With the rapid development of online social networks and the inadequacies in content moderation mechanisms, the detection of fake news has emerged as a pressing concern for the public. Various methods have been proposed for fake news detection, including text-based approaches as well as a series of graph-based approaches. However, the deceptive nature of fake news renders text-based approaches less effective. Propagation tree-based methods focus on the propagation process of individual news, capturing pairwise relationships but lacking the capability to capture high-order complex relationships. Large heterogeneous graph-based approaches necessitate the incorporation of substantial additional information beyond news text and user data, while hypergraph-based approaches rely on predefined hypergraph structures. To tackle these issues, we propose a novel dynamic hypergraph-based multi-view fake news detection model (DHy-MFND) that learns news embeddings across three distinct views: text-level, propagation tree-level, and hypergraph-level. By employing hypergraph structures to model complex high-order relationships among multiple news pieces and introducing dynamic hypergraph structure learning, we optimize predefined hypergraph structures while learning news embeddings. Additionally, we introduce contrastive learning to capture authenticity-relevant embeddings across different views. Extensive experiments on two benchmark datasets demonstrate the effectiveness of our proposed DHy-MFND compared with a broad range of competing baselines.

Advanced Persistent Threats(APTs) are targeted, stealthy, and highly sophisticated cyberattacks posing serious risks to critical infrastructure and sensitive data. In recent years, researchers increasingly focus on constructing provenance graphs from system logs to represent information flows, aiming to detect APTs through such semantically rich structured data. Although provenance graph-based APT detection techniques have shown effectiveness, they still suffer from several limitations: First, most of these methods require real-world APT data and prior expert knowledge; Second, they generally focusing on fine-grained local information while neglecting global information, resulting in in-sufficient extraction of rich contextual information and thus high false positive rates; Third, their detection performance degrades against evasion strategies, indicating insufficient robustness.To address these problems, this paper proposes Advanced Persistent Threat Detection via Graph Contrastive Masked Autoencoder (APT-GCM), a self-supervised learning-based detection model. APT-GCM leverages a graph contrastive masked autoencoder to learn node representations from benign provenance graphs, transforming malicious nodes detection into an outlier detection problem. It integrates the advantages of masked graph autoencoder and graph contrastive learning for extracting both local and global graph information through a dual-branch structure, learning deep implicit features of provenance graph nodes. Additionally, a uniformity loss is introduced to optimize the embedding distribution and improve discriminability. To further improve robustness, a complementary view augmentation module is incorporated, which constructs a complementary view of the masked view and performs feature alignment of masked nodes, strengthening the model’s ability to extract stable semantic information from diverse perspectives and thus improving its robustness against evasion attacks. We evaluate APT-GCM on three sub-datasets from the widely used DARPA E3 dataset, and experimental results demonstrate that APT-GCM outperforms state-of-the-art detection methods.

The success of deep face recognition (FR) systems has raised serious privacy concerns due to their ability to enable unauthorized tracking of users in the digital world. Previous studies proposed introducing imperceptible adversarial noises into face images to deceive those face recognition models, thus achieving the goal of enhancing facial privacy protection. Nevertheless, they heavily rely on user-chosen references to guide the generation of adversarial noises, and cannot simultaneously construct natural and highly transferable adversarial face images in black-box scenarios. In light of this, we present a novel face privacy protection scheme with improved transferability while maintain high visual quality. We propose shaping the entire face space directly instead of exploiting one kind of facial characteristic like makeup information to integrate adversarial noises. To achieve this goal, we first exploit global adversarial latent search to traverse the latent space of the generative model, thereby creating natural adversarial face images with high transferability. We then introduce a key landmark regularization module to preserve the visual identity information. Finally, we investigate the impacts of various kinds of latent spaces and find that F latent space benefits the trade-off between visual naturalness and adversarial transferability. Extensive experiments over two datasets demonstrate that our approach significantly enhances attack transferability while maintaining high visual quality, outperforming state-of-the-art methods by an average 25% improvement in deep FR models and 10% improvement on commercial FR APIs.

Due to the rich relational information of graph-structured data, graph neural networks (GNNs) have been widely used for fraud detection tasks, where the suspiciousness of nodes is identified by aggregating information about the neighbors of different relations. To bypass such detection, fraudsters camouflage themselves by providing seemingly legitimate feedback (i.e., feature camouflage) or connecting many legitimate users (i.e., relation camouflage). Moreover, when the label distribution of nodes is severely skewed, GNN-based algorithms may have limitations. To counteract the effect of disguised fraudsters under imbalanced graphs on fraud detection, we propose a cascaded GNN fraud detector with dual features (CGDF-GNN) in this paper. It tackles the impact of feature camouflage by applying a dual-feature parallel aggregation method and uses a cascaded neighbor aggregator to deal with the single-level learning problem arising from relational camouflage. Experiments on graph-based fraud detection tasks on two real-world datasets demonstrate the effectiveness of our model compared to current state-of-the-art baselines.

Accurate cell classification is the groundwork for downstream analysis of single-cell sequencing data, yet how to identify true marker genes for different cell types still remains a big challenge. Here, we report COSine similarity-based marker Gene identification (COSG) as a cosine similarity-based method for more accurate and scalable marker gene identification. COSG is applicable to single-cell RNA sequencing data, single-cell ATAC sequencing data and spatially resolved transcriptome data. COSG is fast and scalable for ultra-large datasets of million-scale cells. Application on both simulated and real experimental datasets showed that the marker genes or genomic regions identified by COSG have greater cell-type specificity, demonstrating the superior performance of COSG in terms of both accuracy and efficiency as compared with other available methods.

