Region of Interest (ROI)-based image compression optimizes bit allocation by prioritizing ROI for higher-quality reconstruction. However, as the users (including human clients and downstream machine tasks) become more diverse, ROI-based image compression needs to be customizable to support various preferences. For example, different users may define distinct ROI or require different quality trade-offs between ROI and non-ROI. Existing ROI-based image compression schemes predefine the ROI, making it unchangeable, and lack effective mechanisms to balance reconstruction quality between ROI and non-ROI. This work proposes a paradigm for customizable ROI-based deep image compression. First, we develop a Text-controlled Mask Acquisition (TMA) module, which allows users to easily customize their ROI for compression by just inputting the corresponding semantictext. It makes the encoder controlled bytext. Second, we design a Customizable Value Assign (CVA) mechanism, which masks the non-ROI with a changeable extent decided by users instead of a constant one to manage the reconstruction quality trade-off between ROI and non-ROI. Finally, we present a Latent Mask Attention (LMA) module, where the latent spatial prior of the mask and the latent Rate-Distortion Optimization (RDO) prior of the image are extracted and fused in the latent space, and further used to optimize the latent representation of the source image. Experimental results demonstrate that our proposed customizable ROI-based deep image compression paradigm effectively addresses the needs of customization for ROI definition and mask acquisition as well as the reconstruction quality trade-off management between the ROI and non-ROI. Additionally, even by using the uniform mask as input, our method still outperforms the anchor methods in image reconstruction and machine vision tasks (such as object detection and instance segmentation). Our source code will be available at: https://github.com/hccavgcyv/Customizable-ROI-Based-Deep-Image-Compression.

With the emergence of adversarial steganography, existing specialized steganalysis models suffer a significant performance decline in detecting non-homologous adversarial steganographic methods (i.e., trained on traditional-based method and tested on adversarial-based method), resulting in insufficient robustness in complex network environments. To address this issue, we propose a two-stage robust steganalysis framework with multi-feature enhancement against adversarial steganography. The framework integrates edge-aware attention with multi-dimensional statistical features to enhance robustness against adversarial steganography. In the first stage, we design a covariance pooling based convolutional neural network and integrate an edge-aware attention mechanism to improve the feature representation of subtle steganographic traces, enabling fast detection for most samples. In the second stage, samples with uncertain confidence scores from the first stage are further analyzed by extracting block-wise entropy features, global entropy features, and SRM co-occurrence features, followed by dimensionality reduction via principal component analysis (PCA) and classification using a random forest. The final decision is made through the collaborative fusion of the two stages. Experimental results demonstrate that the proposed method achieves excellent detection performance (2.57% average improvement over the existing best method) with strong robustness for adversarial steganography, and its generalization capability is further validated in cross-dataset scenarios. Furthermore, comprehensive ablation studies validate the efficacy of the network architecture.

DeepFake, an AI-driven face-swapping technique, has been weaponized to spread disinformation. In response, researchers have developed forensic detectors to identify such manipulations. To circumvent these defenses, a growing body of work now focuses on generating adversarial samples—carefully perturbed forgeries designed to deceive detection tools. However, most existing adversarial generation methods sacrifice image quality to achieve undetectability, introducing perceptible artifacts that ironically make them more detectable under human scrutiny. To address this limitation, we propose a novel spectral fusion approach to multimodally synthesize forgery traces from authentic facial images. Unlike traditional noise injection methods, our technique integrates diffusion-based noise during image preprocessing, embedding perturbations in the forward process of a diffusion model. This approach not only deceives forensic detectors more effectively but also preserves high visual fidelity. Through extensive experiments, our method achieves state-of-the-art DeepFake anti-forensic performance while preserving high visual fidelity, ensuring that the adversarial samples remain indistinguishable from real images.

