Explore the vast range of titles available.

Extensive development in Generative Artificial Intelligence and the growth of Online Social Networks have facilitated the creation and sharing of synthetic images like never before. This has led to an overwhelming increase in the dissemination of fake content on OSNs. Maintaining the integrity of OSNs is paramount, and detecting synthetic images plays a crucial role in preserving social balance. Existing solutions, while achieving perfect detection performance on test datasets, often experience significant degradation when applied to OSN images. In our work, we propose a robust fake image detector that relies on features minimally affected by common OSN perturbations. Specifically, our solution leverages gradient features in color channels, including chrominance and luminance channels, accompanied by a residual-based CNN. Our low-parameterized solution is characterized by low complexity, making it particularly resource-efficient and suitable for edge devices. Thorough experiments demonstrate that our method achieves 100% accuracy in identifying fake images on our test dataset. We further evaluate the approach on images generated by contemporary generative adversarial networks and diffusion models, where it consistently exhibits strong detection performance. In addition, when applied to images that undergo post-processing operations designed to mimic OSN circulation, the proposed detector maintains high accuracy and robustness. Overall, results indicate that our proposed gradient-based color-channel features, coupled with a low-complexity residual network, provide an effective and OSN-resilient solution for synthetic image detection across both generic and post-processed/compressed scenarios. •AI-generated hyper-realistic synthetic images pose cyber-social threats.•OSN-specific transformations on synthetic images further complicate detection.•Introduced GoC for detection, leveraging gradient magnitude/direction in chroma-luma.•Proposed RNet, with GoC, achieves up to 100% accuracy with minimal parameters.•Robust OSN detection with SOTA results against post-processing and compression.

The proliferation of Artificial Intelligence (AI) models such as Generative Adversarial Networks (GANs) has shown impressive success in image synthesis. Artificial GAN-based synthesized images have been widely spread over the Internet with the advancement in generating naturalistic and photo-realistic images. This might have the ability to improve content and media; however, it also constitutes a threat with regard to legitimacy, authenticity, and security. Moreover, implementing an automated system that is able to detect and recognize GAN-generated images is significant for image synthesis models as an evaluation tool, regardless of the input modality. To this end, we propose a framework for reliably detecting AI-generated images from real ones through Convolutional Neural Networks (CNNs). First, GAN-generated images were collected based on different tasks and different architectures to help with the generalization. Then, transfer learning was applied. Finally, several Class Activation Maps (CAM) were integrated to determine the discriminative regions that guided the classification model in its decision. Our approach achieved 100% on our dataset, i.e., Real or Synthetic Images (RSI), and a superior performance on other datasets and configurations in terms of its accuracy. Hence, it can be used as an evaluation tool in image generation. Our best detector was a pre-trained EfficientNetB4 fine-tuned on our dataset with a batch size of 64 and an initial learning rate of 0.001 for 20 epochs. Adam was used as an optimizer, and learning rate reduction along with data augmentation were incorporated.

The possibility of carrying out a meaningful forensic analysis on printed and scanned images plays a major role in many applications. First of all, printed documents are often associated with criminal activities, such as terrorist plans, child pornography, and even fake packages. Additionally, printing and scanning can be used to hide the traces of image manipulation or the synthetic nature of images, since the artifacts commonly found in manipulated and synthetic images are gone after the images are printed and scanned. A problem hindering research in this area is the lack of large scale reference datasets to be used for algorithm development and benchmarking. Motivated by this issue, we present a new dataset composed of a large number of synthetic and natural printed face images. To highlight the difficulties associated with the analysis of the images of the dataset, we carried out an extensive set of experiments comparing several printer attribution methods. We also verified that state-of-the-art methods to distinguish natural and synthetic face images fail when applied to print and scanned images. We envision that the availability of the new dataset and the preliminary experiments we carried out will motivate and facilitate further research in this area.

