Search

For Deepfake detection, many existing works use the cross-entropy loss to enforce the classifier network to learn the mapping relationship from the RGB domain to the class domain, lacking an explicit constraint to guide the feature extraction network to learn discriminative features from an input image. This constrains the feature representation capability to expose deepfake. In this work, we analyze the feature extraction network in terms of both difference and similarity capabilities and propose a new constraint called similarity loss (SL) to improve the detection performance of the convolutional neural network (CNN) based detector. Moreover, according to the experimental results of the SL on data augmentation effectiveness, we propose a simple yet efficient framework, which is called as efficient similarity representation learning (ESRL), for deepfake detection. Extensive experiments on three public datasets (namely FF++, DFDC, and Celeb-DF) show that the feature extraction network trained with the help of SL can map forged faces and real faces to different feature embedding and map the same type of forged faces to similar feature embedding. [ABSTRACT FROM AUTHOR]

In contexts requiring user authentication, such as financial, legal, and administrative systems, signature verification emerges as a pivotal biometric method. Specifically, handwritten signature verification stands out prominently for document authentication. Despite the effectiveness of triplet loss similarity networks in extracting and comparing signatures with forged samples, conventional deep learning models often inadequately capture individual writing styles, resulting in suboptimal performance. Addressing this limitation, our study employs a triplet loss Siamese similarity network for offline signature verification, irrespective of the author. Through experimentation on five publicly available signature datasets—4NSigComp2012, SigComp2011, 4NSigComp2010, and BHsig260—various distance measure techniques alongside the triplet Siamese Similarity Network (tSSN) were evaluated. Our findings underscore the superiority of the tSSN approach, particularly when coupled with the Manhattan distance measure, in achieving enhanced verification accuracy, thereby demonstrating its efficacy in scenarios characterized by close signature similarity. [ABSTRACT FROM AUTHOR]

Image forgery detection is essential for forensic and security applications. In local locations where key points (KPs) are few, traditional approaches that rely on them suffer from restrictions. To tackle this problem, this paper suggests an innovative strategy that combines pre-processing, feature extraction, and classification methods. We specifically present EFP-AEHO, or Enhanced Flower Pollination-Adaptive Elephant Herd Optimization, for modifying the Deep Belief Network's (DBN) weights. Our method provides better performance by first converting RGB images into the Lab color space, then applying Eigenvalue Asymmetry (EAS) to extract texture features. Its efficacy is highlighted by experimental findings on the F2000 dataset, which show testing accuracy of 99.4%, TPR of 98%, and TNR of 99.12%. [ABSTRACT FROM AUTHOR]

One of the most pressing challenges in audio forgery detection—a major topic of signal analysis and digital forensics research—is detecting copy-move forgery in audio data. Because audio data are used in numerous sectors, including security, but increasingly tampered with and manipulated, studies dedicated to detecting forgery and verifying voice data have intensified in recent years. In our study, 2189 fake audio files were produced from 2189 audio recordings on the TIMIT corpus, for a total of 4378 audio files. After the 4378 files were preprocessed to detect silent and unsilent regions in the signals, a Mel-frequency-based hybrid feature data set was obtained from the 4378 files. Next, RNN and LSTM deep learning models were applied to detect audio forgery in the data set in four experimental setups—two with RNN and two with LSTM—using the AdaGrad and AdaDelta optimizer algorithms to identify the optimum solution in the unlinear systems and minimize the loss rate. When the experimental results were compared, the accuracy rate of detecting forgery in the hybrid feature data was 76.03%, and the hybrid model, in which the features are used together, demonstrated high accuracy even with small batch sizes. This article thus reports the first-ever use of RNN and LSTM deep learning models to detect audio copy-move forgery. Moreover, because the proposed method does not require adjusting threshold values, the resulting system is more robust than other systems described in the literature. [ABSTRACT FROM AUTHOR]

The current deep learning methods for copy–move forgery detection (CMFD) are mostly based on deep convolutional neural networks, which frequently discard a large amount of detail information throughout convolutional feature extraction and have poor long-range information extraction capabilities. The Transformer structure is adept at modeling global context information, but the patch-wise self-attention calculation still neglects the extraction of details in local regions that have been tampered with. A local-information-refined dual-branch network, LBRT (Local Branch Refinement Transformer), is designed in this study. It performs Transformer encoding on the global patches segmented from the image and local patches re-segmented from the global patches using a global modeling branch and a local refinement branch, respectively. The self-attention features from both branches are precisely fused, and the fused feature map is then up-sampled and decoded. Therefore, LBRT considers both global semantic information modeling and local detail information refinement. The experimental results show that LBRT outperforms several state-of-the-art CMFD methods on the USCISI dataset, CASIA CMFD dataset, and DEFACTO CMFD dataset. [ABSTRACT FROM AUTHOR]

Videos are considered as most trustworthy means of communication in the present digital era. The advancement in multimedia technology has made video content sharing and manipulation very easy. Hence, the video authenticity is a challenging task for the research community. Video forensics refer to uncovering the forgery traces. The detection of spatiotemporal object‐removal forgery in surveillance videos is crucial for judicial forensics, as the presence of objects in the video has significant information as legal evidence. The author proposes a passive max–median averaging motion residual algorithm for revealing the forgery traces, successfully giving visible object‐removal traces followed by a deep learning approach, YOLO‐V8, for forged region localization. YOLO‐V8 is the latest deep learning model, which has a wide scope for real‐time application. The proposed method utilizes YOLO‐V8 for object‐removal forgery in surveillance videos. The network is trained on the SYSU‐OBJFORG dataset for object‐removal forged region localization in videos. The fine‐tuned YOLO‐V8 successfully classifies and localizes the object‐removal tampered region with an F1‐score of 0.99 and a precision of 0.99. The observed high confidence score of the bounding box around the forged region makes the model reliable. This fine‐tuned YOLO‐V8 would be a better choice in real‐time applications as it solves the complex object‐based forgery detection in videos. The performance of the proposed system is far better than the existing deep learning approach. [ABSTRACT FROM AUTHOR]

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]