The high-quality, realistic images generated by generative models pose significant challenges for exposing them. So far, data-driven deep neural networks have been justified as the most efficient forensics tools for the challenges. However, they may be over-fitted to certain semantics, resulting in considerable inconsistency in detection performance across different contents of generated samples. It could be regarded as an issue of detection fairness. In this paper, we propose a novel framework named Fairadapter to tackle the issue. In comparison with existing state-of-the-art methods, our model achieves improved fairness performance. Our project is vailable at https://github.com/AppleDogDog/FairnessDetection

Faces synthesized by diffusion models (DMs) with high-quality and controllable attributes pose a significant challenge for Deepfake detection. Most state-of-the-art detectors only yield a binary decision, incapable of forgery localization, attribution of forgery methods, and providing analysis on the cause of forgeries. In this work, we integrate Multimodal Large Language Models (MLLMs) within DM-based face forensics, and propose a fine-grained analysis triad framework called VLForgery, that can 1) predict falsified facial images; 2) locate the falsified face regions subjected to partial synthesis; and 3) attribute the synthesis with specific generators. To achieve the above goals, we introduce VLF (Visual Language Forensics), a novel and diverse synthesis face dataset designed to facilitate rich interactions between `Visual' and `Language' modalities in MLLMs. Additionally, we propose an extrinsic knowledge-guided description method, termed EkCot, which leverages knowledge from the image generation pipeline to enable MLLMs to quickly capture image content. Furthermore, we introduce a low-level vision comparison pipeline designed to identify differential features between real and fake that MLLMs can inherently understand. These features are then incorporated into EkCot, enhancing its ability to analyze forgeries in a structured manner, following the sequence of detection, localization, and attribution. Extensive experiments demonstrate that VLForgery outperforms other state-of-the-art forensic approaches in detection accuracy, with additional potential for falsified region localization and attribution analysis.

Current AIGC detectors often achieve near-perfect accuracy on images produced by the same generator used for training but struggle to generalize to outputs from unseen generators. We trace this failure in part to latent prior bias: detectors learn shortcuts tied to patterns stemming from the initial noise vector rather than learning robust generative artifacts. To address this, we propose \textbf{On-Manifold Adversarial Training (OMAT)}: by optimizing the initial latent noise of diffusion models under fixed conditioning, we generate \emph{on-manifold} adversarial examples that remain on the generator’s output manifold—unlike pixel-space attacks, which introduce off-manifold perturbations that the generator itself cannot reproduce and that can obscure the true discriminative artifacts. To test against state-of-the-art generative models, we introduce GenImage++, a test-only benchmark of outputs from advanced generators (Flux.1, SD3) with extended prompts and diverse styles. We apply our adversarial-training paradigm to ResNet50 and CLIP baselines and evaluate across existing AIGC forensic benchmarks and recent challenge datasets. Extensive experiments show that adversarially trained detectors significantly improve cross-generator performance without any network redesign. Our findings on latent-prior bias offer valuable insights for future dataset construction and detector evaluation, guiding the development of more robust and generalizable AIGC forensic methodologies.

The integration of Cognitive Internet of Things (IoT) sensors with autonomous aerial vehicles (AAVs) has transformed industrial sectors, such as monitoring, logistics, and infrastructure inspection. However, the advancement of visual synthesis technologies like generative adversarial networks and diffusion models has introduced significant risks by enabling the creation of highly realistic AI-manipulated content, making the detection of falsified imagery increasingly challenging. Existing detection methods, largely based on convolutional neural networks (CNNs), focus primarily on global image features and often overlook crucial relational connections, limiting their robustness and generalization. To overcome these limitations, we propose a novel dual-stream architecture that integrates global feature extraction with relational feature learning. By combining the CLIP model with a graph-based topology, our approach identifies hard-to-detect samples and processes them through a graph convolutional network (GCN) to capture both structural and relational information. Extensive evaluations validate the robustness and generalization ability of our method across various generative models and real-world perturbations. This approach offers a scalable and reliable solution to ensure data integrity in industrial IoT systems, helping to preserve societal trust in AI-driven applications.

