Search

In this paper, we propose a fine-grained deepfake detection network based on cross-modality attention. Specifically, it consists of three essential parts. The first is the feature extraction module, including learnable high-pass filters and Gabor convolutions. The former can adaptively extract different high-frequency components from original RGB images, while the latter can adaptively extract texture information at multiple directions and scales. The second is the shallow texture module, which is aimed to enhance texture and high-frequency features. The last is the cross-modality attention module that leverages the complementary information between the three modalities to promote feature learning and fusion. It can propagate the forgery patterns extracted from a specific modality to other modalities to learn previously undetected forgery traces. Moreover, we further introduce a novel diversity loss to penalize texture and frequency feature vectors for overlapping with each other. Our proposed method achieves the most advanced performance on multiple benchmark databases. [ABSTRACT FROM AUTHOR]

Creating security materials that carry distinct information with numerous optical characteristics enables enhanced anticounterfeiting levels to deter forgery ranging from currencies to pharmaceuticals. Circularly polarized long afterglow (CPLA) has attracted extensive attention in anticounterfeiting owing to its multiple and unusual optical properties (i.e., long afterglow and circular polarization), introducing intensity variation into the time dimension. However, constructing a visualized CPLA—meeting the requirements toward practical applications—is still a challenge. Here, a cementation‐coupling strategy is designed to combine chiral photonic membranes with phosphor films for building full‐colored CPLA architectures. The CPLA systems achieve desired performance with a largest afterglow dissymmetry value (gCPLA) of −0.67 and a longest visualization time (tvis) of 40 min simultaneously, satisfying practical demands for information security. As‐prepared CPLA materials are further patterned to work as optical labels in security fields. The resulting multidimensional variations in both time and intensity increase the complexity of information encryption, offering potentials for advanced security technologies. [ABSTRACT FROM AUTHOR]

Copy–move forgery is one of the most frequently used methods for producing fake digital images. Current algorithms for copy–move forgery detection (CMFD) cannot combine high accuracy and fast speed. Motivated by the observation, we propose a novel CMFD algorithm whose workflow is as follows. First, we use a keypoint-extraction method with the lowest contrast threshold to extract more keypoints from the input image. Second, a new technique, gradient-hash matching, finds pairs of similar keypoints quickly and effectively using a hash table, where the hash value is computed using gradients of keypoints. Subsequently, a new method called simplified cluster-based filtering exploits the density pattern of keypoints in the copy–move regions to remove false matching keypoint pairs. Finally, image matting is applied to indicate the forgery regions vividly. Extensive experiments show that not only the new algorithm is better than the state-of-the-art algorithms in terms of computation correctness, but also its computation time is drastically less. Commonly only about half time is needed. The relative time saving is even higher when images are larger. Different algorithms modules are compared through experiments to choose the best combination. [ABSTRACT FROM AUTHOR]

Banknote counterfeiting is a common practice worldwide. Due to the recent developments in technology, banknote imitation has become easier than before. There are different kinds of algorithms developed for the detection of counterfeit banknotes for different countries in the literature. The earlier algorithms utilized classical image processing techniques where the implementations of machine learning and deep learning algorithms appeared with the developments in the artificial intelligence field as well as the computer hardware. In this study, a novel convolutional neural networks-based deep learning algorithm has been developed that detects counterfeit Turkish Lira banknotes and their denominations using the banknote images taken under UV light. The results obtained with the proposed algorithm have been compared with the results obtained with state-of-the-art machine learning and deep learning algorithms. It is seen that the results obtained with the proposed algorithm are superior to the results obtained with the state-of-the-art machine learning and deep learning algorithms. The proposed algorithm achieved 100% accuracy on the training set and 99.95% accuracy on the test set while yielding low inference time with relatively few parameters and small file size. [ABSTRACT FROM AUTHOR]

Quantum secret sharing (QSS) is an important branch of quantum cryptography. Identity authentication is a significant means to achieve information protection, which can effectively confirm the identity information of both communication parties. Due to the importance of information security, more and more communications require identity authentication. We propose a d-level (t , n) threshold QSS scheme in which both sides of the communication use mutually unbiased bases for mutual identity authentication. In the secret recovery phase, the sharing of secrets that only the participant holds will not be disclosed or transmitted. Therefore, external eavesdroppers will not get any information about secrets at this phase. This protocol is more secure, effective, and practical. Security analysis shows that this scheme can effectively resist intercept–resend attacks, entangle–measure attacks, collusion attacks, and forgery attacks. [ABSTRACT FROM AUTHOR]

The generalization of face swapping detectors is necessary when applied to the practical applications. Although the most existing methods may achieve accuracy detection performance on the known forgeries, they fail to make the prediction when faced with unseen face manipulation methods. To alleviate the problem, we propose a novel and practical framework called Detection based on Identity Spatial Constraints with Weighted Frequency Division (DISC-WFD) through introducing the reference image, consisting of the backbone network, the shared Identity Semantic Encoder (ISE) and the corresponding Identity Spatial Constraint (ISC) branches. The ISE is utilized to measure the identity similarity between the input image and the reference image and generates identity spatial constraints. The constraints are imposed on ISC to focus on the high frequency and low-frequency identity-related areas for the discriminative information. The proposed method can significantly improve the performance and the generalization against the unseen manipulation methods. Furthermore, the cross-dataset experiments validate the superiority and the effectiveness of the DISC-WFD. [ABSTRACT FROM AUTHOR]