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In the contemporary digital era, images are omnipresent, serving as pivotal entities in conveying information, authenticating experiences, and substantiating facts. The ubiquity of image editing tools has precipitated a surge in image forgeries, notably through copy-move attacks where a portion of an image is copied and pasted within the same image to concoct deceptive narratives. This phenomenon is particularly perturbing considering the pivotal role images play in legal, journalistic, and scientific domains, necessitating robust forgery detection mechanisms to uphold image integrity and veracity. While advancements in Convolutional Neural Networks (CNN) have propelled copy-move forgery detection, existing methodologies grapple with limitations concerning the detection efficacy amidst complex manipulations and varied dataset characteristics. Additionally, a palpable void exists in comprehensively understanding and exploiting dataset heterogeneity to enhance detection capabilities. This heralds a pronounced exigency for innovative CNN architectures and nuanced understandings of dataset intricacies to augment detection capabilities, which has remained notably underexplored in the prevailing literature. Against this backdrop, our research broaches novel frontiers in copy-move forgery detection by introducing an innovative CNN architecture meticulously tailored to discern the subtlest manipulations, even amidst intricate image contexts. An extensive analysis of multiple datasets – MICC-F220, MICC-F600, and a combined variant – enables us to delineate a granular understanding of their attributes, thereby shedding unprecedented light on their influences on detection performance. Further, our research goes beyond mere detection, delving deep into comprehensive analyses of varied datasets and conducting additional experiments with differential training-validation sets and randomly labeled data to scrutinize the robustness and reliability of our model. We not only meticulously document and analyze our findings but also juxtapose them against extant models, offering an exhaustive comparative analysis. [ABSTRACT FROM AUTHOR]

The identification of the tampered images is the research area of digital forensics, which defines the manipulation in the image. This is easily performed by forgers without the permission of the owners of the images. The misuse of these images in digital content is a significant problem for privacy. There are some studies on the detection of the forgery images, in the literature. However, effective and robust solutions are needed to detect them. In this motivation, a deep learning based architecture is proposed to solve the tampered image detection. It includes feature extraction with transfer learning architecture, selection of features with particle swarm optimization, and multi-classification of images with a deep learning architecture that is designed with Gated Recurrent Units. The proposed architecture is validated with the modified CASIA dataset. Various noisy tampered images are also included in the dataset of the study to demonstrate the robustness of the method. Despite this, tampered and noisy tampered images can even be detected quite accurately. As a result of the experiments, 96.25% accuracy is achieved with the proposed method. An accuracy of 80.5% was achieved in images with Gaussian and salt & pepper noises together. It has been proven through experiments that these results are significantly higher than the SVM classifier. This achievement is capable of supporting the detection of the original image combined with different images by experts working in the field of digital forensics. [ABSTRACT FROM AUTHOR]

The evolution of image manipulation techniques has presented a paradoxical scenario in contemporary visual culture. This phenomenon operates as a double-edged sword, offering both creative liberation and ethical dilemmas. Consequently, there is a need to develop automated mechanisms capable of discerning such forged data. The proposed methodology leverages transfer learning, utilising pre-trained deep learning models as a foundation and fine-tuning them specifically for the task of copy-move forgery detection. This approach uses the knowledge learned from large datasets, enhancing the network's ability to discern subtle patterns indicative of copy-move manipulations in images. Further, this research introduces a custom-designed CNN architecture tailored to the intricacies of copy-move forgery, optimising feature extraction and classification. Experimental evaluations conducted on diverse datasets, namely MICC-F220, MICC-F600, MICC-F2000, and CoMoFoD demonstrate the effectiveness of the proposed method with a True Positive Rate (TPR) of 100%. [ABSTRACT FROM AUTHOR]

Digital picture fraud detection is an increasing societal necessity due to the importance of verified images. The detection of picture copying, splicing, retouching, and re-sampling forgeries is included. In the absence of digital signatures or watermarks, passive picture authentication may serve as an alternative to active authentication. Passive techniques, every so often recognized as blind techniques, could take place without preceding knowledge of the picture or its reference. Identifying counterfeiting picture or tampering was a research field for long a period of time, triggered via the Internet, online platforms, social messaging platforms, and extensive digital image usage. The rate of failure could be a key factor for examining the alteration of picture or forgery, among other existing methods. The research applies almost six common algorithms related to machine learning in order to extract features from Lightweight, Spatial Exploitation, and Residual deep learning models on benchmark datasets MICC-F220, Columbia, and CoMoFoD. The models of incorporated deep learning could consist of AlexNet, GoogleNet, VGG16, VGG19, SqueezeNet, MobileNetV2, ShuffleNet, ResNet-18, ResNet-50, and ResNet-101 for spatial exploitation. Fine-tuning is applied to the top three deep learning models, optimizing hyperparameters centered on indicators of performance for every single benchmark dataset. Tweaked SqueezeNet, MobileNetV2, and ShuffleNet deep learning models with SGDM Optimizer and SVM classifier yielded the best results for MICC-F220 dataset. Fine-tuned VGG19, MobileNetV2, and ResNet-50 deep learning models with SGDM Optimizer and SVM v classifier yielded the best results for Columbia dataset. In CoMoFoD dataset, fine-tuned AlexNet, MobileNetV2, and ShuffleNet deep learning models with SGDM Optimizer and SVM classifier yielded the best results. The proposed approach, utilizing machine learning algorithms and deep learning features, enhanced forgery detection and reduced false positives. Results were validated on benchmark image forgery datasets and compared to current methods. [ABSTRACT FROM AUTHOR]

In audio copy-move forgery forensics, existing traditional methods typically first segment audio into voiced and silent segments, then compute the similarity between voiced segments to detect and locate forged segments. However, audio collected in noisy environments is difficult to segment and manually set, and heuristic similarity thresholds lack robustness. Existing deep learning methods extract features from audio and then use neural networks for binary classification, lacking the ability to locate forged segments. Therefore, for locating audio copy-move forgery segments, we have improved deep learning methods and proposed a robust localization model by CNN-based spectral analysis. In the localization model, the Feature Extraction Module extracts deep features from Mel-spectrograms, while the Correlation Detection Module automatically decides on the correlation between these deep features. Finally, the Mask Decoding Module visually locates the forged segments. Experimental results show that compared to existing methods, the localization model improves the detection accuracy of audio copy-move forgery by 3.0–6.8%and improves the average detection accuracy of forged audio with post-processing attacks such as noise, filtering, resampling, and MP3 compression by over 7.0%. [ABSTRACT FROM AUTHOR]

