Multi-view clustering of remote sensing data plays a vital role in Earth observation analysis. Recently, deep graph clustering methods based on contrastive learning have significantly improved feature representation capabilities. However, most existing approaches treat all views equally, neglecting the inherent uniqueness and heterogeneity across views, which often results in two major issues: 1) discriminative features from clustering-friendly views are underexplored; and 2) redundant or noisy information from less informative views can degrade the shared representation. To address these challenges, we propose a novel multi-view graph clustering framework termed CF-MVGC for remote sensing data, which dynamically preserves discriminative features and suppresses redundancy by assessing view affinity. Specifically, we employ a dual-stage representation learning strategy to extract both view-specific discriminative features and cross-view consistent representations. To further exploit and adaptively integrate complementary information across views, we design a progressive feature filtering model that dynamically evaluates view affinity using two novel metrics, i.e., view fidelity index (VFI) and view criticality index (VCI). Based on these assessments, the module adaptively modulates feature update and reset signals, reinforcing informative views while suppressing noisy or redundant ones. Views with high affinity receive strengthened update signals to retain valuable features, while those with low affinity are subjected to enhanced reset operations to eliminate noise and redundancy. The resulting high-quality, discriminative representations lead to improved clustering performance, establishing a positive feedback loop. Experimental results on four benchmark datasets demonstrate the effectiveness and superiority of CF-MVGC against its competitors.

In the federated clustering task, structural heterogeneity across clients inevitably impedes effective multi-source information sharing. To solve this issue, Personalized Federated Learning (PFL) has emerged as a potentially effective solution for image and text clustering. Unlike Euclidean data, graph-structured data exhibits diverse and fragile local patterns, which widely exist in real-world scenarios. Multi-graph data analysis in the federated learning setting is challenging and important, yet remains underexplored. This motivates us to propose a novel PERsonalized Federated graph-lEvel Clustering neTwork (PERFECT), which generates a specialized aggregation strategy for each client by uploading key model parameters and representative samples without sharing private information. Specifically, for each client, we first reconstruct privacy-preserving representative samples in a min-max optimization manner and then upload these samples to the server for subsequent personalized parameter aggregation. On the server, we first extract graph-level embeddings from the uploaded data, and then estimate affinities among multiple learned embeddings to formulate a personalized aggregation strategy for each client. Subsequently, to help each local model better identify the cluster boundaries, we utilize clustering-wise gradient to update the key components in the personalized model parameters from the server. Extensive experimental results have demonstrated the effectiveness and superiority of PERFECT over its competitors.

Node-level federated graph clustering allows multiple unlabeled subgraph holders to collaboratively train on node-level tasks without sharing private information. Existing methods usually assume that the node attributes are complete and have achieved promising progress. However, in the Federated Graph Learning (FGL) scenarios, this assumption is overly strict due to failures in data collection devices. Consequently, most existing FGL frameworks struggle to extract useful features from attribute-incomplete graphs for clustering, yet the issue remains underexplored. To bridge this gap, we propose a causally-aware attribute completion for Incomplete Federated Graph Clustering (IFedGC), which constructs a reliable global causal structure that incorporates clustering-friendly information to guide attribute completion for each subgraph. Specifically, in the attribute completion step, we first construct the causal structure to extract the causal relationships between initialized features, and then upload them to the server. Subsequently, we integrate multiple uploaded causal structures into a global causal one to achieve cross-client attribute completion. Moreover, to support reliable clustering, we first collect the high-confidence cluster centroids from each subgraph using a Graph Neural Network (GNN) model and subsequently aggregate these centroids on the server. The above two steps are seamlessly integrated into a unified FGL framework to obtain a clustering-oriented causal structure, which is sent back to the client to promote high-quality attribute completion for better clustering. Extensive results on five benchmark datasets demonstrate the effectiveness and superiority of IFedGC against its competitors.

Personalized Federated Learning (PFL), which aims to customize models for each client while preserving data privacy, has become an important research topic in addressing the challenges of data heterogeneity. Existing studies usually enhance the localization of global parameters by injecting local information into the globally shared model. However, these methods focus excessively on the personalized characteristics of individual clients and fail to fully exploit distinctive information across clients, limiting the quality of local models to represent unseen samples well. To address this issue, we propose a novel personalized Federated Privacy-preserving Knowledge Dynamic Alignment (FedPKDA) framework, which ensures data privacy during both the collection of client-side key information and its incorporation into federated model training. Specifically, to ensure data privacy during the cross-client information collection phase, we first conduct feature clipping and add Laplacian noise to the local prototypes extracted from each client. Further, we compute the centroid of the uploaded local prototypes in a latent space and leverage Mahalanobis distance to guide the generation of global prototypes, thereby preserving the semantic contributions from participating clients. Moreover, to boost the personalization of the local model, we dynamically align representations learned by the shared model with both a set of local prototypes and privacy-preserving global prototypes, facilitating effective cross-client knowledge sharing under heterogeneous settings while preserving client-specific characteristics. Extensive experiments on benchmark datasets have verified the superiority of FedPKDA against its competitors.