The technology for detecting forged images is good at detecting known forgery methods. It trains neural networks using many original and corresponding forged images created with known methods. However, when encountering unseen forgery methods, the technology performs poorly. Recently, one suggested approach to tackle this problem is to use a hand-crafted generator of forged images to create a range of fake images, which can then be used to train the neural network. However, the aforementioned method has limited detection performance when encountering unseen forging techniques that the hand-craft generator has not accounted for. To overcome the limitations of existing methods, in this paper, we adopt a meta-learning approach to develop a highly adaptive detector for identifying new forging techniques. The proposed method trains a forged image detector using meta-learning techniques, making it possible to fine-tune the detector with only a few new forged samples. The proposed method inputs a small number of the forged images to the detector and enables the detector to adjust its weights based on the statistical features of the input forged images, allowing the detection of forged images with similar characteristics. The proposed method achieves significant improvement in detecting forgery methods, with IoU improvements ranging from 35.4% to 127.2% and AUC improvements ranging from 2.0% to 48.9%, depending on the forgery method. These results show that the proposed method significantly improves detection performance with only a small number of samples and demonstrates better performance compared to current state-of-the-art methods in most scenarios. [ABSTRACT FROM AUTHOR]

In the field of forensic imaging, it is important to be able to extract a camera fingerprint from one or a small set of images known to have been taken by the same camera (or image sensor). Note that we are using the word fingerprint because it is a piece of information extracted from images that can be used to identify an individual source camera. This technique is very important for certain security and digital forensic situations. Camera fingerprint is based on a certain kind of random noise present in all image sensors that is due to manufacturing imperfections and is, thus, unique and impossible to avoid. Photo response nonuniformity (PRNU) has become the most widely used method for source camera identification (SCI). In this paper, a set of attacks is designed and applied to a PRNU-based SCI system, and the success of each method is systematically assessed both in the case of still images and in the case of video. An attack method is defined as any processing that minimally alters image quality and is designed to fool PRNU detectors or, in general, any camera fingerprint detector. The success of an attack is assessed as the increment in the error rate of the SCI system. The PRNU-based SCI system was taken from an outstanding reference that is publicly available. Among the results of this work, the following are remarkable: the use of a systematic and extensive procedure to test SCI methods, very thorough testing of PRNU with more than 2000 test images, and the finding of some very effective attacks on PRNU-based SCI. [ABSTRACT FROM AUTHOR]

With the rapid development of manipulation technologies, the generation of Deep Fake videos is more accessible than ever. As a result, face forgery detection becomes a challenging task, attracting a significant amount of attention from researchers worldwide. However, most previous work, consisting of convolutional neural networks (CNN), is not sufficiently discriminative and cannot fully utilise subtle clues and similar textures during the process of facial forgery detection. Moreover, these methods cannot simultaneously consider accuracy and time efficiency. To address such problems, we propose a novel framework named FPC‐Net to extract some meaningful and unnatural expressions in local regions. This framework utilises CNN, long short‐term memory (LSTM), channel groups loss (CG‐Loss) and adaptive feature fusion to detect face forgery videos. First, the proposed method exploits spatial features by CNN, and a channel‐wise attention mechanism is employed to separate channels. Specifically, with the help of channel groups loss, the channels are divided into two groups, each representing a specific class. Second, LSTM is applied to learn the correlation of spatial features. Finally, the correlation of features is mapped into other latent spaces. Through a lot of experiments, the results are that the detection speed of the proposed method reaches 420 FPS and the auc scores achieve best performance of 99.7%, 99.9%, 94.7%, and 82.0% on Raw Celeb‐DF, Raw Face Forensics++, F2F and NT datasets respectively. The experimental results demonstrate that the proposed framework has great time efficiency performance while improving the detection performance compared with other frame‐level methods in most cases. [ABSTRACT FROM AUTHOR]

In today's era, digital documents are used in official proceedings and various commercial online platforms. With the advent of Digital locker facilities, a digital document is admissible in various Government and private sectors. Due to this, the misuse of digital documents is increasing and criminal activity has surged during COVID times. Digital documents can be easily manipulated with the help of image-processing software applications. Manipulations include forgeries and duplication in the documents, counterfeiting in currency notes, and alteration and tampering in government documents or personal documents have increased manifolds. In the present study, a preliminary attempt has been made to analysed digitally manipulated documents by using different software which includes JPEG snoop, Adobe Photoshop CS5, and forensically beta software. Apart from that, in this paper new methodology to authenticate manipulations in scanned documents is devised. The authors were able to detect manipulations in altered documents like mark sheets, COVID certificates, Id cards, driving licenses, and passports. The morphological attributes like changes in background colour, variations in pixel size, and specifically appearance of dots and layers were observed. The results obtained were conclusive and were able to detect the manipulations, as well as the date and time of alterations, were detected with help of Forensic beta software. [ABSTRACT FROM AUTHOR]

Recently, Xia et al. proposed a semi-quantum blind signature protocol based on five-particle GHZ state. Their protocol can reduce the computation burden of the communicants. However, their protocol is not secure against forgery attack. We prove that the message sender and the signature receiver may conspire to forge the signer’s signature, because they master all the private keys of the signer. Then, both the signer and the signature receiver can deny a valid signature. Then, based on the three-particle GHZ state, an improved semi-quantum blind signature protocol is proposed. In the improved protocol, the signer shares the signing key with the trusted arbitrator. Even the message sender and the signature receiver conspire, it is infeasible for them to forge the signer’s signature. The improved scheme is secure against the disavowal attack. It has the better efficiency and practicability than the old version as well. [ABSTRACT FROM AUTHOR]

