检索结果-内蒙古大学图书馆

A Joint Secure Mechanism of Multi-task Learning For A UAV Team Under FDI Attacks

IEEE Transactions on Mobile Computing 2025年

作者： Zeng, Rongfei Jiang, Chenyang Wang, Xingwei Li, Baochun Northeastern University Software College Shenyang China AliCloud Hangzhou China Northeastern University Department of Computer Science and Engineering Shenyang China University of Toronto Department of Electrical and Computer Engineering Canada

A UAV team shows tremendous potential for various mobile scenarios. However, some evidences reveal their vulnerability to False Data Injection (FDI) attacks, which can significantly jeopardize the flight security or even lead to catastrophic incidents. Existing studies primarily focus on detecting or defending against FDI attacks at the trajectory control of individual UAVs, leaving a gap in a comprehensive secure mechanism that can simultaneously detect, localize, and compensate for such attacks across an entire UAV team. The complexity of developing such a solution is magnified by the multiple design goals, the inherent sophistication of UAV team, and practical attack assumptions. In this paper, we propose a joint secure framework based on multi-task deep learning to simultaneously detect FDI attacks, localize the compromised components, and compensate control signals to mitigate the impact of FDI attacks on promising UAV teams. Specifically, we design an all-in-one deep learning model framework with a temporal-spatial information extraction module and a hierarchical multi-task module to perform three tasks simultaneously. Moreover, we introduce an iterative learning method with experience replay to counteract knowledge decay during model training. Extensive experiments and real flight demonstrations are presented to validate the improved performance and the benefits of our proposed secure method. A demonstration video and our source code can be accessed via https://***/WingFeiTsang/JS/. © 2025 IEEE. All rights reserved.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

FLEKE: Federated Locate-then-Edit Knowledge Editing

arXiv

引用

arXiv 2025年

作者： Zhao, Zongkai Xu, Guozeng Li, Xiuhua Wei, Kaiwen Zhong, Jiang School of Big Data & Software Engineering Chongqing University China College of Computer Science Chongqing University China

Locate-then-Edit Knowledge Editing (LEKE) is a key technique for updating large language models (LLMs) without full retraining. However, existing methods assume a single-user setting and become inefficient in real-world multi-client scenarios, where decentralized organizations (e.g., hospitals, financial institutions) independently update overlapping knowledge, leading to redundant mediator knowledge vector (MKV) computations and privacy concerns. To address these challenges, we introduce Federated Locate-then-Edit Knowledge Editing (FLEKE), a novel task that enables multiple clients to collaboratively perform LEKE while preserving privacy and reducing computational overhead. To achieve this, we propose FedEdit, a two-stage framework that optimizes MKV selection and reuse. In the first stage, clients locally apply LEKE and upload the computed MKVs. In the second stage, rather than relying solely on server-based MKV sharing, FLEKE allows clients retrieve relevant MKVs based on cosine similarity, enabling knowledge re-edit and minimizing redundant computations. Experimental results on two benchmark datasets demonstrate that FedEdit retains over 96% of the performance of non-federated LEKE while significantly outperforming a FedAvg-based baseline by approximately twofold. Besides, we find that MEMIT performs more consistently than PMET in the FLEKE task with our FedEdit framework. Our code is available at https://***/zongkaiz/FLEKE. Copyright © 2025, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

WQuatNet: Wide range quaternion-based head pose estimation

引用

Journal of King Saud University - computer and Information sciences 2025年第3期37卷 1-14页

作者： Algabri, Redhwan Shin, Hyunsoo Abdu, Ahmed Bae, Ji-Hun Lee, Sungon Dept. of Computer Science & Engineering College of AI Convergence Sejong University Seoul 05006 South Korea Research Institute of Engineering and Technology Hanyang University Ansan 15588 South Korea School of Software Northwestern Polytechnical University Xi’an 710072 China Department of Robotics Hanyang University Ansan 15588 South Korea

Head pose estimation (HPE) is a critical task for numerous applications ranging from human-computer interaction, healthcare, and robotics, to surveillance. Most existing methods employ Euler angles as a representation, which often face challenges such as a gimbal lock, especially in full-range rotation scenarios or rotation matrices that require nine parameters. This study introduces WQuatNet, a novel deep learning-based model that leverages the quaternion representation, which uses only four parameters, to avoid this challenge. WQuatNet was designed based on a landmark-free HPE method to predict head poses across the full-range angles of 360∘ from images. Landmark-free methods bypass the need for explicit detection of facial landmarks;instead, they leverage the entire image to estimate the head orientation. The model incorporates a RepVGG-D2se backbone for robust feature extraction and introduces two loss functions tailored for quaternion predictions. Our experimental results on multiple HPE datasets covering both narrow- and full-range angles demonstrate that WQuatNet outperforms the state-of-the-art (SOTA) approaches in terms of accuracy. The performance of the proposed HPE was evaluated using the CMU, AGORA, BIWI, AFLW2000, and 300W-LP datasets. We also perform ablation studies and error analyses to validate the significance of each component of the model. © The Author(s) 2025.

