The rapid advancement of digital image processing has made image manipulation increasingly accessible, raising significant concerns about misinformation and visual forgery, particularly in critical domains such as journalism, forensics, and public security. To tackle this challenge, we propose PCD-Net, an end-to-end dual-branch network for image manipulation localization (IML). The architecture incorporates a dedicated noise branch to exploit distributional inconsistencies between tampered and authentic regions, thereby improving localization granularity. To efficiently adapt large pre-trained vision backbones to IML tasks without incurring high computational overhead, we introduce a tunable prompt module, enabling frozen backbones to extract task-relevant multi-view features while preserving their generalization ability. Additionally, we design a Feature Enhancement and Fusion Module (FEFM) that employs channel and spatial attention along with a bidirectional cross-attention mechanism to integrate complementary multi-modal, multi-scale features and suppress irrelevant information. The results demonstrate that, compared with existing approaches in the same category, PCD-Net achieves significantly higher localization accuracy across multiple datasets and exhibits superior robustness in complex manipulation scenarios.

With the increasing number of fake images on the Internet, the detection and localization of such images have become a topic worthy of attention. However, existing methods generally have the following problems: Single-type detection struggles to address the complexities of diverse real-world scenarios; Over-reliance on specific situations limits the practical effectiveness of statistical methods in Image Manipulation Localization; The backbone feature extraction network during training often misidentifies high-contrast regions as manipulated areas. In response to these problems, this paper introduces a novel approach named Progressive Multiscale Fusion Network for image manipulation localization. To begin with, an Edge Trace Block is designed to extract multiscale edge features and perform edge supervision so that PMF-Net can obtain global context information on edge parts, including trusted tampering edge clues. Subsequently, we propose an innovative approach named Attention Fusion Block that fuses the features of two different sources using an attention map, and then further extracts the tampering-related information with lightweight attention. Extensive experiments show that our method outperforms state-of-the-art works in both localization performance and robustness on several benchmark datasets.

With advancements in image processing and the proliferation of editing software, image splicing forgery has become increasingly facile to execute yet harder to detect, thereby impacting societal security. Effective detection and localization methods are urgently needed. Existing methods, while somewhat effective, often over-rely on semantic features, overlook shallow features, and struggle to adapt to varying tampered region sizes. To address these issues, we propose a two-stream image splicing forgery localization network, named DMU-Net. The network first introduces a noise stream as a supplementary feature alongside the RGB stream to provide a richer feature representation. Subsequently, we improve the Atrous Spatial Pyramid Pooling module by incorporating an attention mechanism that enables the model to obtain feature maps of different scales, effectively use context information, and enhance the ability to capture tampered regions of various sizes. Finally, we employ a dual attention mechanism to fuse features from both the encoder and decoder stages; this approach effectively leverages shallow features for fusing coarse-grained and fine-grained features, thus enhancing the model’s ability to capture features across different dimensions. Extensive experimental results show that the proposed method outperforms the state-of-the-art image splicing localization methods in terms of detection accuracy and robustness.

Image manipulation localization is a crucial task in multimedia forensics, with the aim of precisely detecting and locating the forged areas within images. Nevertheless, existing approaches frequently encounter issues such as incomplete detection of forged regions and ambiguous boundary responses when dealing with complex scenarios like blurred edges and minor tampering. To address these issues, we put forward a dual-stream progressive image manipulation localization framework based on cross-fusion to enhance edge perception and localization accuracy. This framework adopts a dual-stream architecture consisting of an RGB stream and an edge stream. The RGB stream captures semantic information, while the edge stream focuses on structural details. The two streams are gradually fused in a progressive decoder to achieve multi-stage fine-grained representations of tampered regions. Furthermore, we design a Cross-Stream Progressive Block Attention module (CSPBA), which encompasses a Cross-Stream Feature Fusion module (CSFF) module and a Progressive Block Attention (PBA) module. The CSFF realizes information guidance and complementarity of the two feature streams during the progressive learning stage, while the PBA models channel and spatial attention separately within local blocks. Experimental results on various standard datasets indicate that the proposed method surpasses existing state of the art methods in image manipulation localization.