Federated learning (FL) is a newly emerging distributed learning framework that is communication-efficient with user privacy guarantee. Wireless end-user devices can collaboratively train a global model while keeping their local training data private. Nevertheless, recent studies show that FL is highly susceptible to attacks from malicious users since the server cannot directly access and audit the user's local training data. In this work, we identify a new kind of attack surface that is much easier to be carried out while remaining a high attack success rate. By exploiting the inherent flaw of the weight assignment strategy in the standard federated learning process, our attack can bypass the existing defense methods and damage the performance of the global model effectively. We then propose a new density-based detection strategy to defend against such attack by modeling the problem as anomaly detection to effectively detect anomalous updates. Experimental results on two typical datasets, MNIST and CIFAR-10, show that our attack can significantly affect the convergence of the aggregated model and reduce the accuracy of the global model. This holds true even the state-of-the-art defense strategies are deployed, while our newly proposed defense can effectively mitigate such attack.

In this paper, a novel concept factorization (CF) method, called CF with adaptive neighbors (CFANs), is proposed. The idea of CFAN is to integrate an ANs regularization constraint into the CF decomposition. The goal of CFAN is to extract the representation space that maintains geometrical neighborhood structure of the data. Similar to the existing graph-regularized CF, CFAN builds a neighbor graph weights matrix. The key difference is that the CFAN performs dimensionality reduction and finds the neighbor graph weights matrix simultaneously. An efficient algorithm is also derived to solve the proposed problem. We apply the proposed method to the problem of document clustering on the 20 Newsgroups, Reuters-21578, and TDT2 document data sets. Our experiments demonstrate the effectiveness of the method.

In this paper, we propose a novel graph-based semisupervised learning framework, called joint sparse representation and embedding propagation learning (JSREPL). The idea of JSREPL is to join EPL with sparse representation to perform label propagation. Like most of graph-based semisupervised propagation learning algorithms, JSREPL also constructs weights graph matrix from given data. Different from classical approaches which build weights graph matrix and estimate the labels of unlabeled data in sequence, JSREPL simultaneously builds weights graph matrix and estimates the labels of unlabeled data. We also propose an efficient algorithm to solve the proposed problem. The proposed method is applied to the problem of semisupervised image clustering using the ORL, Yale, PIE, and YaleB data sets. Our experiments demonstrate the effectiveness of our proposed algorithm.

This letter proposes a bottom-up saliency model to predict eye fixation locations. Unlike traditional models that measure saliency by computing local or global distinctness, the proposed model considers saliency as the prediction error, because we believe that image patches or pixels with higher prediction error are more salient than others. The prediction error consists of both mispredicted error and unpredicted error. We propose a new algorithm called sparse residual to compute the mispredicted error. We then adopt outlier detection to compute the unpredicted error. Finally, we obtain the saliency map from merging the two results together via a guided filter. Extensive experiments on three benchmark databases show that our model is superior to 12 state-of-the-art models.

In this paper, a novel label propagation (LP) method is presented, called the manifold adaptive label propagation (MALP) method, which is to extend original LP by integrating sparse representation constraint into regularization framework of LP method. Similar to most LP, first of all, MALP also finds graph edges from given data and gives weights to the graph edges. Our goal is to find graph weights matrix adaptively. The key advantage of our approach is that MALP simultaneously finds graph weights matrix and predicts the label of unlabeled data. This paper also derives efficient algorithm to solve the proposed problem. Extensions of our MALP in kernel space and robust version are presented. The proposed method has been applied to the problem of semi-supervised face clustering using the well-known ORL, Yale, extended YaleB, and PIE datasets. Our experimental evaluations show the effectiveness of our method.

In this paper, a novel projective nonnegative matrix factorization (PNMF) method for enhancing the clustering performance is presented, called automated graph regularized projective nonnegative matrix factorization (AGPNMF). The idea of AGPNMF is to extend the original PNMF by incorporating the automated graph regularized constraint into the PNMF decomposition. The key advantage of this approach is that AGPNMF simultaneously finds graph weights matrix and dimensionality reduction of data. AGPNMF seeks to extract the data representation space that preserves the local geometry structure. This character makes AGPNMF more intuitive and more powerful than the original method for clustering tasks. The kernel trick is used to extend AGPNMF model related to the input space by some nonlinear map. The proposed method has been applied to the problem of document clustering using the well-known Reuters-21578, TDT2, and SECTOR data sets. Our experimental evaluations show that the proposed method enhances the performance of PNMF for document clustering.

Product design is a complicated and creative process. Even for the up-to-date commercial 3D CAD tools, it is very difficult to achieve automation of the entire design process. In the article, a semantic norm model (SNM) is presented to support the top-down process in conceptual design, which is an important phase in product design and has a decisive influence on the cost of the product design. The SNM system can define virtual components in early design stage with semantics and instantiate those components in detailed design, and it bridges the gaps between conceptual design and detailed design. The SNM system is also managed by 3D constraints system to support the variational design of the product. A combined algebraic together with numerical method was used to solve SNM constraints incrementally. Based on the SNM system, an adaptive conceptual design environment is developed and the top-down oriented product design process is demonstrated.