关键词： Deep neural network Full range of rotation Head pose estimation Quaternion

来源：评论

学校读者我要写书评

暂无评论

Novel Load Balancing Mechanism Based on Deep Reinforcement Learning for Human-Centric Applications in Data Centers

引用

Human-centric Computing and Information sciences 2025年 15卷

作者： Hu, Jinbin Luo, Wangqing He, Yi Rao, Shuying Alqahtani, Fayez Tolba, Amr Zhu, Min Wang, Jin School of Computer and Communication Engineering Changsha University of Science and Technology Changsha China Software Engineering Department College of Computer and Information Sciences King Saud University Riyadh Saudi Arabia Department of Computer Science Community College King Saud University Riyadh Saudi Arabia College of Information Science and Technology Zhejiang Shuren University Zhejiang China

Human-computer interaction applications require ultra-low response delays to achieve a better user experience. With the rapid growth of data center network (DCN) topologies, the number of equal-cost paths has increased dramatically. It is imperative to use load balancing between parallel paths to improve link utilization. However, the existing load balancing mechanisms cannot make appropriate forwarding decisions for reacting to the dynamic traffic and path congestion status in large-scale DCNs, resulting in poor network performance. In this paper, we have proposed a dynamic load balancing (DLB) mechanism that uses deep reinforcement learning (DRL) to monitor the status of parallel paths in real time and uses the depth deterministic policy gradient algorithm to make the path state weight (PSW) automatically adapt to different network load scenarios. It then automatically configures the PSW through the DRL agent to guide the switch to select the best forwarding path to balance the load. The experimental results show that DLB significantly reduces the average flow completion by up to 36% compared to state-of-the-art load balancing schemes such as DRILL, LetFlow, and RPS under the asymmetric topology scenario, the result of which significantly enhances the efficiency of human-centric interaction. © (2024), (Korea Information Processing Society). All Rights Reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

EBCFL: An Efficient BlockChain-based Federated Learning Framework for Internet of Vehicles

引用

IEEE Network 2025年

作者： Cao, Dun Liao, Yonghui Alqahtani, Fayez Wang, Jin School of Computer and Communication Engineering Changsha University of Science and Technology China Changsha University of Science and Technology China Software Engineering Department College of Computer and Information Sciences King Saud University Saudi Arabia Hunan University of Science and Technology China

Federated Learning (FL) can train a shared model while protecting vehicle data privacy, which has significant advantages in improving driving safety and efficiency. However, there are still many challenges in applying FL to Internet of Vehicles (IoV). First, the varying computing capabilities of moving vehicles result in slow convergence speed due to underperforming vehicles. Second, malicious vehicles may tamper with model parameters before uploading them to the central server, which is itself vulnerable to single-point failure. To solve the above challenges, we design an efficient and decentralized blockchain FL framework (Efficient BlockChain-based Federated Learning Framework, EBCFL). This framework effectively prevents possible malicious behaviors in the vehicular network nodes and improves the efficiency of FL through a well-designed security verification mechanism. The experimental results show that EBCFL outperforms other schemes in terms of average test accuracy and average total time cost, indicating that EBCFL significantly improves the learning efficiency while bearing an acceptable additional time cost for blockchain communication, demonstrating its strong ability to guard against malicious behaviours and ensure robustness. © 1986-2012 IEEE.

关键词： Blockchain Federated learning IoV Security verification

来源：评论

学校读者我要写书评

暂无评论

An Overview of Security Threats, Attack Detection and Defense for Large-Scale Multi-Agent Systems (LSMAS) in Internet of Things (IoT)

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical Systems 2025年 3卷 70-81页

作者： Cai, Jijing Wen, Long Feng, Hailin Fang, Kai Chen, Junxin Wei, Wei Wang, Wei Zhejiang A and F University College of Mathematics and Computer Science Hangzhou311300 China Macau University of Science and Technology School of Innovation Engineering Macau999078 China Dalian University of Technology School of Software Dalian116621 China Xi'an University of Technology School of Computer Science and Engineering Xi'an710048 China Beijing Institute of Technology School of Medical Technology Beijing100081 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Shenzhen518172 China