Image tampering techniques can lead to distorted or misleading information, which in turn poses a threat in many areas, including social, legal and commercial. Numerous image tampering detection algorithms lose important low-level detail information when extracting deep features, reducing the accuracy and robustness of detection. In order to solve the problems of current methods, this paper proposes a new network called IFE-Net to detect three types of tampered images, namely copy-move, heterologous splicing and removal. Firstly, this paper constructs the noise stream using the attention mechanism CBAM to extract and optimize the noise features. The high-level features are extracted by the backbone network of RGB stream, and the FEASPP module is built for capturing and enhancing the features at different scales. In addition, in this paper, the initial features of RGB stream are additionally supervised so as to limit the detection area and reduce the false alarm. Finally, the final prediction results are obtained by fusing the noise features with the RGB features through the Dual Attention Mechanism (DAM) module. Extensive experimental results on multiple standard datasets show that IFE-Net can accurately locate the tampering region and effectively reduce false alarms, demonstrating superior performance.

With the extensive application of digital image technology, it has brought not only convenience but also substantial security risks. The proliferation of image editing tools has made image tampering much easier, and when maliciously used, it can pose serious threats to social stability. To improve the accuracy and robustness of image forgery detection, we propose a forgery detection network that integrates boundary attention and multi-scale collaborative supervision, building upon previous research. The proposed network first extracts global and local features of the image through a multi-branch structure to capture forgery traces at different levels and then introduces a Boundary Attention Guidance (BAG) mechanism to enhance sensitivity to the boundaries of tampered regions, effectively improving the identification of edge-based forgeries. Furthermore, a Multi-path Semantic Attention Fusion (M-SAF) mechanism is designed to strengthen the compatibility and semantic consistency between multi-source features. Finally, a multi-scale collaborative supervision strategy is employed, jointly optimizing feature responses at different scales, significantly enhancing the model's generalization ability and localization accuracy in complex tampering scenarios. Experimental results show that the proposed method outperforms existing mainstream forgery detection algorithms on multiple public datasets, particularly demonstrating stronger robustness while maintaining high localization accuracy.

The popularization of modern digital image technology has brought convenience to us, but it also poses many risks. The advancement of image editing software allows anyone to modify image content effortlessly. If these modified images are abused, they can severely impact societal safety and stability. To address these risks, we propose an end-to-end multi-scale collaborative enhancement image forgery localization network, termed MSMAE-Net. The method first employs a multi-branch feature extractor to initially capture both global and local information, with each branch optimized for different contextual information and features of the image. Next, to enhance the model’s ability to capture forged traces at various levels while maintaining the correlation between different spatial hierarchies, a boundary information aggregation module is designed. By constructing multiple branches with different receptive fields and collaborative learning with each other, a nested collaborative enhancement branch is designed to make the backbone network pay more attention to key features, so as to obtain better feature representation capability. Furthermore, to further fuse different semantic information, a novel strongly compatible semantic attention fusion module is proposed in this paper. Finally, an attention enhancement module is introduced in the localization of forgery regions to adaptively concentrate on key forged areas in the image and effectively capture the relationships between different pixels. In the experiments, we demonstrate that MSMAE-Net exhibits significant advantages in both localization accuracy and robustness in complex forgery scenarios when compared to other SOTA image forgery detection methods.

With the rapid development of image processing technology, it has become increasingly easy to manipulate images, which poses a threat to the stability and security of people’s lives. Recent methods have proposed the fusion of RGB and noise features to uncover tampering traces. However, these approaches overlook the characteristics of features at different levels, leading to insufficient feature fusion. To address this problem, this paper proposes a double-stream multilevel feature fusion network (DMFF-Net). Unlike the traditional feature fusion approach, DMFF-Net adopts a graded feature fusion strategy. It classifies features into primary, intermediate, and advanced levels and introduces the Primary Feature Fusion Module (PFFM) and the Advanced Feature Fusion Module (AFFM) to achieve superior fusion results. Additionally, a multisupervision strategy is employed to decode the fused features into level-specific masks, including boundary, regular, and refined masks. The DMFF-Net is validated on publicly available datasets, including CASIA, Columbia, COVERAGE, and NIST16, as well as a real-life manipulated image dataset, IMD20, and achieves AUCs of 84.7%, 99.6%, 86.6%, 87.4% and 82.8%, respectively. Extensive experiments show that our DMFF-Net outperforms state-of-the-art methods in terms of image manipulation localization accuracy and exhibits improved robustness.