Federated learning (FL) addresses privacy and data-silo issues in the training of large language models (LLMs).Most prior work focuses on improving the efficiency of federated learning for LLMs (FedLLM).However, security in open federated environments, particularly defenses against malicious clients, remains underexplored.To investigate the security of FedLLM, we conduct a preliminary study to analyze potential attack surfaces and defensive characteristics from the perspective of LoRA updates.We find two key properties of FedLLM: 1) LLMs are vulnerable to attacks from malicious clients in FL, and 2) LoRA updates exhibit distinct behavioral patterns that can be effectively distinguished by lightweight classifiers.Based on these properties, we propose Safe-FedLLM, a probebased defense framework for FedLLM, which constructs defenses across three levels: Step-Level, Client-Level, and Shadow-Level.The core concept of Safe-FedLLM is to perform probe-based discrimination on each client's local LoRA updates, treating them as highdimensional behavioral features and using a lightweight classifier to determine whether they are malicious.Extensive experiments demonstrate that Safe-FedLLM effectively improves FedLLM's robustness against malicious clients while maintaining competitive performance on benign data.Notably, our method effectively suppresses the impact of malicious data without significantly affecting training speed, and remains effective even under high malicious client ratios.

In practical scenarios, network intrusion detection entails analyzing network traffic and issuing timely alerts to protect against potential malicious activities. However, existing main-stream approaches face inherent limitations in feature extraction. Methods based on convolutional neural network filters primarily capture local patterns, focusing on fine grained details within individual data streams, while approaches leveraging attention mechanisms emphasize global representations, modeling overall traffic distributions. Yet these methods often rely on single level feature representations that are either overly localized or excessively globalized, limiting their ability to holistically characterize complex network traffic patterns. To overcome these challenges, we propose a novel intrusion detection framework called MFNID for network situation awareness, where MFNID integrates a dual contrastive learning paradigm within a unified architecture to jointly extract both local and global feature representations from raw traffic data, thereby enhancing the discriminative power of learned representations for edge classification. Concretely, at the local level, MFNID employs a fine grained dual perspective semantic contrastive learning strategy that compares multiple views of the same node, effectively capturing local semantics and node interactions. At the global level, a topology-aware subgraph level contrastive learning approach models similarities and discrepancies across subgraphs, enabling the extraction of highly abstract semantic information from traffic patterns. For edge level intrusion detection, edge representations are derived by combining the embeddings of incident nodes. Extensive experiments on four benchmark datasets demonstrate that MFNID consistently outperforms state of the art methods in edge classification.

Mobile crowd sensing (MCS), as an innovative data acquisition model in the Internet of Things (IoT), employs an incentive mechanism based on users’ reputation evaluation, which is a mainstream reward allocation method. However, in the existing incentive mechanisms based on reputation evaluation, unidirectional incentive strategies and nonadaptive reputation models result in unequal reward allocation. To tackle this issue, we propose an effective interactive incentive mechanism based on adaptive reputation evaluation. Specifically, we generate user status thresholds to classify, rate, and weight user behaviors, based on the average quality thresholds of tasks released or data submitted by different users in each interaction round. Meanwhile, we achieve multiparty consensus by incorporating the obtained user reputation values and combining them with the cumulative reputation values from multiple rounds to obtain adaptive reputation evaluation results. Moreover, we design an interactive incentive strategy that measures users’ incentive values based on their reputation evaluation results in each round, mutually punishing malicious behaviors from both the publisher’s and the worker’s perspectives. Extensive experiments have demonstrated that our method consistently outperforms existing advanced incentive mechanisms.