GANs (Generative Adversarial Networks) are widely employed in many domains of science and technology. They have produced high-resolution, photo-realistic faces that appear real to the human eye. However, recognizing these images is becoming increasingly difficult. This study introduces a new GAN ensemble model that is intended to improve GAN training issues (Mode Collapse and Convergence) and generate knowledge from diverse input samples. The proposed model is built using multiple CNN discriminators architecture based on the voting ensemble technique. It utilizes a modified diversity loss function designed with the goal of minimizing the distance between the generated and original distributions. It is proven as a robust technique for forgery detection, achieving 98.31% accuracy values. One of the major findings of the study is that the novel method outperforms existing GAN models based on a small dataset of "Face Mask Lite"(193 Unmasked images), using quantifiable parameters such as Inception score (IS), Fréchet Inception distance (FID), SSIM (Structural Similarity Index Metric) and Total Computational Time Function. [ABSTRACT FROM AUTHOR]

Digital tampering identification, which detects picture modification, is a significant area of image analysis studies. This area has grown with time with exceptional precision employing machine learning and deep learning-based strategies during the last five years. Synthesis and reinforcement-based learning techniques must now evolve to keep with the research. However, before doing any experimentation, a scientist must first comprehend the current state of the art in that domain. Diverse paths, associated outcomes, and analysis lay the groundwork for successful experimentation and superior results. Before starting with experiments, universal image forensics approaches must be thoroughly researched. As a result, this review of various methodologies in the field was created. Unlike previous studies that focused on picture splicing or copy-move detection, this study intends to investigate the universal type-independent strategies required to identify image tampering. The work provided analyses and evaluates several universal techniques based on resampling, compression, and inconsistency-based detection. Journals and datasets are two examples of resources beneficial to the academic community. Finally, a future reinforcement learning model is proposed. [ABSTRACT FROM AUTHOR]

Image forgery detection has become a hot research topic in security and forensics applications. Keypoints (KPs) based image forgery detection extracts image KPs and utilizes local visual features for identifying forgery regions which shows excellent performance on the basis of memory and robustness over attacks. But, these methods are lacking in handling the cases when forgeries in small regions, in which KPs are limited. To address these challenges, this work introduces a fast and efficient forgery detection using the processes like pre-processing, feature extraction and optimal classification. Initially, the RGB image is converted into L*a*b color space. Then, the KPs are determined using the Eigenvalue Asymmetry (EAS) and after determining the KPs, the texture features like Haralick and skewness are extracted. Then, these features are classified by the deep learning (DL) classifier Deep belief network (DBN) with an adaptive crow search algorithm (ACSA). The proposed DBN-ACSA classifier categorizes the detected image as a normal or forgery image. The experimental results are carried out on the Vision, UCID and CoMoFoD datasets and achieved accuracy, precision, F1 score, recall and ROC values. [ABSTRACT FROM AUTHOR]

Handwritten documents possess immense significance in domains such as law, history, and administration. However, they are vulnerable to forgery, which can undermine their credibility and reliability. This paper aims to establish a dependable technique for identifying altered text in handwritten document images, even in scenarios with high levels of noise and blur. Our study investigates 10 distinct categories of handwritten text that have been altered through various forgery operations. The suggested approach employs the deep neural architectures VGG16 and Resnet50 as feature extractors. The architecture comprises three parts: Feature extraction using individual models, a feature fusion layer, and a classification layer. Initially, we optimize the training process and feature extraction using VGG16 and ResNet50. The feature vectors obtained from both models are then fused together in the feature fusion layer and input into the classification layer for the classification task. Experiments are conducted on a custom-created dataset as well as benchmark datasets including ICPR FDC, IMEI Forged Number, and Kundu to demonstrate that the proposed method is superior to existing approaches. [ABSTRACT FROM AUTHOR]

Purpose: Web users rely heavily on online content make decisions without assessing the veracity of the content. The online content comprising text, image, video or audio may be tampered with to influence public opinion. Since the consumers of online information (misinformation) tend to trust the content when the image(s) supplement the text, image manipulation software is increasingly being used to forge the images. To address the crucial problem of image manipulation, this study focusses on developing a deep-learning-based image forgery detection framework. Design/methodology/approach: The proposed deep-learning-based framework aims to detect images forged using copy-move and splicing techniques. The image transformation technique aids the identification of relevant features for the network to train effectively. After that, the pre-trained customized convolutional neural network is used to train on the public benchmark datasets, and the performance is evaluated on the test dataset using various parameters. Findings: The comparative analysis of image transformation techniques and experiments conducted on benchmark datasets from a variety of socio-cultural domains establishes the effectiveness and viability of the proposed framework. These findings affirm the potential applicability of proposed framework in real-time image forgery detection. Research limitations/implications: This study bears implications for several important aspects of research on image forgery detection. First this research adds to recent discussion on feature extraction and learning for image forgery detection. While prior research on image forgery detection, hand-crafted the features, the proposed solution contributes to stream of literature that automatically learns the features and classify the images. Second, this research contributes to ongoing effort in curtailing the spread of misinformation using images. The extant literature on spread of misinformation has prominently focussed on textual data shared over social media platforms. The study addresses the call for greater emphasis on the development of robust image transformation techniques. Practical implications: This study carries important practical implications for various domains such as forensic sciences, media and journalism where image data is increasingly being used to make inferences. The integration of image forgery detection tools can be helpful in determining the credibility of the article or post before it is shared over the Internet. The content shared over the Internet by the users has become an important component of news reporting. The framework proposed in this paper can be further extended and trained on more annotated real-world data so as to function as a tool for fact-checkers. Social implications: In the current scenario wherein most of the image forgery detection studies attempt to assess whether the image is real or forged in an offline mode, it is crucial to identify any trending or potential forged image as early as possible. By learning from historical data, the proposed framework can aid in early prediction of forged images to detect the newly emerging forged images even before they occur. In summary, the proposed framework has a potential to mitigate physical spreading and psychological impact of forged images on social media. Originality/value: This study focusses on copy-move and splicing techniques while integrating transfer learning concepts to classify forged images with high accuracy. The synergistic use of hitherto little explored image transformation techniques and customized convolutional neural network helps design a robust image forgery detection framework. Experiments and findings establish that the proposed framework accurately classifies forged images, thus mitigating the negative socio-cultural spread of misinformation. [ABSTRACT FROM AUTHOR]