Hashing technology has an excellent high dimensional visual information encoding ability. It can map distance information from high dimensional to low dimensional Hamming space, which is widely used in large-scale image nearest neighbor search tasks. Most recent studies, such as pair-wise and tripletwise, use local positional relations to construct hashing functions. These learning methods, which are only based on local information, will lead to an incoherent feature representation, especially for semantic similarity features. Therefore, we propose a global distance estimation hashing (DEH). The DEH establishes a deep hashing model by constructing global distance relations that can define a distance between every paired category. Thus the distance relations constructed by DEH include much more detailed information. In other words, DEH focuses on global distance relations and makes the division of boundaries have excellent performance, especially for those samples with subtle changes. After the mapping, the model quantization approach effectively decreases the quantization loss caused by transitioning from the real-valued space to the Hamming space. Numerous experiments show that our DEH achieves excellent results on CIFAR-10, NUS-WIDE and ImageNet. These achievements not only validate the effectiveness of DEH in general image hashing retrieval tasks but also demonstrate its significant advantages in handling the large-scale multimedia retrieval systems.

Internet of Medical Things (IoMT) enabled by artificial intelligence (AI) technologies can facilitate automatic diagnosis and management of chronic diseases (e.g., intestinal parasitic infection) based on 2D microscopic images. To improve model performance of object detection challenged by microscopic image characteristics (e.g., focus failure, motion blur, and whether zoomed or not), we propose coupled composite backbone network (C2BNet) to execute parasitic egg detection using 2D microscopic images. In particular, the C2BNet backbone adopts a two-path structure-based backbone and leverages model heterogeneity to learn object features from different perspectives. A novel feature composition style is proposed to flow features within the coupled composite backbone, and ensure mutual enhancement of feature representation ability among different paths of the backbone. To further improve the accuracy of detection results, we propose multiscale weighted box fusion (WBF) to fuse location and confidence scores of all bounding boxes predicted from multiscale feature maps, and iteratively refine box coordinates to form the final prediction. Experimental results on Chula-ParasiteEgg-11 dataset demonstrate that C2BNet not only performs satisfactorily compared with state-of-the-art methods, but also can focus more on learning detailed morphology features and abundant semantic features, resulting in more precise detection for parasitic eggs located in the 2D microscopic image.

DeepFake, an AI technology that can automatically synthesize facial forgeries, has recently attracted worldwide attention. While DeepFakes can be entertaining, they can also be used to spread falsified information or be weaponized as cognition warfare. Forensic researchers have been dedicated to designing defensive algorithms to combat such disinformation. However, attacking technologies have been developed to make DeepFake products more aggressive. For example, by launching anti-forensics and adversarial attacks, DeepFakes can be disguised as authentic media to evade forensic detectors. However, such manipulations often sacrifice image quality for satisfactory undetectability. To address this issue, we propose a method to generate a novel adversarial sharpening mask for launching black-box anti-forensics attacks. Unlike many existing methods, our approach injects perturbations that allow DeepFakes to achieve high anti-forensics performance while maintaining pleasant sharpening visual effects. Experimental evaluations demonstrate that our method successfully disrupts state-of-the-art DeepFake detectors. Moreover, compared to images processed by existing DeepFake anti-forensics methods, our method’s quality of anti-forensics DeepFakes rendered is significantly improved. Our code is available at https://github.com/fb-reps/HQ-AF_GAN .

Liver tumor segmentation plays a crucial role in the diagnosis and treatment of hepatic lesions. However, accurate tumor segmentation remains a challenging task due to the fuzzy boundaries of liver tumors and the uncertainty in shape, size, and location. In this paper, we propose a new end-to-end segmentation network called CGD-Net, which incorporates Transformer and frequency-domain features into a convolutional network, and proposes a new decoder structure to automatically learn from Segmentation of liver tumors in CT images. The proposed CGD-Net consists of a Transformer encoder, a frequency domain information fusion module, a gated decoder and three skip connections. Using the powerful feature extraction capability of the Transformer encoder to extract multi-feature information.CGD(Control Gate Decoder)blocks gradually restore the feature information lost in the encoding process by emphasizing the original information.In order to fully utilize the information of the original image, three skip connections are used to connect each encoder layer and its corresponding decoder layer, and a FEM (Frequency-domain Enhance module)is built in the third skip connection to fuse frequency domain features. Experiments on the LiTS dataset validate that the proposed CGD-Net can effectively segment liver tumors from CT images in an end-to-end manner, with segmentation accuracy exceeding many existing methods.