In the era of the Internet of Things (IoT) and data sharing, users frequently upload their personal information to enterprise databases to enjoy enhanced service experiences provided by various online services. However, the widespread presence of system vulnerabilities, remote network intrusions, and insider threats significantly increases the exposure of private enterprise data on the internet. If such data is stolen or leaked by attackers, it can result in severe asset losses and business operation disruptions. To address these challenges, this paper proposes a novel threat detection framework, TabITD. This framework integrates Intrusion Detection Systems (IDS) with User and Entity Behavior Analytics (UEBA) strategies to form a collaborative detection system that bridges the gaps in existing systems’ capabilities. It effectively addresses the blurred boundaries between external and insider threats caused by the diversification of attack methods, thereby enhancing the model’s learning ability and overall detection performance. Moreover, the proposed method leverages the TabNet architecture, which employs a sparse attention feature selection mechanism that allows TabNet to select the most relevant features at each decision step, thereby improving the detection of rare-class attacks. We evaluated our proposed solution on two different datasets, achieving average accuracies of 96.71% and 97.25%, respectively. The results demonstrate that this approach can effectively detect malicious behaviors such as masquerade attacks and external threats, significantly enhancing network security defenses and the efficiency of network attack detection.

Graph representation is an important part of graph clustering. Recently, contrastive learning, which maximizes the mutual information between augmented graph views that share the same semantics, has become a popular and powerful paradigm for graph representation. However, in the process of patch contrasting, existing literature tends to learn all features into similar variables, i.e., representation collapse, leading to less discriminative graph representations. To tackle this problem, we propose a novel self-supervised learning method called dual contrastive learning network (DCLN), which aims to reduce the redundant information of learned latent variables in a dual manner. Specifically, the dual curriculum contrastive module (DCCM) is proposed, which approximates the node similarity matrix and feature similarity matrix to a high-order adjacency matrix and an identity matrix, respectively. By doing this, the informative information in high-order neighbors could be well collected and preserved while the irrelevant redundant features among representations could be eliminated, hence improving the discriminative capacity of the graph representation. Moreover, to alleviate the problem of sample imbalance during the contrastive process, we design a curriculum learning strategy, which enables the network to simultaneously learn reliable information from two levels. Extensive experiments on six benchmark datasets have demonstrated the effectiveness and superiority of the proposed algorithm compared with state-of-the-art methods.

Semantic segmentation, which aims to accurately identify each pixel, is a meaningful and challenging task. Recently, we witness a strong tendency to improve model efficiency in low-computing applications. However, most real-time methods ignore hierarchical features and context information to improve efficiency, leading to a decrease in the accuracy of semantic segmentation. To this end, we propose a novel system named hierarchical semantic-aware network (HSNet) to refine multilevel context information. HSNet mainly has the following two core modules: 1) hierarchical feature refinement module (HFRM) and 2) cross-scale pyramid fusion module (CPFM). By aggregating hierarchical feature maps, the proposed HFRM learns multilevel feature representation to recover spatial details. Afterward, the dual attention mechanism is developed to refine features from both channel and spatial levels, thereby alleviating the multilevel semantic gap. Meanwhile, the CPFM, which fuses local and global context information in a cross-scale manner, is proposed to enrich semantic information to improve accuracy. Furthermore, HSNet is carefully designed to improve the efficiency of the model by reusing shallow features and reducing channel capacity. Extensive experiments show that our method is effective and superior in segmentation accuracy and inference speed compared with state-of-the-art methods.

Semantic segmentation technique plays a crucial role in Internet of Things applications, such as industrial robotics and self-driving. Recently deep learning approaches have boosted semantic segmentation accuracy greatly. However, their comprehensive performance in terms of accuracy and efficiency is still far from satisfactory. We observe that (1) accuracy-oriented methods rely on numerous convolution layers and sophisticated architectures, which result in heavy computational complexity and usually take a long time for inference; (2) efficiency-oriented methods fail to capture the multiscale context information for discriminative representations during the feature fusion process, thus leading to suboptimal performance. Previous semantic segmentation approaches fail to address these two challenges simultaneously. To tackle the dilemma of precise segmentation and efficient inference, we propose a novel lightweight Multiscale Information Fusion Network (MIFNet). Specifically, the proposed MIFNet mainly consists of two core components, that is, Pyramid Refinement Connection Module (PRCM) and Lightweight Information Fusion Module (LIFM). The PRCM exploits skip learning to establish dependency between different stages. Meanwhile, the pyramid attention mechanism (PAM) in PRCM, which adjusts the weight of hybrid pyramid attention vector to refine spatial features of low-level, is developed to alleviate the semantic gap. Moreover, the LIFM is designed to detect objects at multiple scales from the global-local perspective. In LIFM, the proposed multiscale dense concatenation (MDC) adopts various dilated convolution to extract multiscale local context information. Extensive experimental results on benchmarks data sets demonstrate the significantly better performance of the proposed MIFNet compared with most existing state-of-the-art methods.

