Multi-view clustering (MVC), which aims to separate the multi-view data into distinct clusters in an unsupervised manner, is a fundamental yet challenging task. To enhance its applicability in real-world scenarios, this paper addresses a more challenging task: MVC under multi-source noises, including missing noise and observation noise. To this end, we propose a novel framework, Reliability-Aware Contrastive Deep Multi-View Clustering (RAC-DMVC), which constructs a reliability graph to guide robust representation learning under noisy environments. Specifically, to address observation noise, we introduce a cross-view reconstruction to enhances robustness at the data level, and a reliability-aware noise contrastive learning to mitigates bias in positive and negative pairs selection caused by noisy representations. To handle missing noise, we design a dual-attention imputation to capture shared information across views while preserving view-specific features. In addition, a self-supervised cluster distillation module further refines the learned representations and improves the clustering performance. Extensive experiments on five benchmark datasets demonstrate that RAC-DMVC outperforms SOTA methods on multiple evaluation metrics and maintains excellent performance under varying ratios of noise.

Contrastive learning is widely used in clustering tasks due to its discriminative representation. However, the conflict problem between classes is difficult to solve effectively. Existing methods try to solve this problem through prototype contrast, but there is a deviation between the calculation of hard prototypes and the true cluster center. To address this problem, we propose a center-oriented prototype contrastive clustering framework, which consists of a soft prototype contrastive module and a dual consistency learning module. In short, the soft prototype contrastive module uses the probability that the sample belongs to the cluster center as a weight to calculate the prototype of each category, while avoiding inter-class conflicts and reducing prototype drift. The dual consistency learning module aligns different transformations of the same sample and the neighborhoods of different samples respectively, ensuring that the features have transformation-invariant semantic information and compact intra-cluster distribution, while providing reliable guarantees for the calculation of prototypes. Extensive experiments on five datasets show that the proposed method is effective compared to the SOTA. Our code is published on https://github.com/LouisDong95/CPCC.

Predicting vehicle trajectories at roundabouts is crucial for road safety, as it enables advanced driver-assistance systems (ADAS) and autonomous vehicles to anticipate and respond to other drivers' intentions effectively. This capability enhances situational awareness, reduces the risk of collisions, and contributes to smoother traffic flow. This paper presents an open-source dataset designed to predict vehicle turning intentions at roundabouts, integrating YOLOv8 for object detection and DeepSORT for multi-target tracking. The dataset includes vehicle timestamps, pixel coordinates and heading angles, utilizing monocular ranging to map vehicles to an actual coordinate system. It supports real-time collision prediction, driver alerts, and the detection of abnormal behaviors such as sudden lane changes or harsh braking. This dataset contributes to the development of safer and more efficient traffic management and autonomous driving systems. The dataset is available for public access on GitHub11Details of the roundabout video dataset can be found in: https://github.com/zhoudashi2016/Roundabout-Video-Dataset-for-ITS..

Roundabouts present unique challenges in intelligent transportation systems due to their complex geometry, dynamic interactions, and the limited availability of high-quality datasets. Existing methodologies typically lack contextual richness and perform inadequately when addressing the non-linear nature of roundabout behavior. This paper introduces a data augmentation framework that leverages large language models (LLMs), specifically a fine-tuned GPT-2, to enrich roundabout datasets with semantically meaningful behavioral patterns. Our approach initiates with extracting vehicle features from real-world video using YOLOv8 and DeepSORT, subsequently using a feedforward neural network (FNN) to extract three latent feature, and training GPT-2 on this corpus to generate high-level behavioral labels, thereby semantically enriching the dataset's diversity and semantic depth. To validate the effectiveness of our framework, we train a long short-term memory (LSTM) model for trajectory prediction. Evaluation with an LSTM predictor shows that models trained on synthetic GPT-generated data outperform those using original data, with lower average relative error (1.46% vs. 1.72%) and improved accuracy at the 100th percentile (62% vs. 54%). Experimental results show that our augmented synthetic dataset is capable of improving the robustness of prediction, establishing a new paradigm for intelligent traffic modeling through the integration of foundational models. Our code is available at https://github.com/Rebecca689/llm-roundabout.

With the explosion of social media platforms, a substantial amount of data is generated from social information network. Tensor-based multi-modal clustering methods have been widely applied in various scenarios of social information network by mining potential correlative relationships from large-scale heterogeneous data. Nevertheless, the accuracy and efficiency of tensor-based multi-modal clustering methods are seriously restricted by noise data and the curse of dimensionality. Therefore, this paper presents a Tucker-based multi-modal clustering (TuMC) and an improved TuMC (ITuMC) to enhance the accuracy and efficiency of multi-modal clustering. First, we propose two Tucker-based attribute weight ranking learning approaches to calculate weight tensor efficiently. Then, we present a calculation approach for Tucker-based selective weighted tensor distance (SWTD) and a TuMC method. Meanwhile, an ITuMC method is explored by optimizing the calculation efficiency of the SWTD to further improve clustering speed. Finally, we present a Tucker-based multi-modal clustering and service framework for social information network. Extensive experimental results based on social Geolife GPS trajectory and electricity consumption datasets demonstrate that the TuMC and ITuMC methods can cluster multi-source heterogeneous data with both higher accuracy and efficiency under complex social information network by DVI, AR and execution time measurement.

