Prompt tuning enables Vision-Language Models (VLMs) to efficiently adapt to new tasks through learnable prompt vectors. This naturally raises a question: do these prompts leak private information about their training data? While Membership Inference Attacks (MIAs) can quantify this risk, current methods rely on access to model outputs or internal gradients. This limitation prevents a clear assessment of a prompt’s standalone privacy leakage, particularly in deployment scenarios where such information is inaccessible. In this paper, we propose Prompt Intrinsic Privacy Risk Analyzer (PIPRA) to address this gap. As the first output-free MIA, PIPRA leverages open-source pre-trained VLMs to extract features from both prompts and samples within a shared cross-modal semantic space. By employing a contrastive learning-based feature projector to enhance these representations, PIPRA enables a subsequent discriminator to effectively perform membership inference. Extensive experiments across nine benchmark datasets and multiple VLMs show PIPRA achieves an average AUC of 87.58%, significantly outperforming traditional output-dependent methods (77.05%). These findings reveal that prompts pose a substantially greater privacy risk than previously recognized, highlighting the urgent need for prompt-level privacy protection.

Accurate jailbreak evaluation is critical for LLM red team testing and jailbreak research. Mainstream methods rely on binary classification (string matching, toxic text classifiers, and LLM-based methods), outputting only "yes/no" labels without quantifying harm severity. Emerged multi-dimensional frameworks (e.g., Security Violation, Relative Truthfulness and Informativeness) use unified evaluation standards across scenarios, leading to scenario-specific mismatches (e.g., "Relative Truthfulness" is irrelevant to "hate speech"), undermining evaluation accuracy. To address these, we propose SceneJailEval, with key contributions: (1) A pioneering scenario-adaptive multi-dimensional framework for jailbreak evaluation, overcoming the critical "one-size-fits-all" limitation of existing multi-dimensional methods, and boasting robust extensibility to seamlessly adapt to customized or emerging scenarios. (2) A novel 14-scenario dataset featuring rich jailbreak variants and regional cases, addressing the long-standing gap in high-quality, comprehensive benchmarks for scenario-adaptive evaluation. (3) SceneJailEval delivers state-of-the-art performance with an F1 score of 0.917 on our full-scenario dataset (+6% over SOTA) and 0.995 on JBB (+3% over SOTA), breaking through the accuracy bottleneck of existing evaluation methods in heterogeneous scenarios and solidifying its superiority.

Online social networks (OSNs) have become the most popular platforms for information creation and sharing, actively encouraging users to showcase personal data such as profiles, opinions, and activities. The paradox of sharing and privacy issues is a big trouble for users. Most privacy protection services provided for users, such as access control, need to be manually configured to follow the privacy-aware user intents. It causes a significant cognitive burden for users, due to the dynamic changes in user relationships and the existence of many malicious users in the network. An adaptive privacy-aware sharing strategy management framework (APUS) based on multi-agent reinforcement learning (MARL) is proposed, which provides a service for users to adjust their sharing strategies dynamically in the context of potential malicious users. In APUS, each agent observes some users and has similar workloads, and MARL is adopted for learning cooperation. Besides, the optimal sharing strategies are dynamically derived to manage users' privacy settings for shared content while preventing the impact of malicious users. Experiments conducted on real-world datasets show that this work can effectively promote a win-win situation between the OSN platform and users.

The rapid spread of misinformation, amplified by digital media and AI-generated content, has made automated claim verification increasingly crucial. Traditional methods relying on expert-annotated evidence are labor-intensive and lack scalability, while recent automated systems still struggle with complex claims requiring nuanced reasoning. To address this, we propose CRAVE (Conflicting Reasoning Approach for explainable claim VErification), a novel framework that leverages conflicting rationales generated by large language models (LLMs) for explainable and accurate claim verification. CRAVE comprises three modules: (1) Ambiguity-Elimination Enhanced Evidence Retrieval, which refines entity-based searches to collect relevant evidence from sources like Wikipedia; (2) Conflicting Perspective Reasoning and Preliminary Judgment, where LLMs reason across four dimensions—direct evidence, semantic relationships, linguistic cues, and logical inference—to produce preliminary judgments; (3) Small Language Model (SLM)-based Judge, which is fine-tuned to assess the confidence of conflicting rationales and deliver a final authenticity verdict. Experiments on two public claim verification datasets show that CRAVE significantly outperforms state-of-the-art baselines, with enhanced evidence retrieval and more interpretable predictions. Code is available at: https://github.com/8zym/CRAVE.