Although effective deepfake detection models have been developed in recent years, recent studies have revealed that these models can result in unfair performance disparities among demographic groups, such as race and gender. This can lead to particular groups facing unfair targeting or exclusion from detection, potentially allowing misclassified deepfakes to manipulate public opinion and undermine trust in the model. The existing method for addressing this problem is providing a fair loss function. It shows good fairness performance for intra-domain evaluation but does not maintain fairness for cross-domain testing. This highlights the significance of fairness generalization in the fight against deepfakes. In this work, we propose the first method to address the fairness generalization problem in deepfake detection by simultaneously considering features, loss, and optimization aspects. Our method employs disentanglement learning to extract demographic and domain-agnostic forgery features, fusing them to encourage fair learning across a flattened loss landscape. Extensive experiments on prominent deepfake datasets demonstrate our method's effectiveness, surpassing state-of-the-art approaches in preserving fairness during cross-domain deepfake detection. The code is available at https://github.com/Purdue-M2/Fairness-Generalization.

DeepFake, an AI technology for creating facial forgeries, has garnered global attention. Amid such circumstances, forensics researchers focus on developing defensive algorithms to counter these threats. In contrast, there are techniques developed for enhancing the aggressiveness of DeepFake, e.g., through anti-forensics attacks, to disrupt forensic detectors. However, such attacks often sacrifice image visual quality for improved undetectability. To address this issue, we propose a method to generate novel adversarial sharpening masks for launching black-box anti-forensics attacks. Unlike many existing arts, with such perturbations injected, DeepFakes could achieve high anti-forensics performance while exhibiting pleasant sharpening visual effects. After experimental evaluations, we prove that the proposed method could successfully disrupt the state-of-the-art DeepFake detectors. Besides, compared with the images processed by existing DeepFake anti-forensics methods, the visual qualities of antiforensics DeepFakes rendered by the proposed method are significantly refined.

With the advancement of deep neural networks (DNN), detecting falsified facial images has become a significant challenge. Previous state-of-the-art methods used fake images generated by various techniques as positive samples during the training phase. This strategy ensures that the model is exposed to a wide range of fake generation methods, resulting in a substantially higher number of positive samples than negative ones. However, in real-world scenarios, authentic images distinctly outnumber fake ones, which is not consistent with the hypothesis of designing DNN-based forensics detectors. Furthermore, the excessive use of certain fake images for training DNNs may lead to overfitting to specific fake generation techniques. Current research indicates that detectors often learn semantic features of the images, which can affect their performance. To address this issue, we propose a two-stage meta-learning feature disentanglement framework (TMFD). By leveraging the prior knowledge of meta-learning and incorporating a fine-tuning stage, extensive experimental results demonstrate that our method performs excellently across different domains.

The finance-level Artificial Intelligence of Things (AIoT) is going to become a novel media in the 6G-driven digital society. Inside the financial AIoT environment, large-scale crowd credit assessment with the guarantee of low latency has been a general demand. Facing limited computational resources, there is still a lack of effective computation offloading methods for this purpose to ensure low latency. In order to deal with such an issue, this article introduces edge computing mode and proposes a low-latency edge computation offloading scheme for trust evaluation in financial AIoT. With different elements involved in the assessment process being denoted via mathematical description, a multiobjective optimization problem with constraints is formulated. Then, the aforementioned optimization problem is solved by a specific search algorithm, so that optimal task offloading schemes can be found. To assess the performance of the proposal, some simulation experiments are conducted to verify the proposed task offloading method. And it can be reflected from numerical results that latency can be well reduced compared with baseline methods.