Image splicing forgery, that is, copying some parts of an image into another image, is one of the frequently used tampering methods in image forgery. As a research hotspot in recent years, deep learning has been used in image forgery detection. However, current deep learning methods have two drawbacks: first, they are too simple in feature fusion; second, they rely only on a single cross-entropy loss as the loss function, leading to models prone to overfitting. To address these issues, a image splicing forgery localization method based on multi-scale supervised U-shaped network, named MSU-Net, is proposed in this paper. First, a triple-stream feature extraction module is designed, which combines the noise view and edge information of the input image to extract semantic-related and semantic-agnostic features. Second, a feature hierarchical fusion mechanism is proposed that introduces a channel attention mechanism layer by layer to perceive multi-level manipulation trajectories, avoiding the loss of information in semantic-related and semantic-agnostic shallow features during the convolution process. Finally, a strategy for multi-scale supervision is developed, a boundary artifact localization module is designed to compute the edge loss, and a contrastive learning module is introduced to compute the contrastive loss. Through extensive experiments on several public datasets, MSU-Net demonstrates high accuracy in localizing tampered regions and outperforms state-of-the-art methods. Additional attack experiments show that MSU-Net exhibits good robustness against Gaussian blur, Gaussian noise, and JPEG compression attacks. Besides, MSU-Net is superior in terms of model complexity and localization speed.

Since facial forgery techniques have made remarkable progress, the area of forgery detection attracts a significant amount of attention due to security concerns. Existing methods attempt to utilize convolutional neural networks (CNNs) to mine discriminative clues for forgery detection. However, most of these coarse-grained and vanilla methods struggle to extract subtle and multiscale clues in forgery detection. To address such problems, we propose a well-designed deep learning framework, named SCA-Net, to exploit subtle, multiscale and multiview clues. Specifically, our framework consists of a skipped channel attention module (SCM), a constrained difference module (CDM) and an adaptive attention module (AAM). First, the skipped channel attention module is used as the backbone to extract sufficient different information, including low-level and high-level features. Then, the constrained difference module captures manipulation clues from the input image based on constrained characteristics. Finally, the adaptive attention module captures multiscale features represented by facial forgery. Moreover, we introduce a combined loss to address the learning difficulty of our framework. The experimental results demonstrate that the proposed model has great detection performance compared with other face forgery detection methods in most cases.

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

The pancake graph is an interconnection network that plays a vital role in designing parallel and distributed systems. Due to the unavoidable occurrence of edge faults in large-scale networks and the wide application of path and cycle structures, it is essential and practical to explore the embedding of Hamiltonian paths and cycles in faulty networks. However, existing fault models ignore practical distributions of faulty edges so that only linear edge faults can be tolerated. This paper introduces a powerful fault model named the partitioned fault model. Based on this model, we study the existence of Hamiltonian paths and cycles on pancake graphs with large-scale faulty edges for the first time. We show that the n-dimensional pancake graph P_n admits a Hamiltonian path between any two vertices, avoiding ∑ _i=4^n((i-4)((i-2)!-2) - 1)+1 partition-edge faults for 4 ≤ n ≤ 7 , and avoiding ∑ _i=8^n((i-1)!/2-1)+ 399 faulty partition-edges for n ≥ 8 . Moreover, we prove that P_n admits a Hamiltonian cycle, avoiding ∑ _i=4^n((i-4)((i-2)!-2) - 1)+2 faulty partition-edges for 4 ≤ n ≤ 7 , and avoiding ∑ _i=8^n((i-1)!/2-1)+ 400 partition-edge faults for n ≥ 8 . The comparison results show that our results are a large-scale enhancement of existing results.