With the widespread application of temporal knowledge graph reasoning (TKGR) models, there is an increasing demand to reduce the memory consumption and enhance the reasoning efficiency. Knowledge distillation (KD) is a classical approach to achieve model compression and acceleration, which has been gradually introduced into the TKGR domain. Through KD, the expertise of a high-capability teacher TKGR model can be transferred to a lightweight student TKGR model. The effective transfer of reasoning knowledge primarily faces two major challenges. The first is how to extract high-quality and high-value knowledge from the teacher to the student to achieve better teaching outcomes. The second is how to encourage the teacher to improve the teaching pattern so that the knowledge is more easily assimilated by the student. Motivated by these challenges, this article firstly designs a soft-label evaluation mechanism to mitigate the problem of anomaly diffusion and knowledge transfer redundancy by measuring the confidence and entropy changes of soft labels, then proposes a mutual learning-empowered KD (MLEMKD) framework for compressing TKGR models. It refines the distribution of knowledge by analyzing the cognitive differences between teacher and student models on training samples, which enhances the acceptability of knowledge. Extensive experiments conducted on four benchmark datasets demonstrate that MLEMKD significantly outperforms existing KD methods.

Graph-based semi-supervised learning (GSSL) has long been a research focus. Traditional methods are generally shallow learners, based on the cluster assumption. Recently, graph convolutional networks (GCNs) have become the predominant techniques for their promising performance. However, a critical question remains largely unanswered: why do deep GCNs encounter the oversmoothing problem, while traditional shallow GSSL methods do not, despite both progressing through the graph in a similar iterative manner? In this article, we theoretically discuss the relationship between these two types of methods in a unified optimization framework. One of the most intriguing findings is that, unlike traditional ones, typical GCNs may not effectively incorporate both graph structure and label information at each layer. Motivated by this, we propose three simple but powerful graph convolution methods. The first, optimized simple graph convolution (OGC), is a supervised method, which guides the graph convolution process with labels. The others are two "no-learning" unsupervised methods: graph structure preserving graph convolution (GGC) and its multiscale version GGCM, both aiming to preserve the graph structure information during the convolution process. Finally, we conduct extensive experiments to show the effectiveness of our methods.

Legal Judgment Prediction (LJP) aims to automatically predict a law case’s judgment results based on the text description of its facts. In practice, the confusing law articles (or charges) problem frequently occurs, reflecting that the law cases applicable to similar articles (or charges) tend to be misjudged. Although some recent works based on prior knowledge solve this issue well, they ignore that confusion also occurs between law articles with a high posterior semantic similarity due to the data imbalance problem instead of only between the prior highly similar ones, which is this work’s further finding. This article proposes an end-to-end model named D-LADAN to solve the above challenges. On the one hand, D-LADAN constructs a graph among law articles based on their text definition and proposes a graph distillation operator (GDO) to distinguish the ones with a high prior semantic similarity. On the other hand, D-LADAN presents a novel momentum-updated memory mechanism to dynamically sense the posterior similarity between law articles (or charges) and a weighted GDO to adaptively capture the distinctions for revising the inductive bias caused by the data imbalance problem. We perform extensive experiments to demonstrate that D-LADAN significantly outperforms state-of-the-art methods in accuracy and robustness.