Due to the appeal of Generative Adversarial Networks (GANs), synthetic face images generated with GAN models are difficult to differentiate from genuine human faces and may be used to create counterfeit identities. However, these face images contain artifacts presented in irises owing to the irregularity of highlights between the left and right irises. Adversaries can utilize PS documents of these images trying to conceal the artifacts of images, which makes it more challenging to distinguish between pristine and fake images. In order to tackle this, our research introduces a complete dataset and analytical tools that make a substantial contribution to multimedia forensics. This allows for the authentication of documents despite common alterations in the PS documents. Owing to the lack of large-scale reference IRIS datasets in the PS scenario, this study provided a pioneering dataset aiming to set a standard for multimedia forensic investigations. Given face images, we extracted iris images using the Dlib (King, J Mach Learn Res 10(60):1755–1758, 2020 ) and EyeCool (Wang et al. 2021 ) models, as described in Guo et al. ( 2022 ). However, in some cases, the potential eyelid occlusion phenomenon resulted in incomplete iris images. We utilized a hypergraph convolution-based image inpainting technique to complete the missing pixels in the extracted iris images, thus uncovering the intricate relationships within the iris data. To evaluate the IRIS image dataset and highlight associated issues, we conducted a series of analyses using Siamese Neural Networks, including ResNet50, Xception, VGG16, and MobileNet-v2, to measure the similarities between authentic and synthetic human iris images. Our SNN model, with four different backbones, effectively differentiated between genuine and synthetic iris images. For instance, using the Xception network, we achieved 56.76% similarity in IRISes for synthetic images and 92.77% similarity in IRISes for real images. The effectiveness of our approach was demonstrated by the similarity scores obtained from all SNN architectures, which showed a significant difference between the GAN-generated images from ProGAN or StyleGAN and the original PS iris photos. The similarity scores resulting from StyleGAN are higher than those of the ProGAN architecture, but at its highest, it is 76%, while for the pristine images, it ranges from 85% to 95%. This discrepancy can be utilized in order to distinguish between pristine and GAN-generated images.

SNS providers are known to carry out the recompression and resizing of uploaded images, but most conventional methods for detecting fake images/tampered images are not robust enough against such operations. In this paper, we propose a novel method for detecting fake images, including distortion caused by image operations such as image compression and resizing. We select a robust hashing method, which retrieves images similar to a query image, for fake-image/tampered-image detection, and hash values extracted from both reference and query images are used to robustly detect fake-images for the first time. If there is an original hash code from a reference image for comparison, the proposed method can more robustly detect fake images than conventional methods. One of the practical applications of this method is to monitor images, including synthetic ones sold by a company. In experiments, the proposed fake-image detection is demonstrated to outperform state-of-the-art methods under the use of various datasets including fake images generated with GANs.

This article tackles the problem of detecting small objects in satellite or aerial remote sensing images by relying on super-resolution to increase image spatial resolution, thus the size and details of objects to be detected. We show how to improve the super-resolution framework starting from the learning of a generative adversarial network (GAN) based on residual blocks and then its integration into a cycle model. Furthermore, by adding to the framework an auxiliary network tailored for object detection, we considerably improve the learning and the quality of our final super-resolution architecture, and more importantly increase the object detection performance. Besides the improvement dedicated to the network architecture, we also focus on the training of super-resolution on target objects, leading to an object-focused approach. Furthermore, the proposed strategies do not depend on the choice of a baseline super-resolution framework, hence could be adopted for current and future state-of-the-art models. Our experimental study on small vehicle detection in remote sensing data conducted on both aerial and satellite images (i.e., ISPRS Potsdam and xView datasets) confirms the effectiveness of the improved super-resolution methods to assist with the small object detection tasks.