As an important and challenging problem, Face Forgery Detection has gained considerable attention. Usually, it suffers from the diversity of forgery patterns in forgery images, which requires a detection model to have capability of capturing various patterns in the challenging scenarios. To address this problem, we present a divide-and-aggregate learning framework to build multi-expert models and integrate them into a unified model. Firstly, the built multi-expert models are pre-trained to capture and preserve the specific forgery pattern produced by each manipulation method separately. Secondly, to transfer diverse knowledge of experts, we propose an integrating approach based on knowledge distillation. However, the difference of manipulation-aware knowledge among these experts concerns the way of distillation when the knowledge is combined in the only student model. Thus, to determine the importance of each expert, we propose a sample-aware Adaptive Learning from Experts strategy (ALFE) to assign adaptive expert distillation weights for each fake sample based on the predictions of each expert. Experiments show that our method achieves SOTA performances on ACC/AUC in the benchmark of FaceForensics++, demonstrating the effectiveness of our proposed method. [ABSTRACT FROM AUTHOR]

Video forgery detection and localization is one of the most important issue due to the advanced editing software that provides strengthen to tools for manipulating the videos. Object based video tampering destroys the originality of the video. The main aim of the video forensic is to eradicate the forgeries from the original video that are useful in various applications. However, the research on detecting and localizing the object based video forgery with advanced techniques still remains the open and challenging issue. Many of the existing techniques have focused only on detecting the forged video under static background that cannot be applicable for detecting the forgery in tampered video. In addition to this, conventional techniques fail to extract the essential features in order to investigate the depth of the video forgery. Hence, this paper brings a novel technique for detecting and localizing the forged video with multiple features. The steps involved in this research are keyframe extraction, pre-processing, feature extraction and finally detection and localization of forged video. Initially, keyframe extraction uses the Gaussian mixture model (GMM) to extract frames from the forged videos. Then, the pre-processing stage is manipulated to convert the RGB frame into a grayscale image. Multi-features need to be extracted from the pre-processed frames to study the nature of the forged videos. In our proposed study, speeded up robust features (SURF), principal compound analysis histogram oriented gradients (PCA-HOG), model based fast digit feature (MBFDF), correlation of adjacent frames (CAF), the prediction residual gradient (PRG) and optical flow gradient (OFG) features are extracted. The dataset used for the proposed approach is collected from REWIND of about 40 forged and 40 authenticated videos. With the help of the DL approach, video forgery can be detected and localized. Thus, this research mainly focuses on detecting and localization of forged video based on the ResNet152V2 model hybrid with the bidirectional gated recurrent unit (Bi-GRU) to attain maximum accuracy and efficiency. The performance of this approach is finally compared with existing approaches in terms of accuracy, precision, F-measure, sensitivity, specificity, false-negative rate (FNR), false discovery rate (FDR), false-positive rate (FPR), Mathew's correlation coefficient (MCC) and negative predictive value (NPV). The proposed approach assures the performance of 96.17% accuracy, 96% precision, 96.14% F-measure, 96.58% sensitivity, 96.5% specificity, 0.034 FNR, 0.04 FDR, 0.034 FPR, 0.92 MCC and 96% NPV, respectively. Along with is, the mean square error (MSE) and peak-to-signal-noise ratio (PSNR) for the GMM model attained about 104 and 27.95, respectively. [ABSTRACT FROM AUTHOR]

The tension between the diverging density profiles in Lambda cold dark matter simulations and the constant-density inner regions of observed galaxies is a long-standing challenge known as the 'core–cusp' problem. We demonstrate that the SMUGGLE galaxy formation model implemented in the arepo moving mesh code forms constant-density cores in idealized dwarf galaxies of M ⋆ ≈ 8 × 107 Msun with initially cuspy dark matter (DM) haloes of M 200 ≈ 1010 Msun. Identical initial conditions run with an effective equation of state interstellar medium model preserve cuspiness. Literature on the subject has pointed to the low density threshold for star formation, ρth, in such effective models as an obstacle to baryon-induced core formation. Using a SMUGGLE run with equal ρth, we demonstrate that core formation can proceed at low density thresholds, indicating that ρth is insufficient on its own to determine whether a galaxy develops a core. We reaffirm that the ability to resolve a multiphase interstellar medium at sufficiently high densities is a more reliable indicator of core formation than any individual model parameter. In SMUGGLE , core formation is accompanied by large degrees of non-circular motion, with gas rotational velocity profiles that consistently fall below the circular velocity |$v_\text{circ} = \sqrt{GM/R}$| out to ∼2 kpc. Asymmetric drift corrections help recover the average underlying DM potential for some of our less efficient feedback runs, but time-variations in the instantaneous azimuthal gas velocity component are substantial, highlighting the need for careful modelling in the inner regions of dwarfs to infer the true distribution of DM. [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]

With the recent advancement in modern technology, one can easily manipulate a digital image or video using computer software or a mobile application. The purpose of editing visual media could be as simple as to look good before sharing to the social networking site's or can be as malicious as to defame or hurt one's reputation in the real world through such morphed visual imagery. Identity theft is one of the examples where one's identity get stolen by some impersonator who can access the personal and financial information of an innocent person. To avoid such drastic situations, law enforcement authorities must use some automatic tools and techniques to find out whether a person is innocent or the culprit. One major question that arises here is how and what parts of visual imagery can be manipulated or edited. The answer to this question is important to distinguish the authentic images/videos from the doctored multimedia. This survey provides a detailed analysis of image and video manipulation types, popular visual imagery manipulation methods, and state-of-the-art image and video forgery detection techniques. It also surveys different fake image and video datasets used in tampering. The goal is to develop a sense of privacy and security in the research community. Finally, it focuses to motivate researchers to develop generalized methods to capture artificial visual imagery which is capable of detecting any type of manipulation in given visual imagery. [ABSTRACT FROM AUTHOR]