The conundrum of the ubiquitous deceptive reviews has overruled the online ontology with the obsession of obscure but obligatory posting of product reviews for the customers to believe, behold and beget the online product marketing. This mandates contemporary research in the direction to delve deeper on the application and analysis of deceiving online reviews with matured and advanced AI models functional on large scale datasets to effectively and efficiently demarcate between the genuine and the sham. The research counteracts the counterfeiting product reviews via the applications, assessment and analysis of the befitting AI models - Elastic-net Classifier model based on block coordinate descent with Wordcloud and its further performance enhancement through LightGBM Trees Classifier with Grid Search and Early Stopping support, with Log-Loss as performance metric for experimentation to gain insight into the intricacies of detection, diagnosis and diminution of fake product reviews. The paper also delineates discriminative and affirmative aspects of the dataset quality, statistics, stability and standards inherent and coherent to the creation of the dataset using Large Language Models (LLMs) intrinsic to the zeitgeist juncture of recent times promoting machines to produce large scale, cost effective bogus reviews in lieu of the Amazon Mechanical Turks. The results obtained with the Log-Loss holdout score of 0.1462 conforming the LightGBM classifier proves its performance better than the Elastic-Net classifier, conforming it as better than the ROC-AUC in terms of its proximity to the prediction probability for the matching actual/true value. [ABSTRACT FROM AUTHOR]

Copy-Move Forgery (CMF) is a common form of image manipulation attack that involves copying and pasting a part of an image to another position within the same image. This study proposes a Deep Learning (DL) model for detecting CMF, particularly in the presence of various malicious attacks. The proposed approach involves several steps, including converting the input image to grayscale, preprocessing the image using the Simple Linear Iterative Clustering (SLIC) algorithm to generate superpixel partitions, and then extracting keypoint features using the Speeded Up Robust Features (SURF) detector. Finally, a Generative Adversarial Network (GAN) is employed for feature description and matching. To assess the effectiveness of the approach, the types of features used for copy-move forgery were addressed. The proposed approach was examined under rotation, blurring, jpg compression, and scaling attacks. Furthermore, experimental results showed that the proposed approach can detect multiple CMFs with high accuracy. Finally, the proposed method was compared with recent state-of-the-art methods. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning, face forgery detection methods have also achieved remarkable progress. However, most methods suffer significant performance degradation on low-quality compressed face images. It is due to: (a) The image artifacts will be blurred in the process of image compression, resulting in the model learning insufficient artifact traces; (b) Low-quality images will introduce a lot of noise information, and minimizing the training error causes the model to absorb all correlations in the training dataset recklessly, leading to the over-fitting problem. To solve the above problems, we consider learning domain invariant representations to inscribe the correct relevance, i.e., artifacts, to improve the robustness of low-quality images. Specifically, we propose a novel face forgery detector, called DIFLD. The model has the following components: (1) a high-frequency invariant feature learning module(hf-IFLM), which effectively retrieves the blurred artifacts in low-quality compressed images; and (2) a high-dimensional feature distribution learning module(hd-FDLM), that guides the network to learn more about the consistent features of distribution. With the above two modules, the whole framework can learn more discriminative correct artifact features in an end-to-end manner. Through extensive experiments, we show that our proposed method is more robust to image quality variations, especially in low-quality images. Our proposed method achieves a 3.67% improvement over the state-of-the-art methods on the challenging dataset NeuralTextures. [ABSTRACT FROM AUTHOR]

In the real-world scenario, the digital videos are captured to keep in records the life related memories, security purpose, truthful evidence etc. Due to rise in multimedia technology, the digital videos are mostly posted over social websites and applications such as Facebook, Instagram, What's App, YouTube, etc. through the internet in daily routine. The contents of these social digital videos are manipulated by easily available editing tools and software. Therefore, the security of digital videos over social media are the most important requirement of people. This paper presents a systematic survey on Copy-Move forgery and its detection with several passive techniques in the digital videos. At first, Copy-Move forgery is introduced with its various types in this paper. Then, a survey is provided on the existing passive techniques for detecting Copy-Move forgery in digital videos. Here, brief review of techniques is also presented in the tabular forms with their used features, datasets, parameters, type of forgery and their limitations. Furthermore, this survey provides the parameters and datasets in detail which are used for the evaluation of existing techniques. Besides, the detecting tools for Copy-Move video forgery and its future directions are detailed in this survey. This paper also provides various new challenges for automatic detection of Copy-Move video forgery in the realm of deep learning. [ABSTRACT FROM AUTHOR]

Copy-move image forgery involves digitally modifying an image by copying and pasting content, hiding foreground objects, or highlighting them through duplication. However, as digital image forgery can become an extremely unsafe and challenging technique to classify images effectively, therefore understanding the detection and classification of real and forgery images is essential. In this research, an improved butterfly optimization algorithmbased convolutional neural network (IBOA-CNN) is proposed for copy-move forgery detection (CMFD), enhancing accuracy and convergence speed by expanding the iteration memory. This proposed approach is used to detect and classify images as original or fake accurately and effectively using deep learning (DL). Initially, the image is obtained by the MICC-F220, MICC-F600, MICC-F2000, and CASIA 2.0 datasets and then image pre-processing is performed by converting Red Green Blue (RGB) into a grayscale image. The Local Binary Pattern (LBP), Wavelet Features (DWT), and ResNet-50 are utilized to extract the features from the images, IBOA is used for feature selection and finally, CNN is employed for the classification to classify CMFD as an original or fake image. Existing methods such as Stacked Sparse Denoising Autoencoder-Spotted Hyena Optimizer-Grasshopper Optimization Algorithm (SSDAESHO-GOA), Deep CNN using ResNet-101, and CNN are compared with the IBOA-based CNN approach using MICCF-2000 dataset. The proposed IBOA-based CNN achieves a better accuracy of 97.59%, 99.20%, 99.83%, and 98.92% for MICC-F220, MICC-F600, MICC-F2000, and CASIA 2.0 datasets compared with the existing methods like SSDAE-SHO-GOA, Deep CNN using ResNet-101, and CNN. [ABSTRACT FROM AUTHOR]