Face anti-spoofing aims to distinguish between live and spoof images to ensure the authenticity and reliability of face recognition. Methods based on convolutional neural networks surpass prior approaches in accuracy but remain vulnerable to adversarial attacks. Traditional vulnerability disclosure relies on image quality metrics, which lack crucial identity details for face recognition in deceptive images. Thus, we introduce a novel framework that creates identity-consistent adversarial samples for face anti-spoofing. We also redefine image quality assessment for anti-spoofing by using detection rates from facial recognizers rather than conventional metrics. Inspired by style transfer, our generator incorporates an LKA module to enhance performance. An identity recognition module ensures consistency within synthesized images, capturing the essence of identity across live and spoof visuals. Our approach outperforms most adversarial tactics on anti-spoofing detectors while retaining a high identity recognition rate.

Fake news detection has been a more urgent technical demand for operators of online social platforms, and the prevalence of deep learning well boosts its development. From the model structure, existing research works can be categorized into three types: convolution filtering-based neural network approaches, sequential analysis-based neural network approaches, and attention mechanism-based neural network approaches. However, almost all of them were developed oriented to scenes of a single language, without considering the context of mixed languages. To bridge such gap, this article extends to the basic pretraining language processing model transformer into the multiscale format and proposes a novel fake news detection model for the context of mixed languages through a multiscale transformer to fully capture the semantic information of the text. By extracting more fruitful feature levels of initial textual contents, it is expected to obtain more resilient feature spaces for the semantics characteristics of mixed languages. Finally, experiments are conducted on a postprocessed real-world dataset to illustrate the efficiency of the proposal by comparing performance with four baseline methods. The results obtained show that the proposed method has an accuracy of about 2%–10% higher than commonly used baseline models, indicating that the scheme has appropriate detection efficiency in mixed language scenarios.

This paper proposes a dual-channel network for DeepFake detection. The network comprises two channels: one using a stacked Maxvit block to process the downsampled original images, and the other using a stacked ResNet basic block to capture features from the discrete cosine transform of the image spectrums. The components extracted from the two channels are concatenated using a linear layer to train the entire model for exposing DeepFakes. Experimental results demonstrate that the proposed method could achieve satisfactory forensics performance. Besides, the experiments of cross-dataset evaluations prove it is also high in generalizability.

Currently, health management driven by intelligent means is a general demand of social systems. Although a number of researchers have paid attention to such areas, they have primarily focused on improving the performance of intelligent algorithms. Such intelligent algorithms are mostly based on the central computing mode, where all the user data are aggregated together in a central cloud to implement computing tasks. This poses a great threat to personal privacy due to exposure to the outside world. To address this challenge, this work uses a federated learning mechanism and proposes a privacy-preserving social computing framework for health management. User data are deposited in different user terminals to prevent exposure. A group of parameters are pretrained for each terminal in an iteration and are then transferred to the center cloud for updating. After multiple rounds of interactive training between the center cloud and the terminals, a recognition model finishes training for each terminal without direct access to data from other sources. Finally, this work also conducts experiments on a real-world dataset to assess the overall performance of the proposed approach.

So far, researchers have proposed many forensics tools to protect the authenticity and integrity of digital information. However, with the explosive development of machine learning, existing forensics tools may compromise against new attacks anytime. Hence, it is always necessary to investigate anti-forensics to expose the vulnerabilities of forensics tools. It is beneficial for forensics researchers to develop new tools as countermeasures. To date, one of the potential threats is the generative adversarial networks (GANs), which could be employed for fabricating or forging falsified data to attack forensics detectors. In this article, we investigate the anti-forensics performance of GANs by proposing a novel model, the ExS-GAN, which features an extra supervision system. After training, the proposed model could launch anti-forensics attacks on various manipulated images. Evaluated by experiments, the proposed method could achieve high anti-forensics performance while preserving satisfying image quality. We also justify the proposed extra supervision via an ablation study.