This article looks at how the biometric surveillance of migrants in the European Union interweaves border‐passing with the embodied capacity to pass as, or against, one's bureaucratic image. Despite biometrics' promise to eliminate photographic mediation, photo IDs are embedded in biometric regulation, which further entangles bodies and photographs. Based on ethnographic research in the Turkish city of Izmir, the migrant hotspot of Chios in Greece, and Athens' counterfeit document market, this article examines the material, embodied, and performative experiments migrants employ to pass borders while negotiating their bureaucratic images (both authentic and fake). Photographs emerge as a regime of practice through which European citizenship is enacted and exercised. [ABSTRACT FROM AUTHOR]

The advancements in Image editing techniques produce realistic‐looking artificial images with ease. These images can easily circumvent the forensic systems making the authentication process more tedious and difficult. To overcome this problem, we introduce a modern convolutional neural network (CNN) named ForensicNet, inspired by the recent developments in computer vision. The three major contributions of our CNNs are inverted bottleneck, separate downsampling layers, and using depth‐wise convolutions for mixing information in the spatial dimension. The inverted bottlenecks help improve accuracy and reduce network parameters/FLOPs. The separate downsampling layers help converge the network. The normalization layers also help stabilize training whenever the spatial resolution is changed. The depth‐wise convolution is a grouped convolution where the number of groups and channels are the same. The experiments show that ForensicNet outperforms the state‐of‐the‐art methods by a large margin. [ABSTRACT FROM AUTHOR]

In this study, a snapshot-based hyperspectral imaging (HSI) algorithm that converts RGB images to HSI images is designed using the Raspberry Pi environment. A Windows-based Python application is also developed to control the Raspberry Pi camera and processor. The mean gray values (MGVs) of two distinct regions of interest (ROIs) are selected from three samples of 100 NTD Taiwanese currency notes and compared with three samples of counterfeit 100 NTD notes. Results suggest that the currency notes can be easily differentiated on the basis of MGV values within shorter wavelengths, between 400 nm and 500 nm. However, the MGV values are similar in longer wavelengths. Moreover, if an ROI has a security feature, then the classification method is considerably more efficient. The key features of the module include portability, lower cost, a lack of moving parts, and no processing of images required. [ABSTRACT FROM AUTHOR]

A banknote is a currency issued by a country, and it was first introduced in the 16th century. The counterfeiting of banknotes by cunning criminals became a great challenge with the current advanced technology. Forensic scientists are using chemical methods, such as Fourier transform infrared (FTIR) spectroscopy for differentiating genuine and counterfeit banknotes. However, the FTIR spectra of banknotes may require further pattern recognition analysis due to their high similarities. In this paper, a fuzzy graph-based algorithm for authentication of the FTIR spectrum, namely chemometrics fuzzy autocatalytic set (c-FACS), is used to discriminate between genuine and counterfeit hundred Ringgit Malaysian (RM100) banknotes. The results show that the genuine and counterfeit RM100 banknotes have slightly distinct patterns when analyzed using c-FACS. In addition, the results are compared with RM50 banknotes, and the results reveal that the nodes or dominant axis varies between the two banknotes. To verify the reliability of the results, the results obtained via c-FACS are compared with principal component analysis (PCA). The c-FACS showed better performances as compared to PCA in terms of time consumption and observation. Thus, the c-FACS has the ability to assist forensic investigations involving banknote counterfeiting crimes. [ABSTRACT FROM AUTHOR]

The widespread dissemination of facial forgery technology has brought many ethical issues and aroused widespread concern in society. Most research today treats deepfake detection as a fine grained classification task, which however makes it difficult to enable the feature extractor to express the features related to the real and fake attributes. This paper proposes a depth map guided triplet network, which mainly consists of a depth prediction network and a triplet feature extraction network. The depth map predicted by the depth prediction network can effectively reflect the differences between real and fake faces in discontinuity, inconsistent illumination, and blurring, thus in favor of deepfake detection. Regardless of the facial appearance changes induced by deepfake, we argue that real and fake faces should correspond to their respective latent feature spaces. Particularly, the pair of real faces (original–target) remain close in the latent feature space, while the two pairs of real–fake faces (original–fake, target–fake) instead keep faraway. Following this paradigm, we suggest a triplet loss supervision network to extract the sufficiently discriminative deep features, which minimizes the distance of the original–target pair and maximize the distance of the original–fake (also target–fake) pair. The extensive results on public FaceForensics++ and Celeb-DF datasets validate the superiority of our method over competitors. [ABSTRACT FROM AUTHOR]

Face forgery represented by DeepFake technique has raised severe societal concerns. Due to the different scales of tampering traces and the different resolutions of face images, adopting common processing pipelines and standard form of convolutional neural networks (CNNs) will lead to problems such as omission, redundancy, and bias when extracting key discriminative features. To solve the above issues, unlike most existing methods that treat face forensics as a vanilla binary classification task, the authors instead reformulate it as a multi‐scale object detection problem and propose a novel framework called MSFRNet based on multi‐scale feature extraction. Concretely, to alleviate the issues of features omission and redundancy, the authors construct a two‐stream prediction network, where the shallow branch discovers small‐scale objects such as tiny noise by capturing low‐level features with higher resolution and more details, while the deep stream exploits larger receptive fields to detect large‐scale blocky artefacts. Moreover, a multi‐scale feature extraction module is designed to enrich feature representations in each stream. To solve the problem of features bias and ensure that unbiased feature representations are learned, more appropriate data augmentation approaches are proposed by introducing counterfactual causal reasoning. Extensive experiments demonstrate that our framework outperforms most ordinary binary classifiers and achieves positive performance. [ABSTRACT FROM AUTHOR]