Copy-move forgery detection poses a significant challenge because the brightness and contrast of forged and real regions are highly consistent, and the forensic clues are weakened by various affine transformations and post-processing operations. Existing deep learning models ignore the hierarchical dependencies of the features and pay less attention to information purification. To solve these problems, we propose a novel two-stage model to detect copy-move forgery, dubbed by CCAIR-Net. First, in the coarse localization stage, we propose a cross-scale condition aggregation module to integrate multi-level features from global to local. This aggregation structure can eliminate semantic disparities and capture multi-scale hierarchical dependencies of features. In particular, the condition aggregation block enables feature purification and filtering of interfering information. Second, in the refinement stage, the designed weighted fusion mechanism can guide the model to remove falsely detected regions and supplement the miss-detected regions by adaptively weighted fusion of coarse-grained and fine-grained features. Furthermore, the stage-wise training strategy takes advantage of different losses to train the network to detect tampered regions at various scales. Extensive experiments demonstrate that the proposed CCAIR-Net performs better than state-of-the-art methods. It can detect and segment forged and real areas more accurately, even for affine transformations and post-processing attack images. [ABSTRACT FROM AUTHOR]

The growing prevalence of fake images on the Internet and social media makes image integrity verification a crucial research topic. One of the most popular methods for manipulating digital images is image splicing, which involves copying a specific area from one image and pasting it into another. Attempts were made to mitigate the effects of image splicing, which continues to be a significant research challenge. This study proposes a new splicing detectionmodel, combining Sonine functions-derived convex-based features and deep features. Two stages make up the proposed method. The first step entails feature extraction, then classification using the "support vector machine" (SVM) to differentiate authentic and spliced images. The proposed Sonine functions-based feature extraction model reveals the spliced texture details by extracting some clues about the probability of image pixels. The proposed model achieved an accuracy of 98.93% when tested with the CASIA V2.0 dataset "Chinese Academy of Sciences, Institute of Automation" which is a publicly available dataset for forgery classification. The experimental results show that, for image splicing forgery detection, the proposed Sonine functions-derived convex-based features and deep features outperform state-of-the-art techniques in terms of accuracy, precision, and recall. Overall, the obtained detection accuracy attests to the benefit of using the Sonine functions alongside deep feature representations. Finding the regions or locations where image tampering has taken place is limited by the study. Future research will need to look into advanced image analysis techniques that can offer a higher degree of accuracy in identifying and localizing tampering regions. [ABSTRACT FROM AUTHOR]

In document forensics, identifying ink mismatches is crucial for detecting forgeries and determining document authenticity. However, identifying and separating specific inks from paper can be challenging. Hyperspectral imaging can capture unique spectral patterns exhibited by inks composed of different materials, even when their colors appear identical. Hyperspectral document analysis (HSDI) can be employed to authenticate documents by analyzing the ink. Earlier studies had insufficiently accurate black ink detection, so this paper proposes a novel approach using deep learning and pre-processing methods to improve black ink detection accuracy. The proposed approach uses supervised deep learning to identify ink mismatches in hyperspectral document images. The study evaluated the performance of the proposed model using a hyperspectral image dataset consisting of UWA (University of Western Australia) writing ink in both blue and black colors and different types of artificially identical color inks mixed in various ratios to find ink mismatches. The results showed that the proposed system performed better than other systems reported in the literature, improving the average accuracy by up to 0.18% for blue and 0.36% for black. The proposed method accurately detects ink mismatches and identifies various inks based on their unique spectral response, rendering it highly beneficial for applications in document forensics. [ABSTRACT FROM AUTHOR]

Due to the drastic increase in the generation of high-quality fake images in social networking, it is essential to design effective recognition approaches. Image/video manipulation defines any set of actions which can be carried out on digital content by the use of software editing approaches or artificial intelligence. A major kind of image and video editing comprises replicating the regions of the image, named as copy-move technique. Conventional image processing methods physically search for the pattern relevant to the replicated contents, restricting the utilization in massive classification of data. Contrastingly, the recently developed deep learning (DL) models have exhibited promising performance over the traditional models. In this aspect, this paper presents a novel intelligent deep learning based copy move image forgery detection (IDL-CMIFD) technique. The proposed IDL-CMIFD technique intends to design a DL model to classify the candidate images into two classes: original and forged/tampered and then localized the copy moved regions. In addition, the proposed IDL-CMIFD technique involves the Adam optimizer with Efficient Net based feature extractor to derive a useful set of feature vectors. Moreover, chaotic monarch butterfly optimization (CMBO) with deep wavelet neural network (DWNN) model is applied for classification purposes. The CMBO algorithm is utilized to optimally tune the parameters involved in the DWNN model in such a way that the classification performance gets improved. The performance validation of the proposed model takes place on benchmark MICC-F220, MICC-F2000, MICC-F600 datasets. A wide range of comparative analyses is performed and the results ensured the better performance of the IDL-CMIFD technique in terms of different evaluation parameters. [ABSTRACT FROM AUTHOR]

Face manipulation technology is rapidly evolving, making it impossible for human eyes to recognize fake faces in photos. Convolutional Neural Network (CNN) discriminators, on the other hand, can quickly achieve high accuracy in distinguishing fake from real face photos. In this paper, we investigate how CNN models distinguish between fake and real faces. According to our findings, face forgery detection heavily relies on the variation in the texture of the images. As a result of the aforementioned discovery, we propose a deep texture variation network, a new model for robust face fraud detection based on convolution and pyramid pooling. Convolution combines pixel intensity and pixel gradient information to create a stationary representation of composition difference information. Simultaneously, multi-scale information fusion based on the pyramid pooling can prevent the texture features from being destroyed. The proposed deep texture variation network outperforms previous techniques on a variety of datasets, including Faceforensics++, DeeperForensics-1.0, Celeb-DF, and DFDC. The proposed model is less susceptible to image distortion, such as JPEG compression and blur, which is important in this field. [ABSTRACT FROM AUTHOR]