Matrix factorization has always been an encouraging field, which attempts to extract discriminative features from high-dimensional data. However, it suffers from negative generalization ability and high computational complexity when handling large-scale data. In this paper, we propose a learnable deep matrix factorization via the projected gradient descent method, which learns multi-layer low-rank factors from scalable metric distances and flexible regularizers. Accordingly, solving a constrained matrix factorization problem is equivalently transformed into training a neural network with an appropriate activation function induced from the projection onto a feasible set. Distinct from other neural networks, the proposed method activates the connected weights not just the hidden layers. As a result, it is proved that the proposed method can learn several existing well-known matrix factorizations, including singular value decomposition, convex, nonnegative and semi-nonnegative matrix factorizations. Finally, comprehensive experiments demonstrate the superiority of the proposed method against other state-of-the-arts.

The use of image-splicing technologies had detrimental effects on the security of multimedia information. Hence, it is necessary to develop effective methods for detecting and locating such tampering. Previous studies have mainly focused on the supervisory role of the mask on the model. The mask edges contain rich complementary signals, which help to fully understand the image and are usually ignored. In this paper, we propose a new network named EAU-Net to detect and locat the splicing regions in the image. The proposed network consists of two parts: Edge-guided SegFormer and Sparse-connected U-Net (SCU). Firstly, the feature extraction module captures local detailed cues and global environment information, which are used to deduce the initial location of the affected regions by SegFormer. Secondly, a Sobel-based edge-guided module (EGM) is proposed to guide the network to explore the complementary relationship between splicing regions and their boundaries. Thirdly, in order to achieve more precise positioning results, SCU is used as postprocessing for removing false alarm pixels outside the focusing regions. In addition, we propose an adaptive loss weight adjustment algorithm to supervise the network training, through which the weights of the mask and the mask edge can be automatically adjusted. Extensive experimental results show that the proposed method outperforms the state-of-the-art splicing detection and localization methods in terms of detection accuracy and robustness.

short-paper Share on On Construction of Fault-Tolerant Virtual Backbones in Heterogeneous Wireless Sensor Networks Authors: Xiaoming Wu College of Computer and Data Science, Fuzhou University, China College of Computer and Data Science, Fuzhou University, China 0000-0003-1154-5607Search about this author , Yanhua Liu College of Computer and Data Science, Fuzhou University, China College of Computer and Data Science, Fuzhou University, China 0000-0002-6076-9968Search about this author , Lichao Su College of Computer and Data Science, Fuzhou University, China College of Computer and Data Science, Fuzhou University, China 0000-0003-2641-5901Search about this author , Xiao-Yan Li College of Computer and Data Science, Fuzhou University, China College of Computer and Data Science, Fuzhou University, China 0000-0001-6295-2072Search about this author Authors Info & Claims APNet '22: Proceedings of the 6th Asia-Pacific Workshop on NetworkingJuly 2022Pages 92–94https://doi.org/10.1145/3542637.3543704Published:07 November 2023Publication History 0citation0DownloadsMetricsTotal Citations0Total Downloads0Last 12 Months0Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Abstract We propose a novel algorithm for detecting the duplication of moving objects in video and locating forged motion sequences. First, the algorithm constructs an energy factor (EF) curve to identify the suspect frames of the video. Second, an adaptive-parameter-based Visual Background Extractor (ViBe) algorithm (APViBe) is employed for background modelling. Moreover, all motion sequences are identified by using an improved fast compressive tracking (FCT) algorithm based on an adaptive learning rate and measurement matrix (ALMFCT). Third, a similarity-analysis-based scheme (SAS) is designed to search for pairs of suspect motion sequences. Finally, the flip-invariant scale-invariant feature transform (FISIFT) algorithm is used to match the feature points of moving objects in the pairs of suspect motion sequences, based on which the forged motion sequences in the video are confirmed. Experimental results show that the proposed approach outperforms previous algorithms in computational efficiency, accuracy and robustness.

Interconnection networks play a critical role in the architecture of high-performance computing (HPC) systems. The Galaxyfly network has emerged as a flexible-radix low-diameter topology which is designed for HPC. Considering the importance of collective communication in HPC, in this paper, we present two different all-to-all routing algorithms for the Galaxyfly network. The first one complies with the rule of supernode-first, and it takes full advantage of the network resources in the routing process. As for the second one, we abide by the rule of router-first so that packets can be delivered to other routers within the same supernode as early as possible. The proposed all-to-all routing algorithms use breadth-first and recursive approaches for collecting and sending packets. To our knowledge, this is the first all-to-all routing work for Galaxyfly networks.