most popular types of image forgeries. In the current literature, most of the existing techniques detect these types of forgeries. However, most researchers have targeted only JPEG compressed images. Though, digital forensic techniques should not be particular to any image format. In deep learning, the convolutional neural network (CNN) and autoencoder are very popular methods to extract complex visual features in digital images. In the proposed method, multiple structures stacked autoencoders (SAE) are introduced for forgery detection in various image compression techniques, where the pre-trained AlexNet and VGG16 are utilized for image features extraction. The Ensemble Subspace Discriminant classifier is utilized for authentic and forged image classification. We performed an extensive ablation study on two CASIA datasets, where the results with two autoencoders and AlexNet features are dominant over all architectures and state-of-the-art methods, it achieved 95.9% accuracy for JPEG images and 93.3% for TIFF images.
... Digital forensics in the context of multimedia has received substantial attention from the research community. In this regard, image forgery detection [69,78,211,235,2,42,89,178,189,236,19,71,45,22,119,25] is one of the most explored topics not only in the multimedia context but across all digital forensics research, according to the number of survey publications available in the literature (see Section 3). Other image forensics surveys analysed topics such as hyperspectral image [124,69], image authentication [134], the affectation of noise in images [115] and image steganalysis [61,117,140,230]. ...
... Standardized evaluation procedures and benchmarks [235,42,178,134,236,202,128,70,94,192,230,71,63,31,78] Explore the use of novel AI methods and novel data types [235,233,38,134,61,117,211,202,192,230,71,45,199,69,156,25,63,208,124] Robust pre-processing and feature extraction [233,38,2,42,115,61,236,19,211,202,128,230,45,199,156] Reduce training and data acquisition overheads [38,61,196,94,192,189,71,45,199,25,31] More comprehensive outcome readability [42,236,211,70,94,156,25] More focus on anti-forensics mechanisms [42,89,178,236,202,94,230,45,22,199,156] Rigorous mechanisms to ensure protection/watermarking [178,134] Analyse multiple threats/tampering at once [178,117,236,202,196,70,192,71,45,119,63,140] Reliable detection with real data and dynamic contexts [71,45,22] ...
Due to its critical role in cybersecurity, digital forensics has received much focus from researchers and practitioners. The ever increasing sophistication of modern cyberattacks is directly related to the complexity of evidence acquisition, which often requires the use of different technologies. To date, researchers have presented many surveys and reviews in the field. However, such works focused on the advances of each domain of digital forensics individually. Therefore, while each of these surveys facilitates researchers and practitioners to keep up with the latest advances in a particular domain of digital forensics, the overall picture is missing. By following a sound research methodology, we performed a qualitative meta-analysis of the literature in digital forensics. After a thorough analysis of such literature, we identified key issues and challenges that spanned across different domains and allowed us to draw promising research lines, facilitating the adoption of strategies to address them.
... The passive solutions have been developed when the image retouching, copy-move, and splicing are applied to produce modified digital images. We recommend reviewing the work of Saber et al. [52], who has shown various approaches for detection techniques of tampering and forgery developed from 2005 to 2020. Also, we recommend the work developed by Thakur and Rohilla [61], which presents an overview of some techniques used for the manipulation detection of digital images. ...
It is proposed a forensic method for the capture device identification from digital images, which requires two elements: i) a digital image subject to controversy named disputed image and ii) a set of eligible capture devices with which the disputed image could have been shot. In order to define a device statistical fingerprint, a set of reference digital images is produced for each eligible capture device. The device statistical fingerprint is estimated averaging the statistical distribution of the photo response non-uniformity (PRNU) signal extracted from each set of reference digital images. Then, a comparison based on Kullback-Leibler divergence (KLD) is performed between the statistical fingerprint for each capture device and the statistical distribution of the PRNU signal extracted from the disputed image. Considering that KLD is a non-symmetric measure, the capture device, for which the smallest KLD has been estimated, will be chosen such as the one that shot the disputed image. The effectiveness of the proposed method was estimated by using a case study, which includes eight eligible capture devices, each of which shot thirty reference images and twenty disputed images. Then, the performance of the proposed method was like the performance of the methods that use peak-to-correlation energy as the discrimination criterion when they were applied to the case study. Finally, the proposed method offers two advantages; it reduces the processing time when the PRNU signal is extracted from digital image and it avoids the aberration produced by the lens into the PRNU signal.
... Digital image research is the latest field of research that aims to enable the authenticity of images. There are several methods proposed in digital forensics in recent years as shown in Figure 1 There are two types of the active methods that are digital watermarking and digital signature [2]. A digital watermark is added to the photo to identify copyright. ...
... Normally, Digital messages, digital documents, and software validity are checked using a digital signature. Since the receiver may assume that the message is created by the authorized sender, based on the On the other hand, passive methods include image retouching, image splicing, and copy-move attack [2]. Image retouching is considered a forgery of a minimally harmful form of the digital image. ...
With billions of digital images flooding the internet which are widely used and regards as the major information source in many fields in recent years. With the high advance of technology, it may seem easy to fraud the image. In digital images, copy-move forgery is the most common image tampering, where some object(s) or region(s) duplicate in the digital image. The important research has attracted more attention in digital forensic is forgery detection and localization. Many techniques have been proposed and many papers have been published to detect image forgery. This paper introduced a review of research papers on copy-move image forgery published in reputed journals from 2017 to 2020 and focused on discussing various strategies related with fraud images to highlight on the latest tools used in the detection. This article will help the researchers to understand the current algorithms and techniques in this field and ultimately develop new and more efficient algorithms of detection copy-move image.