Deep learning is considered one of the most efficient and reliable methods through which the legitimacy of a digital image can be verified. In the current cyber world where deepfakes have shaken the global community, confirming the legitimacy of a digital image is of great importance. With the advancements made in deep learning techniques, now we can efficiently train and develop state-of-the-art digital image forensic models. The most traditional and widely used method by researchers is convolution neural networks (CNN) for verification of image authenticity but it consumes a considerable number of resources and requires a large dataset for training. Therefore, in this study, a transfer learning based deep learning technique for image forgery detection is proposed. The proposed methodology consists of three modules namely; preprocessing module, convolutional module, and the classification module. By using our proposed technique, the training time is drastically reduced by utilizing the pre-trained weights. The performance of the proposed technique is evaluated by using benchmark datasets, i.e., BOW and BOSSBase that detect five forensic types which include JPEG compression, contrast enhancement (CE), median filtering (MF), additive Gaussian noise, and resampling. We evaluated the performance of our proposed technique by conducting various experiments and case scenarios and achieved an accuracy of 99.92%. The results show the superiority of the proposed system. [ABSTRACT FROM AUTHOR]

This study focuses on the field of voice forgery detection, which is increasing in importance owing to the introduction of advanced voice editing technologies and the proliferation of smartphones. This study introduces a unique dataset that was built specifically to identify forgeries created using the "Mix Paste" technique. This editing technique can overlay audio segments from similar or different environments without creating a new timeframe, making it nearly infeasible to detect forgeries using traditional methods. The dataset consists of 4665 and 45,672 spectrogram images from 1555 original audio files and 15,224 forged audio files, respectively. The original audio was recorded using iPhone and Samsung Galaxy smartphones to ensure a realistic sampling environment. The forged files were created from these recordings and subsequently converted into spectrograms. The dataset also provided the metadata of the original voice files, offering additional context and information that could be used for analysis and detection. This dataset not only fills a gap in existing research but also provides valuable support for developing more efficient deep learning models for voice forgery detection. By addressing the "Mix Paste" technique, the dataset caters to a critical need in voice authentication and forensics, potentially contributing to enhancing security in society. Dataset:  https://drive.google.com/drive/folders/10cBCvQTF-XqCfdQuUU4y%5fssrbi3hUJkw (accessed on 19 November 2023). Dataset License: CC BY-NC-ND [ABSTRACT FROM AUTHOR]

Digital media devices such as smartphones, cameras, and notebooks are becoming increasingly popular. Through digital platforms such as Facebook, WhatsApp, Twitter, and others, people share digital images, videos, and audio in large quantities. Especially in a crime scene investigation, digital evidence plays a crucial role in a courtroom. Manipulating video content with high-quality software tools is easier, which helps fabricate video content more efficiently. It is therefore necessary to develop an authenticating method for detecting and verifying manipulated videos. The objective of this paper is to provide a comprehensive review of the passive methods for detecting video forgeries. This survey has the primary goal of studying and analyzing the existing passive techniques for detecting video forgeries. First, an overview of the basic information needed to understand video forgery detection is presented. Later, it provides an in-depth understanding of the techniques used in the spatial, temporal, and spatio-temporal domain analysis of videos, datasets used, and their limitations are reviewed. In the following sections, standard benchmark video forgery datasets and the generalized architecture for passive video forgery detection techniques are discussed in more depth. Finally, identifying loopholes in existing surveys so detecting forged videos much more effectively in the future are discussed. [ABSTRACT FROM AUTHOR]

Now-a-days biometric systems are useful in recognizing person’s identity but criminals change their appearance in behaviour and psychological to deceive recognition system. To overcome from this problem we are using new technique called Deep Texture Features extraction from images and then building train machine learning model using CNN (Convolution Neural Networks) algorithm. This technique refers as LBPNet or NLBPNet as this technique heavily dependent on features extraction using LBP (Local Binary Pattern) algorithm. In this project we are designing LBP Based machine learning Convolution Neural Network called LBPNET to detect fake face images. Here first we will extract LBP from images and then train LBP descriptor images with Convolution Neural Network to generate training model. Whenever we upload new test image then that test image will be applied on training model to detect whether test image contains fake image or non-fake image. Below we can see some details on LBP. Local binary patterns (LBP) is a type of visual descriptor used for classification in computer vision and is a simple yet very efficient texture operator which labels the pixels of an image by thresholding the neighborhood of each pixel and considers the result as a binary number. Due to its discriminative power and computational simplicity, LBP texture operator has become a popular approach in various applications. It can be seen as a unifying approach to the traditionally divergent statistical and structural models of texture analysis. Perhaps the most important property of the LBP operator in real-world applications is its robustness to monotonic gray-scale changes caused, for example, by illumination variations. Another important property is its computational simplicity, which makes it possible to analyze images in challenging real-time settings. [ABSTRACT FROM AUTHOR]

Deep learning advancements have resulted in breakthroughs in facial forgery techniques. Facial forgery videos are growing increasingly lifelike, making it impossible for people to tell the difference between the real and the fake. The proliferation of facial forgery techniques, as well as the slowness with which they may be detected, could jeopardize personal data security. As a result, it's critical to look at approaches that can be trained on both real and fake videos and then utilized to identify facial forgeries or not in videos. This study found that forged face videos undergo truncation between consecutive frames of optical flow imaging after dense optical flow processing. We present an approach for detecting video face forgery that extracts and analyzes characteristics from real and fake material, then use those features to train classification models on Celeb-DF and FaceForensics++. In addition, we employ a unique facial double-triangle region to assist in the extraction of video inter-frame feature data. Experiments results show that the facial motion features extracted from the double triangle region successfully assist in capturing the dense optical flow truncation. Extensive evaluation suggests that our proposed approach is effective for video face forgery detection. [ABSTRACT FROM AUTHOR]