Images play an important role in transmitting visual information in our life. It could lead to severe consequences if images are manipulated or tampered maliciously. Digital forensics is an important research area to secure multimedia information. Many forensics technologies are applied to protect our community from the abuse of digital information. In many cases, after tampering, attackers could apply operations such as resampling, JPEG compression, blurring, etc. to cover the traces of tampering. Therefore, it is necessary to detect these manipulations in image forensics before exposing forgeries. In this paper, we propose to employ the prediction error filters, ConvNeXt blocks and convolution modules to classify images with different compression quality factors and resampling rates. By tracing the inconsistencies of resampling rates and compression quality factors, it could provide supplementary information for forensics researchers to expose possible forgeries. The proposed method could achieve great classification performance regardless of the interpolation algorithms. Also, it is highly robust against JPEG compression. In addition, the proposed method can be applied for estimating quality factors of JPEG compression. [ABSTRACT FROM AUTHOR]

Media content forgery is widely spread over the Internet and has raised severe societal concerns. With the development of deep learning, new technologies such as generative adversarial networks (GANs) and media forgery technology have already been utilized for politicians and celebrity forgery, which has a terrible impact on society. Existing GAN-generated face detection approaches rely on detecting image artifacts and the generated traces. However, these methods are model-specific, and the performance is deteriorated when faced with more complicated methods. What's more, it is challenging to identify forgery images with perturbations such as JPEG compression, gamma correction, and other disturbances. In this paper, we propose a global–local facial fusion network, namely GLFNet, to fully exploit the local physiological and global receptive features. Specifically, GLFNet consists of two branches, i.e., the local region detection branch and the global detection branch. The former branch detects the forged traces from the facial parts, such as the iris and pupils. The latter branch adopts a residual connection to distinguish real images from fake ones. GLFNet obtains forged traces through various ways by combining physiological characteristics with deep learning. The method is stable with physiological properties when learning the deep learning features. As a result, it is more robust than the single-class detection methods. Experimental results on two benchmarks have demonstrated superiority and generalization compared with other methods. [ABSTRACT FROM AUTHOR]

Thje circulation of misinformation increased by 365% in 2017 according to the report Approaching the Future (2018). In 2019, almost a third of the queries received by Maldita.es media corresponded to gender issues, according to the same report. ^is research aims to study, through the analysis of the denials on gender issues published in the sections of the media dedicated to the Spanish verification Newtral and Maldito Feminismo and the perception of expert journalists, the transit of falsehoods around women's equality. ^e results show how most hoaxes resort to the myth of false reports of gender violence and manipulate official data to question the usefulness of the Law against Gender Violence. ^ey are mainly disseminated through social networks, messaging channels and pseudo-media and, for the most part, can be verified by resorting to easily accessible documentary sources open to the public. [ABSTRACT FROM AUTHOR]

Blockchain technology and smart contracts have huge potential which has not been exploited fully yet. The main objective of this paper is to showcase the powerful attributes of blockchain technology and smart contracts, showcasing our unique and powerful use case of document verification in the field of higher education using the Ethereum protocol. Our smart contract use case will take advantage of the main attributes of blockchain technology to solve the problem of document forgery. These amazing attributes are immutability, censorship resistance, extreme robusticity, transparency, and neutrality, in addition to near-perfect availability and decentralization. Ethereum enables developers to create decentralized applications without having to invest in expensive infrastructure. Document forgery has a very long track record in the education sector and academia. In this digital age, it has become frighteningly simple and inexpensive to acquire fake university diplomas, certificates, and many other types of credentials. This has a long-term negative effect on higher-level education because it damages the healthy competitive environment of students and the reputation and credibility of institutions. The most problematic version of the diploma which is the most susceptible to forgery is physical diplomas. Even with relatively expensive and difficult-to-replicate security elements, such as holograms and special security markings, these are not efficient enough to keep bad actors away from trying to forge them and replicate them. The more complex methods we use for preventing physical document forgery, the more knowledge and experience does the verifier needs beforehand due to the complexity and the unique nature of anti-forgery methods and materials one has to look for during examination. The verification process of continually evolving and changing physical forgery prevention stamps, materials, holograms and others are expensive to automate the verification procedure and introduces additional human labor cost (training staff, hiring new employees, hiring trainers and forgery specialists). Therefore the best prevention method for replication is to build a system that makes it infeasible to even try to commit forgery. Usually, when an employer asks for the diploma, the student sends an electronic photocopy of the document to them or scans it. This completely nullifies the effect of holograms, watermarks, special UV active materials, and all other physical security elements. Even with the use of centralized electronic document verification systems, data manipulation is still possible, in addition, such a system introduces the concept of having to trust a third party for verification and single point of failure, in addition to lack of transparency, immutability, and data availability. An ideal solution would be one that is trustless, transparent, immutable, and always accessible. Blockchain technology offers the optimal solution to document forgery. In this article, we will showcase our Ethereum smart contract solution and all of the crucial aspects of document integrity. [ABSTRACT FROM AUTHOR]