The user identity linkage that establishes correspondence between users across networks is a fundamental issue in various social network applications. Efforts have recently been devoted to introducing network embedding techniques that map the different network users into the common representation space, thereby inferring user correspondence based on the similarities of their representations. However, existing studies that separately train the network embedding and space alignment in two stages may lead to conflict between the objectives of the two stages. Besides, the similarities between unlabeled cross-network user pairs are difficult to define and largely impact the result. Moreover, many previous methods still need plenty of labeled aligned user pairs to ensure performance, which may not be available. To address the above problems, we propose to solve the weakly-supervised user identity linkage problem via JOintly learning to Represent and Align, i.e., the JORA model. The architecture of JORA adopts the inductive graph convolutional network (GCN) that learns representations for each network. The model is jointly optimized by the representation learning component and alignment learning component. The former one aims to preserve the similarities between intranetwork users. The latter one aligns the different spaces by a projection function and aims to preserve the similarities between cross-network users. A specific attention mechanism is proposed to learn self-adaptive similarities for unlabeled user pairs during alignment learning and it reduces the error propagation caused by predefined similarities. The joint optimization helps perceive network characteristics during alignment and reduces the number of labeled users required. Experiments conducted on real social networks show that the proposed model achieves significantly better performance than the state-of-the-art methods.

Aiming to extrapolate missing facts in the future timestamp, temporal knowledge graph (TKG) reasoning has significant practical value across various applications. Most existing methods mainly rely on direct historical interactions to extract the temporal features of entities and have achieved promising performance in some specific scenes. However, these methods are constrained when it comes to predicting emerging events that lack such direct historical interaction information. To address this limitation, we propose a novel approach called the Homogeneous Entity Context Enhanced Representation Network (HECERN). Homogeneous entities are defined as entities with similar behavior patterns. HECERN takes advantage of the complex interaction connections among the relations of homogeneous entities, which contain rich and relevant context information for accurate prediction of emerging events. Specifically, we generate corresponding entity context subgraph for each history subgraph and extract dependencies for homogeneous entities and neighboring entities based on these two subgraphs, respectively. In addition, we introduce an attention-guided fusion mechanism that dynamically integrates information from neighbor-level dependencies and homogeneous-level dependencies to effectively generate the final entity representation. The effectiveness of HECERN is demonstrated through comprehensive experiments on three publicly available event-based TKG datasets. The results clearly indicate that our proposed approach significantly outperforms state-of-the-art methods in accurately predicting future events. (The source code is available at https://anonymous.4open.science/r/HECERN-2C6B.)

Structured text with plentiful hierarchical structure information is an important part in real-world complex texts. Structured text classification is attracting more attention in natural language processing due to the increasing complexity of application scenarios. Most existing methods treat structured text from a local hierarchy perspective, focusing on the semantics dependency and the graph structure of the structured text independently. However, structured text has global hierarchical structures with sophisticated dependency when compared to unstructured text. According to the variety of structured texts, it is not appropriate to use the existing methods directly. The function of distinction information within semantics dependency and graph structure for structured text, referred to as meta-information, should be stated more precisely. In this article, we propose HGMETA, a novel meta-information embedding frame network for structured text classification, to obtain the fusion embedding of hierarchical semantics dependency and graph structure in a structured text, and to distill the meta-information from fusion characteristics. To integrate the global hierarchical features with fused structured text information, we design a hierarchical LDA module and a structured text embedding module. Specially, we employ a multi-hop message passing mechanism to explicitly incorporate complex dependency into a meta-graph. The meta-information is constructed from meta-graph via neighborhood-based propagation to distill redundant information. Furthermore, using an attention-based network, we investigate the complementarity of semantics dependency and graph structure based on global hierarchical characteristics and meta-information. Finally, the fusion embedding and the meta-information can be straightforwardly incorporated for structured text classification. Experiments conducted on three real-world datasets show the effectiveness of meta-information and demonstrate the superiority of our method.