Digital image forgeries become one of the most challenges faced by technology users today. A copy-move forgery is one of the most common types of these forgeries. This type is not only common, but it is also very simple to execute to create deceptive images. Many algorithms use various technologies to create a high-performance Copy Move Forgery Detection (CMFD) system. There are currently two major CMFD trends: traditional CMFD algorithms and deep-learning-based CMFD algorithms. The main concept behind CMFD algorithms is to extract image features using various techniques and then search for matching features. This main idea can be carried out by using different feature extraction techniques with various matching techniques. For traditional algorithms, there are many types of features extractors used such as invariant image moments, texture and intensity descriptors, Scale-Invariant Feature Transform (SIFT), Speed Up Roust Features (SURF), Discrete Cosine Transform (DCT), Singular Value Decomposition (SVD), Principal Component Analysis (PCA), and other extractors. The strength of these extractors varies according to the image properties and the forgery's performance perfection. Deep learning-based CMFD algorithms operate as a black box, by extracting image features using layers with complex training and validation processes to achieve the best scenario, such as Convolutional Neural Network (CNN), Convolutional Long Short-Term Memory (CovLSTM), Multi-domain CNN, and Buster-Net. This paper discusses different types of digital image forgery with focusing on copy-move forgery. A detailed survey of various types of CMFD algorithms, on the other hand, has been displayed. The paper provides a comprehensive comparison of various algorithms and evaluates them using various types of evaluation parameters. Finally, the paper focuses on the different datasets used by various algorithms to evaluate their performance accuracy and testing time. These datasets are detailed in terms of image numbers, the number of original images, the number of forged images, the resolution variety in each dataset, the size of the tampered region in each dataset, and the strength of each dataset compared with each other. [ABSTRACT FROM AUTHOR]

In modern society, digital images can be far-reaching, and the images are manipulated by various software and hardware technologies. The image forgery activities are undertaken by the attackers mainly for damaging the reputation of people or receiving fiscal gain, etc. Taking this into consideration, many techniques are developed to detect the forged images. In this paper, a new deep learning-based approach is introduced for copy-move forgery detection. The input images are segmented into non-overlapping patches using superpixel-based modified dense peak clustering and the features are extracted from the segmented patches by applying deep learning structure of attention-based DenseNet 121 model. Besides, to compare every block, the depth of each pixel is reconstructed, and eventually matching process is carried out using the adaptive chimp patch matching approach, which detects the suspicious forged regions in an image. Finally, the matched keypoints are merged with the segmented patches using the merged keypoint matching algorithm. As a result, the new deep learning approach has detected the forged regions efficiently from the tampered image with less time even the image is compressed, rotated, or scaled. The performance is evaluated in terms of recall, precision, accuracy, F1-score, computational time, and False Positive Rate (FPR). Moreover, the performance is compared with the other existing approaches, and the outcomes showed that the proposed method has achieved higher accuracy of 97%, recall of 99%, precision of 97.84%, F1-score of 98.81%, FPR of 0.022 and less computational time of 2.5 s. [ABSTRACT FROM AUTHOR]

Copyright of Journal of South China University of Technology (Natural Science Edition) is the property of South China University of Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

With the increasing use of deep learning technology, there is a growing concern over creating deep fake images and videos that can potentially be used for fraud. In healthcare, manipulating medical images could lead to misdiagnosis and potentially life-threatening consequences. Therefore, the primary purpose of this study is to explore the use of deep learning algorithms to detect deep fake images by solving the problem of recognizing the handling of samples of cancer and other diseases. Therefore, this research proposes a framework that leverages state-of-the-art deep convolutional neural networks (CNN) and a large dataset of authentic and deep fake medical images to train a model capable of distinguishing between authentic and fake medical images. Specifically, the paper trained six CNN models, namely, ResNet101, ResNet50, DensNet121, DenseNet201, MobileNetV2, and MobileNet. These models had trained using 2000 samples over three classes: Untampered, FalseBenign, and False-Malicious, and compared against several state-of-the-art deep fake detection models. The proposed model enhanced ResNet101 by adding more layers, achieving a training accuracy of 99%. The findings of this study show near-perfect accuracy in detecting instances of tumor injections and removals. [ABSTRACT FROM AUTHOR]

With the widespread application of deep learning, many artificially generated fake images and videos appear on the Internet. However, it is difficult for people to distinguish the real from the fake ones, making the research on detecting and recognizing fake images or videos receive significant attention. Since new forgery techniques can reduce the effectiveness of specific detection methods or even make them ineffective, research on detecting facial depth forgery needs to be continuously developed. To defend against the onslaught of new facial depth forgery methods, we proposed an image gradient-based approach to transform the facial depth forgery detection problem into the recognition and analysis of video frames. Specifically, there are two key components in this approach: (1) we capture images from videos and crop the face section, which dramatically reduces the amount of data; (2) we use the image gradient operator to process the face image that extracts image features for detection and recognition. After these, we have conducted extensive experiments on different facial depth forgery datasets. Experimental results demonstrated that using our image gradient approach could effectively detect facial depth forgery and achieve excellent detection and identification performance. [ABSTRACT FROM AUTHOR]

The recent face forgery detection models have shown better accuracy for in-house generated and altered face image datasets. Therefore, the results of such a model cannot be compared directly and fairly. Moreover, some of the studies used datasets of smaller size, thus models can be overfitted. To address these issues, we selected a larger public dataset, created and altered by experts in photoshop. Thus, the goal of this study is to develop a face forgery detection model for expert-generated standard images. As a preprocessing step in our proposed approach, a convexhull reduced of an aligned face is extracted from each image. A convolutional neural network-based face forgery detection model is developed and trained from scratch. The images are normalized and label smoothing is applied to train the model to get minimum validation loss. The trained model is used to extract 1024 features of each image. Afterward, a feature selection algorithm is developed to select the optimum number of features without compromising the model performance. Moreover, random parameter optimization is performed to get the best parameters to train multiple classifiers. Only 36 features out of 1024 are selected using kNN(k = 4) for 76.04% sensitivity, 71.76% AUROC. The proposed approach achieved comparable results compared to the existing state-of-the-art face forgery models. [ABSTRACT FROM AUTHOR]