Image inpainting with large missing blocks is quite challenging to obtain visual consistency and realistic effect. In this paper, the multi-scale patch generative adversarial networks with edge detection image inpainting (MPGE) was proposed. Firstly, an edge detector was introduced into the generator of multi-scale generative adversarial networks (GAN) to guide the inpainting of the edge contour in the image inpainting, which improved the inpainting effect of image posture and expression. Secondly, we designed a patch-GAN as the local discriminant to capture high frequency, and a function L 2 -loss was utilized to keep the high resolution and style of the original image. Thirdly, a multi-head attention mechanism was introduced into the generator and local discriminator to build a multilevel and multi-dimensional dependent network model for image subspaces, which improved the global consistency of the inpainted image. Finally, by finding the minimum data set with similar network expression ability, we quickly obtained the optimal value of multi-head. Thereby, a lot of training time was saved. The experiments conducted on Celeba dataset proved that our proposed algorithm quantitatively and qualitatively outperformed the baselines.

As an active microwave coherent imaging technology, synthetic aperture radar (SAR) images suffer from severe speckle noise and low-resolution problems due to the limitations of the imaging system, which cause difficulties in image interpretation and target detection. However, the existing SAR super-resolution (SR) methods usually reconstruct the images by a determined degradation model and hardly consider multiplicative speckle noise, meanwhile, most SR models are trained with synthetic datasets in which the low-resolution (LR) images are down-sampled from their high-resolution (HR) counterparts. These constraints cause a serious domain gap between the synthetic and real SAR images. To solve the above problems, this paper proposes an unsupervised blind SR method for SAR images by introducing SAR priors in a cycle-GAN framework. First, a learnable probabilistic degradation model combined with SAR noise priors was presented to satisfy various SAR images produced from different platforms. Then, a degradation model and a SR model in a unified cycle-GAN framework were trained simultaneously to learn the intrinsic relationship between HR–LR domains. The model was trained with real LR and HR SAR images instead of synthetic paired images to conquer the domain gap. Finally, experimental results on both synthetic and real SAR images demonstrated the high performance of the proposed method in terms of image quality and visual perception. Additionally, we found the proposed SR method demonstrates the tremendous potential for target detection tasks by reducing missed detection and false alarms significantly.

The coronavirus (COVID-19) pandemic is putting healthcare systems across the world under unprecedented and increasing pressure according to the World Health Organization (WHO). With the advances in computer algorithms and especially Artificial Intelligence, the detection of this type of virus in the early stages will help in fast recovery and help in releasing the pressure off healthcare systems. In this paper, a GAN with deep transfer learning for coronavirus detection in chest X-ray images is presented. The lack of datasets for COVID-19 especially in chest X-rays images is the main motivation of this scientific study. The main idea is to collect all the possible images for COVID-19 that exists until the writing of this research and use the GAN network to generate more images to help in the detection of this virus from the available X-rays images with the highest accuracy possible. The dataset used in this research was collected from different sources and it is available for researchers to download and use it. The number of images in the collected dataset is 307 images for four different types of classes. The classes are the COVID-19, normal, pneumonia bacterial, and pneumonia virus. Three deep transfer models are selected in this research for investigation. The models are the Alexnet, Googlenet, and Restnet18. Those models are selected for investigation through this research as it contains a small number of layers on their architectures, this will result in reducing the complexity, the consumed memory and the execution time for the proposed model. Three case scenarios are tested through the paper, the first scenario includes four classes from the dataset, while the second scenario includes 3 classes and the third scenario includes two classes. All the scenarios include the COVID-19 class as it is the main target of this research to be detected. In the first scenario, the Googlenet is selected to be the main deep transfer model as it achieves 80.6% in testing accuracy. In the second scenario, the Alexnet is selected to be the main deep transfer model as it achieves 85.2% in testing accuracy, while in the third scenario which includes two classes (COVID-19, and normal), Googlenet is selected to be the main deep transfer model as it achieves 100% in testing accuracy and 99.9% in the validation accuracy. All the performance measurement strengthens the obtained results through the research.