Network Representation Learning (NRL), which aims to embed nodes into a latent, low-dimensional vector space while preserving some network properties, facilitates the network analysis tasks. The goal of most NRL methods is to make similar nodes represented similarly in the embedding space. Many methods adopt the skip-gram model to achieve such goal by maximizing the predictive probability among the context nodes for each center node. The context nodes are usually determined based on the concept of \textit{proximity} which is defined based on some explicit network features. However, these proximities may result in a loss of training samples and have limited discriminative power. We propose a general and unified generative adversarial learning framework to address the problems. The proposed framework can handle almost all kinds of networks in a unified way, including homogeneous plain networks, attribute augmented networks and heterogeneous networks. It can improve the performances of the most of the state-of-the-art skip-gram based NRL methods. Moreover, another unified and general NRL method is extended from the framework. It can learn the network representation independently. Extensive experiments on proximity preserving evaluation and two network analysis tasks, i.e., link prediction and node classifications, demonstrate the superiority and versatility of our framework.

Network embedding is to learn low-dimensional representations of nodes while preserving necessary information for network analysis tasks. Though representations preserving both structure and attribute features have achieved in many real-world applications, learning these representations for networks with attribute information is difficult due to the heterogeneity between structure and attribute information. Many existing methods have been proposed to preserve explicit proximities between nodes, with optimization limited to node pairs with large structure and attribute proximities, which may lead to overfitting. To address the above problems, we adopt an attribute augmented network to represent attribute and structure information in a unified framework. Specifically, we study the problem of attribute augmented network embedding that exploits the strength of generative adversarial nets (ANGANs) in capturing the latent distribution of data to learn robust and informative representations of nodes. The ANGAN method obtains the low-dimensional representations of nodes through adversarial learning between the generative and discriminative models. The generative model approximates the underlying connectivity and attributes distributions of nodes by using the distributions generated from the learned representations. It is implemented by utilizing the properties of the attribute augmented network to improve the traditional Skip-gram model. The discriminative model is designed as a binary classifier to distinguish the truly connected node pairs from the generated ones. The pre-training algorithm and the teacher forcing approach are adopted to improve training efficiency and stability. Empirical results show that ANGAN generally outperforms state-of-the-art methods in various real-world applications, which demonstrates the effectiveness and generality of our method.

Stance detection aims at identifying people's stand-point towards a given target. New targets are constantly appearing on social media, making previous annotated data unusable by stance detection models relying on classical supervised machine learning. Thus, cross-target stance detection which uses labeled data from source targets to learn a model that can be adapted to the destination new target, has become a prevailing research direction. However, previous methods rely on manually chosen similar source-destination target pairs and lack generalization to unseen targets with no explicit relation to known ones. To this end, we investigate the problem from a domain adaptation perspective and further propose a novel Unified Target-aware Domain Adaptation method (UTDA) that leverages knowledge transfer capability of transformer-based language model. The proposed method can effectively extract critical target-shared features for detecting stance by feature disentanglement and automatically learn to identify target relations. UTDA can easily be applied to a new unseen target since it does not rely on any pre-defined target pairs. Experimental results on two benchmark stance datasets demonstrate that our method achieves better performance than strong baselines.

Modern learnable collaborative filtering recommendation models generate user and item representations by deep learning methods (e.g. graph neural networks) for modeling user-item interactions. However, most of them may still have unsatisfied performances due to two issues. Firstly, some models assume that the representations of users or items are fixed when modeling interactions with different objects. However, a user may have different interests in different items, and an item may also have different attractions to different users. Thus the representations of users and items should depend on their contexts to some extent. Secondly, existing models learn representations for user and item by symmetrical dual methods which have identical or similar operations. Symmetrical methods may fail to sufficiently and reasonably extract the features of user and item as their interaction data have diverse semantic properties. To address the above issues, a novel model called Asymmetrical context-awaRe modulation for collaBorative filtering REcommendation (ARBRE) is proposed. It adopts simplified GNNs on collaborative graphs to capture homogeneous user preferences and item attributes, then designs two asymmetrical context-aware modulation models to learn dynamic user interests and item attractions, respectively. The learned representations from user domain and item domain are input pair-wisely into 4 Multi-Layer Perceptrons in different combinations to model user-item interactions. Experimental results on three real-world datasets demonstrate the superiority of ARBRE over various state-of-the-arts.