With the wide application of visual sensors and development of digital image processing technology, image copy-move forgery detection (CMFD) has become more and more prevalent. Copy-move forgery is copying one or several areas of an image and pasting them into another part of the same image, and CMFD is an efficient means to expose this. There are improper uses of forged images in industry, the military, and daily life. In this paper, we present an efficient end-to-end deep learning approach for CMFD, using a span-partial structure and attention mechanism (SPA-Net). The SPA-Net extracts feature roughly using a pre-processing module and finely extracts deep feature maps using the span-partial structure and attention mechanism as a SPA-net feature extractor module. The span-partial structure is designed to reduce the redundant feature information, while the attention mechanism in the span-partial structure has the advantage of focusing on the tamper region and suppressing the original semantic information. To explore the correlation between high-dimension feature points, a deep feature matching module assists SPA-Net to locate the copy-move areas by computing the similarity of the feature map. A feature upsampling module is employed to upsample the features to their original size and produce a copy-move mask. Furthermore, the training strategy of SPA-Net without pretrained weights has a balance between copy-move and semantic features, and then the module can capture more features of copy-move forgery areas and reduce the confusion from semantic objects. In the experiment, we do not use pretrained weights or models from existing networks such as VGG16, which would bring the limitation of the network paying more attention to objects other than copy-move areas.To deal with this problem, we generated a SPANet-CMFD dataset by applying various processes to the benchmark images from SUN and COCO datasets, and we used existing copy-move forgery datasets, CMH, MICC-F220, MICC-F600, GRIP, Coverage, and parts of USCISI-CMFD, together with our generated SPANet-CMFD dataset, as the training set to train our model. In addition, the SPANet-CMFD dataset could play a big part in forgery detection, such as deepfakes. We employed the CASIA and CoMoFoD datasets as testing datasets to verify the performance of our proposed method. The Precision, Recall, and F1 are calculated to evaluate the CMFD results. Comparison results showed that our model achieved a satisfactory performance on both testing datasets and performed better than the existing methods. [ABSTRACT FROM AUTHOR]

Digital images have become an important carrier for people to access information in the information age. However, with the development of this technology, digital images have become vulnerable to illegal access and tampering, to the extent that they pose a serious threat to personal privacy, social order, and national security. Therefore, image forensic techniques have become an important research topic in the field of multimedia information security. In recent years, deep learning technology has been widely applied in the field of image forensics and the performance achieved has significantly exceeded the conventional forensic algorithms. This survey compares the state-of-the-art image forensic techniques based on deep learning in recent years. The image forensic techniques are divided into passive and active forensics. In passive forensics, forgery detection techniques are reviewed, and the basic framework, evaluation metrics, and commonly used datasets for forgery detection are presented. The performance, advantages, and disadvantages of existing methods are also compared and analyzed according to the different types of detection. In active forensics, robust image watermarking techniques are overviewed, and the evaluation metrics and basic framework of robust watermarking techniques are presented. The technical characteristics and performance of existing methods are analyzed based on the different types of attacks on images. Finally, future research directions and conclusions are presented to provide useful suggestions for people in image forensics and related research fields. [ABSTRACT FROM AUTHOR]

At present, anti-counterfeiting schemes based on the combination of anti-counterfeiting patterns and two-dimensional codes is a research hotspot in digital anti-counterfeiting technology. However, many existing identification schemes rely on special equipment such as scanners and microscopes; there are few methods for authentication that use smartphones. In particular, the ability to classify blurry pattern images is weak, leading to a low recognition rate when using mobile terminals. In addition, the existing methods need a sufficient number of counterfeit patterns for model training, which is difficult to acquire in practical scenarios. Therefore, an authentication scheme for an anti-counterfeiting pattern captured by smartphones is proposed in this paper, featuring a single classifier consisting of two modules. A feature extraction module based on U-Net extracts the features of the input images; then, the extracted feature is input to a one-class classification module. The second stage features a boundary-optimized OCSVM classification method. The classifier only needs to learn positive samples to achieve effective identification. The experimental results show that the proposed approach has a better ability to distinguish the genuine and counterfeit anti-counterfeiting pattern images. The precision and recall rate of the approach reach 100%, and the recognition rate for the blurry images of the genuine anti-counterfeiting patterns is significantly improved. [ABSTRACT FROM AUTHOR]

Forgery detection is one of the challenging subjects in computer vision. Forgery is performed using image manipulation with editor tools. Image manipulation tries to change the concept of the image but preserves the integrity of the texture and structure of the image as much as possible. Images are used as evidence in some applications, so if the images are manipulated, they will not be reliable. The copy-move forgery is one of the simplest image manipulation methods. This method removes or inserts information into the image with the least clue by copying a part of the image and pasting it into other places of the same image. Recently, traditional (block-based and keypoint-based) and deep learning methods have been proposed to detect forgery images. Traditional methods include two main steps, feature extraction, and feature matching. Unlike the traditional methods, the deep learning method performs the forgery detection automatically by extracting hierarchical features directly from the data. This paper presents a deep learning method for forgery detection at both image and pixel levels. In this method, we used a pre-trained deep model with a global average pooling (GAP) layer instead of default fully connected layers to detect forgery. The GAP layer creates a good dependency between the feature maps and the classes. In pixel forgery detection, a visualization technique called heatmap activation is used in forgery images. This technique identifies parts of the image that are candidates for forgery. Then, the best candidate is selected and the location of the forgery is determined. The proposed method is performed on the CoMoFod and MICC datasets. The extensive experiments showed the satisfactory performance of the proposed method. [ABSTRACT FROM AUTHOR]

Protecting data against tampering is a significant concern in modern times. Digital photographs are essential for displaying information. Digital picture forgeries include adding unusual patterns to real pictures, causing visual heterogeneity. CMF is a sort of digital image forgery in which a segment of an image is linked to a similar picture to cover or recreate forgeried components. The forgery seems authentic since the goal area has the same qualities as the original. Despite several ways to detect CMFD, there exist research gaps such as false detection, excessive execution time and low accuracy. Therefore, to address this issue, we present a hybrid optimization technique and classifier for CMFD. Proposed a novel deep learning technique stacked sparse denoising autoencoder (SSDAE) to classify the images as legitimate or fake. Additionally, the weight and bias parameters of the SSDAE model are optimized using the Grasshopper Optimization Algorithm (GOA) and the Spotted Hyena optimizer (SHO). The experiments are conducted on MICC-F220, MICC-F600, MICC-F2000 and CASIA2.0 datasets. Experimental results indicate that the proposed scheme find out image forgery region with Accuracy = 97.45%; Precision = 98.75%; Recall = 98.25% and F1 = 98.55% on MICC-F200 dataset, Accuracy = 98.92%; Precision = 88.45%; Recall = 85.21% and F1 = 91.41% on MICC-F600 dataset, Accuracy = 99.12%; Precision = 99.25%; Recall = 91.14% and F1 = 85.32% on MICC-F2000 dataset and Accuracy = 98.02%; Precision = 96.03%; Recall = 97.74% and F1 = 97.48% on CASIA 2.0 dataset. [Extracted from the article]

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]