Falsified faces generated by DeepFake are severe threats to our community. Many smart systems in Industry 4.0, such as electronic payments and identity verification, rely on bioinformation authentication. These applications may compromise with forgeries generated by DeepFake. Notwithstanding many promising results on DeepFake forensics have been reported recently, we are now facing new security challenges brought by antiforensics attacks. With adversarial perturbations injected by antiforensics algorithms, falsified faces could masquerade themselves to disrupt forensics detectors as well as industrial applications. Therefore, to secure biometric data, in particular facial information, we propose a countermeasure against the attacks of DeepFake antiforensics. The proposed model features dual channels and multiple supervisors to capture biological attributes from manifold aspects. After training, the proposed method can purify antiforensics images by eliminating adversarial perturbations. With experimental evaluations, we show that purified faces are highly distinguishable from real ones. The proposed method is justified as a reliable defense tool for protecting facial bioinformation against antiforensics amid Industry 4.0.

The rapid development of the Internet of Vehicles has substantially boosted the prevalence of vehicular social networks (VSN). However, content security has gradually been a latent threat to the stable operation of VSN. The VSN is a time-varying environment and mixed with various real or fake contents, which brings great challenges to the sustainability of VSN. To establish a sustainable VSN, it is of practical value to possess a strong ability for fake content detection. Related works can be divided into the global semantics-based approaches and the local semantics-based approaches, though both with limitations. Leveraging these two different approaches, this paper proposes a fake content detection model based on the mixed graph neural networks (GNN) for sustainable VSN. It takes GNN as the bottom architecture and integrates both convolution neural networks and recurrent neural networks to capture two aspects of semantics. Such a mixed detection framework is expected to possess a better detection effect. A number of experiments were conducted on two social network datasets for evaluation, and the results indicated that the detection effect can be improved by about 5%-15% compared with baseline methods.

Nowadays, online spamming has already been a remarkable threat to contents security of Internet of Things. Due to constant technical progress, online spamming activities have been more and more concealed. This brings much fuzziness to spammer detection scenarios, yielding the issue of fuzzy detection of spammers. Although existing detection techniques for spammers utilized idea of deep learning, they still ignore to release power of label spaces. As real nature about a user may be usually fuzzy, but the label annotated for a user is always certain. To remedy such gap, this article proposes a label smoothing-based fuzzy detection method for spammers (Fuz-Spam). First of all, deep representation is still utilized to deeply fuse features, which acts as the foundation of neural computing. On this basis, generative adversarial learning is introduced to transform previous label spaces into distributed forms. In addition, two groups of experiments are carried out on two real-world datasets for evaluation. The results demonstrate that the Fuz-Spam improves identification efficiency about 10% to 20% than previous ones, and that the Fuz-Spam is endowed with proper stability.

Realizing autonomous vehicles is one of the ultimate dreams for humans. However, perceptual information collected by sensors in dynamic and complicated environments, in particular, vision information, may exhibit various types of degradation. This may lead to mispredictions of context followed by more severe consequences. Thus, it is necessary to improve degraded images before employing them for context prediction. To this end, we propose a generative adversarial network to restore images from common types of degradation. The proposed model features a novel architecture with an inverse and a reverse module to address additional attributes between image styles. With the supplementary information, the decoding for restoration can be more precise. In addition, we develop a loss function to stabilize the adversarial training with better training efficiency for the proposed model. Compared with several state-of-the-art methods, the proposed method can achieve better restoration performance with high efficiency. It is highly reliable for assisting in context prediction in autonomous vehicles.