Smart grid enhances the intelligence of the traditional power grid, which allows sharing varied data such as consumer, production, or energy with service consumers. Due to the untrustworthy networks, there exist potential security threats (e.g., unauthorized access and modification, malicious data theft) hindering the development of smart grid. While several access control schemes have been proposed for smart grid to achieve sensitive data protection and fine-grained identity management, most of them cannot satisfy the requirements of decentralizing smart grid environment and suffer from key escrow problems. In addition, some existing solutions cannot achieve dynamic user management for lacking the privilege revocation mechanism. In this paper, we propose a decentralizing access control system with user revocation to relieve the above problems. We design a new multiple-authority attribute-based encryption (MABE) scheme to keep data confidentiality and adapt decentralizing smart grid applications. We also compare our proposal with the similar solution from both security and performance. The comparing results show that our access control system can achieve a trade-off among confidentiality, authentication, distribution and efficiency in smart grid.

Edge computing is an emerging distributed computing concept that allows edge servers to provide authorized consumers with various on-demand services. Due to highly dynamic and untrustworthy network environments, various potential security concerns (e.g., unauthorized access, data manipulation, and privacy leakage) have been the critical factors restricting the development of edge computing. A recent heterogeneous framework proposed by Dougherty et al. (CCS’21), named APECS, deploys token-based authorization and multiple attribute-based encryption (MABE) to guarantee access control and data confidentiality. While APECS achieves a secure asynchronous access control without the “always-on” cloud, it suffers from privacy leakage (caused by the public identity information) and fake data spreading issues (due to the data confidentiality). In this paper, we propose an Anonymous and Auditable Distributed Access Control Framework for Edge Computing (AADEC) to relieve these issues. AADEC is based on two building blocks that we designed, namely a conditional anonymous authentication and an auditable MABE with optimized performance. We also define the formal security models and present security proofs for our proposal. The final qualitative comparison and performance benchmark demonstrate that AADEC can achieve a trade-off among anonymity, confidentiality, auditability and efficiency.

Despite the myriad benefits offered by blockchain technology, most of them still face several interrelated issues, such as limited transaction throughput, exorbitant transaction fees, and protracted confirmation times. Payment channel networks have emerged as a promising scalability solution, allowing two mutually distrustful users to engage in multiple off-chain transactions. However, existing schemes based on Hash Time Lock Contract or Anonymous Multi-hop Lock generally cannot ensure strong unlinkability of payments, due to the fact that the time-lock information still remains on the blockchain. To enhance on-chain privacy, a versatile tool was recently proposed by Thyagarajan et al. (CCS’20), namedVerifiable Timed Signatures, but it suffers from the dual insufficiencies of linear-increasing performance and time unverifiability (i.e., performance is linear to the number of signature shares, and signatures cannot be ensured recoverable after the specified time). In this paper, we first propose an approach to reduce computational overhead of VTS, which can be applied to enhance other established schemes, such as VTD (S&P’22) and VTLRS (ESORICS’22). To further reduce the computational complexity fromO(n)toO(1), we introduce a new cryptographic primitive calledVerifiable Timed Adaptor Signatures. Moreover, we extend the VTAS to VTAS+which provides the security property of verifiable recovery. We demonstrate the practicality of our proposal via presenting a concrete instantiation and constructing a privacy-enhanced payment channel network. Finally, the comprehensive evaluation reveals that our solutions exhibit superior performance than the state-of-the-art schemes.

Over the past decade, the Internet of Things (IoT) is widely adopted in various domains, including education, commerce, government, and healthcare. There are also many IoT-based applications drawn significant attentions in recent years. With the increasing numbers of the connected devices in the IoT system, one of the challenging tasks is to ensure devices’ authenticity, which allows users to have a high confidence in the decision. In addition, due to the heterogeneity of the IoT system and the resource-constrained devices, how to efficiently manage such system and guarantee the security and privacy for devices is concerned. In this article, we proposed a new blockchain-based authentication scheme to meet the challenges. Our proposed framework combines the blockchain technique and the modular square root algorithm to achieve an effective authentication process. Besides, we demonstrate the security and utility of the proposed scheme by providing the security analysis and the detailed experiment.

With the trend of low emissions and sustainable development, the demand for hybrid electric vehicles (HEVs) has increased rapidly. By combining a conventional internal combustion engine with one or more electric motors powered by a battery, HEVs have the advantages over traditional vehicles in better fuel economy and lower tailpipe emissions. Nevertheless, the power management strategies (PMSs) for conventional vehicles which mainly focus on the efficiency of internal combustion engine are no longer applicable due to the complex internal structure of HEVs. Hence, a large number of novel strategies appropriate for HEVs have been surveyed, but most of the researches concentrate on discussing the classifications of PMSs and comparing their cons and pros. This paper presents a comprehensive review of power management strategies adopted in HEVs aiming at specific challenges for the first time. The categories of the existing PMSs are presented based on the different algorithms, followed by a brief study of each type including the analysis of its pros and cons. Afterwards, the implementation and optimization of power management strategies aiming at proposed challenges are introduced in detail with the description of their optimization objectives and optimized results. Finally, future directions and open issues of PMSs in HEVs are discussed.