In recent years, social platforms have become the main venue for disseminating fake news. Since much fake news is deliberately fabricated by malicious users or generated by adversarial deep learning models, content-only approaches can not detect fake news effectively. Compared to texts, the propagation patterns of fake news are much harder to be forged. Recent work found that the “context” of news, the tree-structured graph representing the propagation relationship of news and Twitter posts, is vital for fake news detection. Some work utilize graph neural networks to learn the representation of news' context graphs, achieving stunning performance. However, these methods still suffer from two problems. Firstly, Twitters posts in the context of news are not equally important for fake news detection. However, most previous works treat them equally. Moreover, the context of news presents diverse structures such as “star-shaped” graphs, with many nodes interacting with a central node, or “line-shaped” graphs, with sparse connections among neighbors. With single-scale graph representation, previous work can not handle diverse structures well. We propose a novel diversity-aware context attention network to cope with these problems. A context attention pooling function is proposed to extract the critical information within the context. It utilizes an attention module to automatically assign a greater weight to those important posts and a smaller weight to helpless posts. Furthermore, jump knowledge, which concatenates the pooling result from multiple network layers, is adopted. It offers the model multi-scale receptive fields and better adapts to diverse structures. Extensive experiments are conducted under various dataset settings, which confirms the superiority of our approaches over state-of-the-art models.

The user alignment problem that establishes a correspondence between users across networks is a fundamental issue in various social network analyses and applications. Since symbolic representations of users suffer from sparsity and noise when computing their cross-network similarities, the state-of-the-art methods embed users into the low-dimensional representation space, where their features are preserved and establish user correspondence based on the similarities of their low-dimensional embeddings. Many embedding-based methods try to align latent spaces of two networks by learning a mapping function before computing similarities. However, most of them learn the mapping function largely based on the limited labeled aligned user pairs and ignore the distribution discrepancy of user representations from different networks, which may lead to the overfitting problem and affect the performance. To address the above problems, we propose a cycle-consistent adversarial mapping model to establish user correspondence across social networks. The model learns mapping functions across the latent representation spaces, and the representation distribution discrepancy is addressed through the adversarial training between the mapping functions and the discriminators as well as the cycle-consistency training. Besides, the proposed model utilizes both labeled and unlabeled users in the training process, which may alleviate the overfitting problem and reduce the number of labeled users required. Results of extensive experiments demonstrate the effectiveness of the proposed model on user alignment on real social networks.

Clustering is the basis of many complex network analysis and application tasks. Preserving the clustering properties in network representation space contributes to a better clustering performance. In this paper, an Attribute Network Embedding method based on Joint Clustering of representation and network (ANEJC) is proposed. Based on variational graph auto-encoder, ANEJC jointly reconstructs adjacency matrix and attribute matrix. In order to preserve the clustering property of the network, ANEJC clusters network structure and hidden layer representations of variational graph auto-encoder, simultaneously. Extensive experiments carried out on four synthetic datasets and three real-world datasets demonstrate a superior clustering performance of ANEJC over the state-of-art methods.

Despite its success in learning network node representations, network embedding is still relatively new for multiplex networks (MNs) with multiple types of edges. In such networks, the inter-layer anchor links are usually missing, which represent the alignment relations between nodes on different layers and are a crucial prerequisite for many cross-network applications like network alignment. For mining such anchor links between layers for MNs, multiplex network embedding (MNE) has become one of the most promising techniques. In this paper, we consider two problems for MNs: 1) edges can be missing to different extent, and data augmentation may mitigate this issue; 2) the known alignment anchor links between layers can be misleading since the behaviors of nodes on different layers are not always consistent, so the most informative ones should be emphasized compared with those misleading ones. However, most existing works neglect the two problems and simply 1) adopt one structural view for all the layers (e.g. random walk with the same window size) and 2) equally extract information from all the anchor links. We propose an end-to-end contrastive framework called cM2NE for MNE, utilizing multiple structural views for each layer and learning with several plug-in components for different scenarios. Through end-to-end optimization on three levels, the intra-view, inter-view, and inter-layer level, our framework achieves to select the fitted views for different layers and maximize the inter-layer mutual information by emphasizing those most informative anchor links. Extensive experimental results on real-world datasets for node classification and multi-network alignment show that our approach consistently outperforms peer methods.