Generating falsified faces by artificial intelligence, widely known as DeepFake, has attracted attention worldwide since 2017. Given the potential threat brought by this novel technique, forensics researchers dedicated themselves to detect the video forgery. Except for exposing falsified faces, there could be extended research directions for DeepFake such as anti-forensics. It can disclose the vulnerability of current DeepFake forensics methods. Besides, it could also enable DeepFake videos as tactical weapons if the falsified faces are more subtle to be detected. In this paper, we propose a GAN model to behave as an anti-forensics tool. It features a novel architecture with additional supervising modules for enhancing image visual quality. Besides, a loss function is designed to improve the efficiency of the proposed model. After experimental evaluations, we show that the DeepFake forensics detectors are susceptible to attacks launched by the proposed method. Besides, the proposed method can efficiently produce anti-forensics videos in satisfying visual quality without noticeable artifacts. Compared with the other anti-forensics approaches, this is tremendous progress achieved for DeepFake anti-forensics. The attack launched by our proposed method can be truly regarded as DeepFake anti-forensics as it can fool detecting algorithms and human eyes simultaneously.

In traditional visual cryptography schemes (VCSs), pixel expansion remains to be an unsolved challenge. To alleviate the impact of pixel expansion, several colored-black-and-white VCSs, called CBW-VCSs, were proposed in recent years. Although these methods could ease the effect of pixel expansion, the reconstructed image obtained by these methods may also suffer from low contrasts. To address this issue, we propose a contrast-enhanced (k, n) CBW-VCS based on random grids, named (k,n) RG-CBW-VCS, in this article. By applying color random grids, a binary secret image is encrypted into n color shares that have no pixel expansion. When any k 1 (k 1 > k ) color shares are collected together, the stacked results of them can be identified as the secret image; whereas the superposition of any k 2 ( k 2 < k ) color shares shows nothing. Through theoretical analysis and experimental results, we justify the effectiveness of the proposed (k, n) RG-CBW-VCS. Compared with related methods in feature, contrast, and pixel expansion, the results indicate that the proposed method generally achieves better performance.

Recent linguistic steganalysis methods model texts as sequences and use deep learning models to extract discriminative features for detecting the presence of secret information in texts. However, natural language has a complex syntactic structure and sequences have limited representation ability for text modeling. Moreover, previous methods tend to extract features from local continuous word sequences, which cannot effectively model global characteristics. In this paper, we present a linguistic steganalysis method with graph neural network. In the proposed method, texts are translated as directed graphs with the associated information, where nodes denote words and edges show associations between the words. By training a graph convolutional network for feature extraction, each node of a graph can collect contextual information to update self-expression, accordingly effectively solving the problem of poor representation of polysemous words. Meanwhile, we adopt a globally-shared matrix to record correlation strengths between words so that each text can effectively utilize the global information to obtain the better self-representation. Experimental results have shown that the proposed work achieves the state-of-the-art performance comparing with the previous works.

In recent years, with the improvements in machine learning, image forensics has made considerable progress in detecting editing manipulations. This progress also raises more questions in image forensics research, such as can the parameters applied in a manipulation be estimated. Many parameter estimation works have already been performed. However, most of these works are based on mathematical analyses. In this paper, we attempt to solve a particular parameter estimation problem from a different aspect. Specifically, a new convolutional neural network (CNN) model is proposed to estimate the resampling rate for resampled images regardless of whether the image is upscaled or downscaled. This model features an original layer to generate a measurable energy map toward the estimation of resampling rate (METEOR). The METEOR layer is demonstrated to be an outstanding method that can assist in enhancing the estimation performance of the CNN. Furthermore, the METEOR layer can also increase the robustness of the CNN against JPEG compression, which makes it extremely important in realistic application scenarios. Our work has verified that machine learning, particularly CNNs, with proper optimization can also be refined to adapt to parameter estimation in digital forensics with excellent performance and robustness.

Unsharp masking (USM) sharpening is a basic technique for image manipulation and editing. In recent years, the detection of USM sharpening has attracted attention from image forensics point of view. After USM sharpening, overshoot artifacts, which shape image texture, are generated along image edges. By utilizing the special characteristic of the texture modification caused by the USM sharpening, a novel method called edge perpendicular binary coding is proposed in this letter to detect USM sharpening. Extensive experiments have been conducted to show the superiority of the proposed method over the existing methods.