This erratum replaces the corresponding author Liang Tiancai with Ai Shan. In the article cited above, the authors wish to change the corresponding author from Liang Tiancai to Ai Shan as shown below.1 Shan Ai School of Computer Science and Cyberspace Security, Hainan University, Hainan, China Email address: [email protected] ORCID ID: 0000-0002-1784-0220

When making regression predictions, the traditional random forest (RF) algorithm can only make predictions within the training set, which can easily lead to overfitting when modeling data have some specific noise. To solve the problem of over-fitting, an improved RF method is proposed in this paper for wind pressure prediction. With the aim to verify the prediction performance of the improved RF algorithm, this paper predicts the wind pressure coefficients of a high-rise building model without wind pressure measurement points. The results show that the improved RF can achieve good results in predicting the mean and fluctuating wind pressure coefficients of high-rise buildings, and its relative error for each measurement point is basically controlled at 5%, which is acceptable in engineering terms. Further applications show that this improved RF can be used for wind pressure distribution prediction in other large-span building type wind tunnel tests.

Correlation Degree Optimization Driven Random Forest for Detecting DDoS Attacks in Cloud Computing" [1], there was an error in the expression below formula (1) in Section 3.2, where theta "" symbol should be replaced with alpha "".Therefore the expression "() = () + (1 -)(), (0 < < 1)" should be corrected to be "() = () + (1 -)(), (0 < < 1)".

Distributed Denial-of-Service (DDoS) is one of the most destructive network attacks. In Socially Aware Networking (SAN), there are many problems in current detection methods, such as low flexibility in detecting different attacks, high false-negative and false-positive rates. In this paper, we propose a DDoS detection method for SAN based on fusion feature series forecasting. Specifically, we define a multi-protocol-fusion feature (MPFF) to characterize normal network flows. Moreover, we utilize the time-series Autoregressive Integrated Moving Average Model (ARIMA) to formally describe the MPFF sequence, which is subsequently used in network flow forecasting and error calculation. Finally, we present the ARIMA detection model with error correction based on MPFF time series to identify DDoS in SAN. The experimental results show that the proposed method can effectively distinguish attacking flows from normal ones. Compared with previous DDoS detection methods for SAN, the proposed method can achieve better performance of detecting DDoS in terms of detection rate, false-positive rate and time delay.

Distributed denial-of-service (DDoS) has caused major damage to cloud computing, and the false- and missing-alarm rates of existing DDoS attack-detection methods are relatively high in cloud environment. In this paper, we propose a DDoS attack-detection method with enhanced random forest (RF) optimized by genetic algorithm based on flow correlation degree (FCD) feature. We define the FCD feature according to the asymmetric and semidirectivity interaction characteristics and use the two-tuples FCD feature consisting of packet-statistical degree (PSD) and semidirectivity interaction abnormality (SDIA) to describe the features of attack flow and normal flow. Then we use a genetic algorithm based on the FCD feature sequences to optimize two key parameters of the decision tree in the RF: the maximum number of decision trees and the maximum depth of every single decision tree. We apply the trained RF model with optimized parameters to generate the classifier to be used for DDoS attack-detection. The experiment shows that the proposed method can effectively detect DDoS attacks in cloud environment with a higher accuracy rate and lower false- and missing-alarm rates compared to existing DDoS attack-detection methods.

Distributed denial of service (DDoS) attacks has caused huge economic losses to society. They have become one of the main threats to Internet security. Most of the current detection methods based on a single feature and fixed model parameters cannot effectively detect early DDoS attacks in cloud and big data environment. In this paper, an adaptive DDoS attack detection method (ADADM) based on multiple-kernel learning (MKL) is proposed. Based on the burstiness of DDoS attack flow, the distribution of addresses, and the interactivity of communication, we define five features to describe the network flow characteristic. Based on the ensemble learning framework, the weight of each dimension is adaptively adjusted by increasing the interclass mean with a gradient ascent and reducing the intraclass variance with a gradient descent, and the classifier is established to identify an early DDoS attack by training simple multiple-kernel learning (SMKL) models with two characteristics including interclass mean squared difference growth (M-SMKL) and intraclass variance descent (S-SMKL). The sliding window mechanism is used to coordinate the S-SMKL and M-SMKL to detect the early DDoS attack. The experimental results indicate that this method can detect DDoS attacks early and accurately.