Online social networks are indispensable platforms where people share personal data from their daily lives. However, social sharing raises many privacy issues. One of the most difficult, the “privacy paradox,” is that social-network users want to meet their social needs by enhancing interactions with their friends and are at the same time concerned about the risk of privacy leakage. This work aims to help social-network users weigh the benefits of social sharing and the costs of privacy leakage. A proposed criterion for privacy-risk measurement can quantify the probability of privacy leakage according to multi-person competitive behaviors. By analyzing the continuous competition between a user and some unwanted knowers, a general-sum stochastic game model related to the privacy paradox is constructed. The Markov decision process (MDP) and a role-mining method are introduced to facilitate the game analysis. The existence of a Nash equilibrium strategy is proved theoretically, and effective personal access-control policies are derived from this strategy as solved by a reinforcement learning algorithm. Experiments evaluate the constructed privacy stochastic game model and the new criterion for privacy-risk measurement. This work helps users develop effective personal policies in all cases to optimize their payoffs in the privacy paradox.

Community detection provides invaluable help for various network based services, such as marketing and product recommendation. A specific service usually requires a set of interested communities rather than all communities in the network. In this paper, we address the cases where some exemplar nodes are provided in advance and the set of interested communities is mined for some specific services. Providing sufficient and suitable priori exemplars is not an easy task in most cases. With inadequate priori knowledge, most of recent community detection methods may fail to capture the requirements of a service. We describe the service requirements' essence by a so-called interested attribute subspace with large importance weights on some focus attributes, and study the problem of detecting the set of interested communities based on the guidance of the most limited exemplar information, i.e., two exemplar nodes from any potential interested community. An Interested Subspace and Community Mining (ISCM) method is proposed. In ISCM, a priori knowledge extension technique is designed at first by utilizing the neighborhood of the two exemplar nodes to get more exemplar nodes. Then the interested subspace is inferred from the extension. Finally the set of interested communities are located and mined by the guidance of the interested subspace. Experiments on synthetic datasets demonstrate the effectiveness and efficiency of our method and applications on real-world datasets show its application values for network based services.

Legal Judgment Prediction (LJP) is the task of automatically predicting a law case's judgment results given a text describing its facts, which has excellent prospects in judicial assistance systems and convenient services for the public.In practice, confusing charges are frequent, because law cases applicable to similar law articles are easily misjudged.For addressing this issue, the existing method relies heavily on domain experts, which hinders its application in different law systems.In this paper, we present an end-to-end model, LADAN, to solve the task of LJP.To distinguish confusing charges, we propose a novel graph neural network to automatically learn subtle differences between confusing law articles and design a novel attention mechanism that fully exploits the learned differences to extract compelling discriminative features from fact descriptions attentively.Experiments conducted on realworld datasets demonstrate the superiority of our LADAN.

Network embedding is the process of learning low-dimensional representations for nodes in a network while preserving node features. Existing studies only leverage network structure information and emphasize the preservation of structural features. However, nodes in real-world networks often have a rich set of attributes providing extra semantic information. It has been demonstrated that both structural and attribute features are important for network analysis tasks. To preserve both features, we investigate the problem of integrating structure and attribute information to perform network embedding and propose a multimodal deep network embedding (MDNE) method. MDNE captures the non-linear network structures and the complex interactions among structures and attributes using a deep model consisting of multiple layers of non-linear functions. Since structures and attributes are two different types of information, a multimodal learning method is adopted to pre-process them and help the model to better capture the correlations between node structure and attribute information. We define the loss function employing structural and attribute proximities to preserve the respective features, and the representations are obtained by minimizing the loss function. Results of extensive experiments on four real-world data sets show that the proposed method performs significantly better than baselines on a variety of tasks, which demonstrates the effectiveness and generality of our method.