Ginseng is one of the rare traditional Chinese medicine in China, with a long history of application. There are many prescriptions of ginseng recorded in ancient traditional Chinese medicine books, yet the name, origin, place of origin, collection and processing, and quality identification of ginseng have changed with the changes of the times. In this paper, the origin and development of ginseng is re-examined, which is convenient for clinical clarification of confusion and forgery. And the modern clinical research of ginseng is summarized to provide reference for the inheritance, use and resource development of ginseng. [ABSTRACT FROM AUTHOR]

More than 70 years have passed since Philippe Lauer published his edition of the 130 royal diplomas of Charles III the Simple (893/898-923). Since then numerous studies of these diplomas have been brought forward, concerning their genuineness, interpolations, datings, identifications of places and more. This paper unites these studies and adds further thoughts, thus providing comments on no less than 47 charters, acting as a supplement to Lauer's edition: Four deperdita are added to the collection. Seven diplomas thought to be genuine by Lauer are identified as forgeries, while in turn three supposed forgeries are shown to be genuine. Four more diplomas contain interpolations and another two were rewritten at a later point. Datings of a further 18 diplomas are corrected, as are the places of issue of another 13. [ABSTRACT FROM AUTHOR]

With the advance of the agricultural frontier in the Cerrado areas (brazilian savanna), where the productive forces of agribusiness have exercised their domain, there has been an intense process of land appropriation for the production of commodities. The territories of some traditional communities, especially on the valley floor, began to be incorporated into latifundiums in order to constitute legal reserve areas, involving forgery of land documents and a conservationist discourse. The municipality of Formosa do Rio Preto stands out for its large concentration of land ownership, with various groups of agricultural production having advanced their properties over territories belonging to the traditional communities (geraizeiras), along the lines mentioned above. In this work, this process is examined in the light of the concepts of environmental injustice and environmental conflict, seeking to highlight the intertwining between the territory and environment categories. The research was carried out through different strategies, including field work, document analysis and interviews with members of the traditional communities (geraizeiras). The results reveal how the advance on the traditional territories leads to environmental injustices, through an unequal distribution of burdens and benefits. [ABSTRACT FROM AUTHOR]

In 1608, Antonio Barisone (1557/8–1623), rector of the Jesuit college at Ferrara, became ensnared in an elaborate deception designed to expose the unscrupulous methods by which Jesuits exploited vulnerable wealthy widows and enlarged the material wealth of their Society. Entering into a correspondence with a Venetian noblewoman who lamented the loss of her Jesuit confessor following the expulsion of the Society of Jesus from Venice (1606), it took several months before Barisone realized that the letters he was receiving actually had their origins in the anti-Jesuit circles linked to Paolo Sarpi (1552–1623). In addition to throwing light on Venice as a hotbed of espionage, political rumors, and conspiratorial activity in the early sixteenth century, this episode foregrounds several themes and leitmotifs that would go on to dominate anti-Jesuit polemic over the subsequent centuries. [ABSTRACT FROM AUTHOR]

On the grounds of the bibliographic analysis of the publications in the Polish language in the Grand Duchy of Lithuania in the second half of the 16th century, this article reconstructs the phenomena of anonymity, counterfeiting and piracy. In this country, the life of the printed media was fairly liberal and hardly restricted at all. In the course of political and religious struggles, authors, translators, publishers and compilers frequently preferred to conceal the data on the real authorship and typography in their publications. Political and religious factions had to consider the opinion of the ruler and their seniority; therefore, only anonymous impact on the public opinion allowed ensuring the defense of one's attitudes and the desired impact on the society. This strategy of anonymity was protecting the stakeholders from getting into trouble, while also expanding the scope of commercial activity for the typographers. The phenomenon of piracy was also being promoted by the different legal regulation of the printed media in the Grand Duchy of Lithuania and the Kingdom of Poland, and, due to the physically vast distances, the feeling of impunity developed. The authors and typographers were acting honestly in such cases when the published literature contained no controversial materials, or when they had the solid backing of the powers, and also in the cases when legal protection of the printed media was ensured. [ABSTRACT FROM AUTHOR]

Referring to the widespread problem of diploma forgery in Indonesian educational institutions as the impetus for UNTIRTA's latest vision as an "Integrated, Smart, and Green University," UNTIRTA intends to use blockchain technology to prevent diploma forgery and overcome issues related to existing platforms at UNTIRTA, such as frequent connection interruptions when accessed by a large number of users simultaneously. Before using blockchain technology, UNTIRTA must evaluate several readiness issues. This study presented the interpretative structural modeling (ISM) method to assess the primary preparedness elements for adopting blockchain technology in universities and sought to provide pertinent strategy ideas for UNTIRTA's blockchain technology application. The results reveal sixteen major parameters that influence the adoption readiness of blockchain technology at UNTIRTA. The primary variables impacting the adoption and deployment of blockchain technology at UNTIRTA are management and employee support and a grasp of the technology. To realize UNTIRTA's mission as an "Integrated, Smart, and Green University", the proposed method entails determining an initial agreement in which all stakeholders have a shared understanding and commitment to Blockchain technology implementation at UNTIRTA. The objective of the tactical proposal is to establish each unit's mission in the blockchain implementation program. The objective of the technical proposal is to construct a planning document that will serve as a coordination tool between the chairman and members, as well as all parties interested in the adoption of Blockchain technology at UNTIRTA. [ABSTRACT FROM AUTHOR]

Automatic Speaker Verification (ASV) has its benefits compared to other biometric verification methods, such as face recognition. It is convenient, low cost, and more privacy protected, so it can start being used for various practical applications. However, voice verification systems are vulnerable to unknown spoofing attacks, and need to be upgraded with the pace of forgery techniques. This paper investigates a low-cost attacking scenario in which a playback device is used to impersonate the real speaker. The replay attack only needs a recording and playback device to complete the process, so it can be one of the most widespread spoofing methods. In this paper, we explore and investigate some spectral clues in the high sampling rate recording signals, and utilize this property to effectively detect the replay attack. First, a small scale genuine-replay dataset of high sample rates are constructed using some low-cost mobile terminals; then, the signal features are investigated by comparing their spectra; machine learning models are also applied for evaluation. The experimental results verify that the high frequency spectral clue in the replay signal provides a convenient and reliable way to detect the replay attack. [ABSTRACT FROM AUTHOR]

Bank X submitted a claim to its financial institution bond carrier for the following facts.1 Bank X allows its customers to request wire transfers in person, via a phone call, or by email. Bank X received a number of wire transfer requests from someone purporting to be Customer A, a valued customer of Bank X. Each request followed the same pattern: The fraudster emailed a branch manager of Bank X pretending to be Customer A and requested international wire transfers from Customer A's account. The fraudster then emailed the wire transfer authorization form as a PDF attachment that contained the forged signature of Customer A. Once the fraud was discovered, it was revealed that over $1 million was transferred from Customer A's account. The company defaulted on the loan, and the bank contacted the life insurance company to assert a claim against the collateral. [Extracted from the article]

The article reconstructs the history of a misattribution and its relationship to the afterlife of a forgery in cultural activity. Topics include Pseudo-Pindar and Dares Phrygius's forged history of the Trojan War, in manuscripts, printed editions and the minds of humanists and philologists; and devoid of mythological phenomena and heavy on quantitative exactitude all the historians and poets to medieval book culture.

The image copy–move forgery can achieve the realistic effects without leaving any obvious manipulation traces because the copied source and pasted target belong to the homogenous sources. Image copy–move forgery detection (CMFD) is still a serious challenge issue for researchers, e.g. computational efficiency, occlusive (smoothing) object detection, and partial object detection, under various post-processing and geometrical transformations. This paper proposes a novel CMFD scheme using the characteristics of local descriptors. First, the proposed method deeply analyzes the structure and mines the inherent characteristics of the local descriptor (SURF) for feature extraction in the coarse and smooth regions. Subsequently, the proposed method takes the kernel features as coarse feature matching to decrease matching costs. Then, the found candidate keypoints with a relatively small quantity are used with complete features to perform fine keypoint matching for getting suspicious candidate keypoint pairs. Furthermore, based on the deep mining of the inherent local descriptor characteristics, the proposed method can indicate the forgery region localizations through keypoint pairs, even the forgeries suffering from various geometrical transformations. Then, the proposed method proposes adaptive dual-filtering algorithms of K -means relying on keypoint characteristics, and spatial distance for hierarchical progress of feature filtering. Finally, Delaunay Triangulation relies on the true-positive keypoint pairs to perform the forgery region matting effectively and efficiently. The experimental results demonstrate that the proposed method can achieve the best F1 scores compared to the state-of-the-art methods in most cases, especially in anti-scaling transformations. [ABSTRACT FROM AUTHOR]

In practical application, many scenarios need to protect user identity and privacy, and multiple parties are required to participate in transaction audits, but the existing signature schemes are often inefficient and weak blind. Therefore, this paper proposes a new multi-proxy blind signature scheme based on block blind coding. It can not only resist forgery attacks, deny attacks, and intercept retransmission attacks, but also has stronger anonymity and higher efficiency. For instance, we design a securities trading model based on this signature scheme; through the analysis of the safety and efficiency, the scheme features unforgeability and non-deniability, and the efficiency can reach 50%. This signature scheme applies to the transaction or process management, which needs to protect user privacy and multi-party audit during processing, so it has strong practicability. [ABSTRACT FROM AUTHOR]

AI face-swapping technologies, such as DeepFake, bring negative effects in daily life. However, existing face forgery detection algorithms have weak robustness and lack interpretable ability. Aiming at the above problem, this paper proposes a face frequency-domain watermarking algorithm (Face-FW) which combines Discrete Wavelet Transform (DWT), Discrete Cosine Transform (DCT) and Single Value Decomposition (SVD). To detect face forgery and verify the attribution of the original face, the algorithm extracts face features from a face image, and then compresses and encrypts them into a binary watermarking. Finally, Face-FW embeds the generated watermarking to frequency domain of the image. At the same time, the algorithm uses a dynamic feature fusion algorithm to broaden the scope of applications. This paper generates test sets CASIA-DF and IMDB-DF by embedding watermarking meanwhile tampering the faces in the selected standard face image datasets CASIA-FaceV5 and IMDB-WIKI. Experimental results demonstrate that Face-FW reaches detection success rates of 97.6% and 96.9% on the test sets respectively and achieves a better performance than compared methods. Moreover, the algorithm can provide face authentication for face images according to the non-integrated watermarking, showing strong robustness and interpretability. [ABSTRACT FROM AUTHOR]

The emergence of advanced machine learning or deep learning techniques such as autoencoders and generative adversarial networks, can generate images known as deepfakes, which astonishingly resemble the realistic images. These deepfake images are hard to distinguish from the real images and are being used unethically against famous personalities such as politicians, celebrities, and social workers. Hence, we propose a method to detect these deepfake images using a light weighted convolutional neural network (CNN). Our research is conducted with Deep Fake Detection Challenge (DFDC) full and sample datasets, where we compare the performance of our proposed model with various state-of-the-art pretrained models such as VGG-19, Xception and Inception-ResNet-v2. Furthermore, we perform the experiments with various resolutions maintaining 1:1 and 9:16 aspect ratios, which have not been explored for DFDC datasets by any other groups to date. Thus, the proposed model can flexibly accommodate various resolutions and aspect ratios, without being constrained to a specific resolution or aspect ratio for any type of image classification problem. While most of the reported research is limited to sample or preview DFDC datasets only, we have also attempted the testing on full DFDC datasets and presented the results. Contemplating the fact that the detailed results and resource analysis for various scenarios are provided in this research, the proposed deepfake detection method is anticipated to pave new avenues for deepfake detection research, that engages with DFDC datasets. [ABSTRACT FROM AUTHOR]