Abstract Road traffic prediction plays a vital role in real-time traffic management of an intelligent transportation system (ITS). Many prediction models achieve fine results. However, most ignore the intrinsic characteristics of traffic parameter data and do not consider the spatiotemporal effects of road sections, which can reflect the situation of all road traffic. Therefore, multi-section traffic prediction is still an open problem. In this paper, empirical mode decomposition (EMD) is employed to decompose the information of traffic parameters into many intrinsic mode function (IMF) components, which represent the original road traffic information in periodic and random sequences. Then, by considering the superiority of deep learning in multi-dimensional data processing, which can handle the spatiotemporal effects, a prediction model based on a convolutional neural network (CNN) is proposed to achieve the prediction of periodic and random sequences, whose results are combined to obtain the final prediction. The dataset from the Caltrans Performance Measurement System is used to validate the model. The proposed prediction model is compared to several well-known models, such as PCA-BP, Lasso-BP, and standard CNN. Experiments show that the proposed prediction model achieves higher accuracy.

We propose an attention-injective deformable convolutional network called ADCrowdNet for crowd understanding that can address the accuracy degradation problem of highly congested noisy scenes. ADCrowdNet contains two concatenated networks. An attention-aware network called Attention Map Generator (AMG) first detects crowd regions in images and computes the congestion degree of these regions. Based on detected crowd regions and congestion priors, a multi-scale deformable network called Density Map Estimator (DME) then generates high-quality density maps. With the attention-aware training scheme and multi-scale deformable convolutional scheme, the proposed ADCrowdNet achieves the capability of being more effective to capture the crowd features and more resistant to various noises. We have evaluated our method on four popular crowd counting datasets (ShanghaiTech, UCF_CC_50, WorldEXPO'10, and UCSD) and an extra vehicle counting dataset TRANCOS, and our approach beats existing state-of-the-art approaches on all of these datasets.

Most of overlapping community detection algorithms cannot be applied to networks with highly overlapping community such as online social networks where individuals belong to many communities. One important reason is that many algorithms detect communities based on the explicit borders where nodes have more connections inside the communities, however, when the vertices' membership number gets large, the explicit borders between communities will fade away. To overcome this disadvantage, a new algorithm named MCNLPA is proposed by expanding the traditional Label Propagation Algorithm (LPA) based on the Maximal Clique Network for highly overlapping community detection. By finding all maximal cliques in networks and defining reasonable edges between them, the maximal clique network is established. Then the updated rule of classic LPA is modified to apply to the maximal network. Experiments show that MCNLPA has a relatively good performance in highly overlapping community detection and overlapping nodes identification.

Community detection is an important technique to understand the structure of complex social networks. Many approaches have been devised to extract community structures in recent years. In this paper we propose a novel neighborhood vector propagation algorithm (NVPA) to detect communities in a social network which has greater accuracy than algorithms in the literature. In our approach, a neighborhood vector is proposed to store the neighborhood information, and a vector propagation algorithm is designed to disseminate neighborhood information to other nodes. After neighborhood propagation, hierarchical clustering is used to find the community structure based on similarity measures. We apply our algorithm on two real-world networks and LRF benchmark networks. Experimental results show that our algorithm achieves greater accuracy than several well known algorithms in the literature.

In spite of the large effort behind the development of the WBEM and CIM standards for the management of distributed systems, there has been very little work addressing security in those standards. In this paper we present a role-based access control (RBAC) policy language to render fine-grained access control policies for WBEM and CIM. The language is an extension of CIM-SPL, a preliminary DMTF policy language standard. The CIM-SPL RBAC extension fully complies with the WBEM standards. Access control policies can be specified for CIM object constructs according to the standard NIST RBAC model as well as with an extended model adapted for CIM. This extension provides a policy-based RBAC mechanism in the WBEM infrastructure.