The vehicular ad-hoc network (VANET) is a critical component of intelligent transportation, which can improve transportation efficiency and promote road safety. To address security and privacy concerns in VANET, Zhong et al. presented a privacy-preserving authentication scheme. Furthermore, they stated that their scheme was secure and resistant to forgery attacks. However, in this article, we provide three different attack methods to demonstrate that their scheme is vulnerable to Type II attacks, coalition attacks, and universal forgery attacks. Hence, the security of their scheme cannot be guaranteed, and it cannot be deployed in a real-world VANET setting. To fix the security flaws, we give an improved scheme for revising their scheme. Our scheme retains the security properties of the original scheme, but the aggregate signature length is a fixed constant. Compared with related schemes, our enhanced scheme has a higher level of security and communication performance. [ABSTRACT FROM AUTHOR]

Authentication is very much essential in managing security. In modern times, it is one in all priorities. With the advent of technology, dialogue with machines becomes automatic. As a result, the need for authentication for a variety of security purposes is rapidly increasing. For this reason, biometrics-based certification is gaining dramatic momentum. The proposed method describes an off-line Genuine/Forgery signature classification system using radon transform and K-Nearest Neighbour classifier. Every signature features are extracted by radon transform and they are aligned to get the statistic information of his signature. To align the two signatures, the algorithm used is Extreme Points Warping. Many forged and genuine signatures are selected in K-Nearest Neighbour classifier training. By aligning the test signature with each and every reference signatures of the user, verification of test signature is done. Then the signature can be found whether it is genuine or forgery. A K-Nearest Neighbour is used for classification for the different datasets. The result determines how the proposed procedure is exceeds the current state-of-the-art technology. Approximately, the proposed system's performance is 90 % in signature verification system. [ABSTRACT FROM AUTHOR]

As the world is gradually moving towards digitization, forgery of vital digital documents has become relatively easy. Therefore, the need for efficient and secure verification and authentication practices of digital documents is also increasing. Self-sovereign identity (SSI) is a set of technologies that build on core concepts in identity management, blockchain technology, and cryptography. SSI enables entities to create fraud-proof verifiable credentials and instantly verify the authenticity of a digital credential. The online document verification solutions must deal with a myriad of issues in regard to privacy and security. Moreover, various challenging and tedious processes have made document verification overly complex and time-consuming which motivated us to conduct this research. This work presents a novel framework for online document verification based on SSI technology. The solution address the complexity and interoperability issues that are present in the current digital document verification systems. We look at a particular use case, i.e., document verification in online loan processing and evaluate how this proposed approach can make an impact on the existing system. Our solution based on SSI standards replaces the intermediary and enables trust between players in the ecosystem. The technology also holds the potential to make the system more efficient, interoperable, and privacy-preserving. [ABSTRACT FROM AUTHOR]

To defend against manipulation of image content, such as splicing, copy-move, and removal, we develop a Progressive Spatio-Channel Correlation Network (PSCC-Net) to detect and localize image manipulations. PSCC-Net processes the image in a two-path procedure: a top-down path that extracts local and global features and a bottom-up path that detects whether the input image is manipulated, and estimates its manipulation masks at multiple scales, where each mask is conditioned on the previous one. Different from the conventional encoder-decoder and no-pooling structures, PSCC-Net leverages features at different scales with dense cross-connections to produce manipulation masks in a coarse-to-fine fashion. Moreover, a Spatio-Channel Correlation Module (SCCM) captures both spatial and channel-wise correlations in the bottom-up path, which endows features with holistic cues, enabling the network to cope with a wide range of manipulation attacks. Thanks to the light-weight backbone and progressive mechanism, PSCC-Net can process $1,080\text{P}$ images at 50+FPS. Extensive experiments demonstrate the superiority of PSCC-Net over the state-of-the-art methods on both detection and localization. Codes and models are available at https://github.com/proteus1991/PSCC-Net. [ABSTRACT FROM AUTHOR]

The prime goal of creating synthetic digital data is to generate something very closer to real ones when the original data are scarce. However, the trustworthiness of such digital content is dipping potentially in society owing to malicious users. Deepfake method that uses computer graphics and computer vision techniques to replace the face of one person with the face of a different person is becoming an area of big concern. Such techniques can easily be used to hide the identity of a person. Therefore, a method is needed to verify the originality of such face images/videos. To this end, we design a deep learning model enhanced with visual attention technique to differentiate manipulated videos/images (generated by deepfake methods) from real ones. At first, we extract the face region from video frames and then pass the same through the pre-trained Xception model to obtain the feature maps. Next, with the help of the visual attention mechanism, we mainly try to focus on the deepfake video manipulation leftover artifacts. We evaluate our model on two publicly available datasets, namely FaceForensics++ and Celeb-DF (V2), and our model outperforms many state-of-the-art methods tested on these two datasets. Source code of the proposed method can be found at: https://github.com/tre3x/Deepfake-Video-Forgery-Detection. [ABSTRACT FROM AUTHOR]