With the global advancement of the Internet of Things (IoT), large-scale multi-agent systems (LSMAS) technology has been increasingly adopted across various industries. Despite the widespread use of IoT, vulnerabilities in its software and hardware components pose significant challenges to ensuring security. To address the security concerns faced by LSMAS, this article explores its application in IoT domains such as smart grids, smart manufacturing, and smart healthcare. By examining the structural layers of IoT-the perception layer, network layer, and application layer-this paper analyzes the specific security threats encountered by each layer, along with the defense strategies designed to counter these attacks. Furthermore, we categorize and compare both traditional and AI-based attack detection methods, dividing the latter into machine learning-based, deep learning-based, and transfer learning-based approaches. This analysis highlights the strengths and weaknesses of the various attack detection methods currently deployed in LSMAS, identifying the existing challenges they face. Finally, we outline potential trends for the future development of LSMAS in IoT, offering research directions for experts in related fields. © 2023 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Survey on Anomaly Detection with Few-Shot Learning 8th

A Survey on Anomaly Detection with Few-Shot Learning

引用

8th International Conference on Cognitive Computing, ICCC 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Chen, Junyang Wang, Changbo Hong, Yifan Mi, Rui Zhang, Liang-Jie Wu, Yirui Wang, Huan Zhou, Yue College of Computer Science and Software Engineering Shenzhen University Shenzhen China Center of Health Administration and Development Studies Hubei University of Medicine Shiyan China College of Informatics Huazhong Agricultural University Wuhan China Hohai University Nanjing China Department of Obstetrics and Gynecology Tianyou Hospital Affiliated to Wuhan University of Science and Technology Wuhan China

ISBN: (纸本)9783031779534

The primary objective of anomaly detection is to identify abnormal or unusual patterns within a dataset, where the number of normal samples typically exceeds that of abnormal samples. Due to the scarcity of labeled abnormal samples, traditional methods face challenges when dealing with anomaly detection. To overcome these limitations, few-shot learning has emerged as a promising solution. By leveraging a limited number of labeled anomaly samples, few-shot learning enables the construction of models that enhance anomaly detection performance and generalization. This paper provides a comprehensive investigation of anomaly detection, covering its definition, fundamental principles, methods, and challenges. Furthermore, it introduces few-shot learning as a solution and explores its principles, applications, and technical categorization, including meta-learning, transfer learning, generative models, prototypical learning, and siamese networks. The paper explores the utilization of few-shot learning in anomaly detection across diverse data types This paper delves into significance across different domains. Additionally, it addresses the challenges faced by few-shot learning in the field of anomaly detection and proposes future directions for development. This comprehensive analysis aims to provide profound insights and guidance for prospective research and application in anomaly detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Multi-perception large kernel convnet for efficient image super-resolution

引用

四川大学学报(自然科学版) 2025年第1期62卷 67-78页

作者： MIAO Xuan LI Zheng XU Wen-Zheng College of Computer Science(College of Software) Sichuan UniversityChengdu 610065China Tianfu Engineering-Oriented Numerical Simulation&Software Innovation Center Sichuan UniversityChengdu 610207China

Significant advancements have been achieved in the field of Single Image Super-Resolution(SISR)through the utilization of Convolutional Neural Networks(CNNs)to attain state-of-the-art *** efforts have explored the incorporation of Transformers to augment network performance in ***,the high computational cost of Transformers makes them less suitable for deployment on lightweight ***,the majority of enhancements for CNNs rely predominantly on small spatial convolutions,thereby neglecting the potential advantages of large kernel *** this paper,the authors propose a Multi-Perception Large Kernel convNet(MPLKN)which delves into the exploration of large kernel ***,the authors have architected a Multi-Perception Large Kernel(MPLK)module aimed at extracting multi-scale features and employ a stepwise feature fusion strategy to seamlessly integrate these *** addition,to enhance the network's capacity for nonlinear spatial information processing,the authors have designed a Spatial-Channel Gated Feed-forward Network(SCGFN)that is capable of adapting to feature interactions across both spatial and channel *** results demonstrate that MPLKN outperforms other lightweight image super-resolution models while maintaining a minimal number of parameters and FLOPs.

关键词： Single Image Super-Resolution Lightweight model Deep learning Large kernel

来源：评论

学校读者我要写书评

暂无评论

A Safety Evaluation Method and System for a High Core Wall Dam Based on Construction Data

Journal of Intelligent Construction

引用

Journal of Intelligent Construction 2025年第1期3卷 1-14页

作者： Zicheng Wang Yingchi Mao Yaosheng Tan Qiaoling Shen Houlei Xu College of Computer Science and Software Engineering Hohai University Nanjing China PowerChina Kunming Engineering Corporation Limited Kunming China China Three Gorges Group Corporation Beijing China

In view of the complex operational conditions and dynamically changing safety risks associated with high core wall dams in the construction period, a comprehensive safety evaluation system for high core wall dams, which utilizes fuzzy theory and emergency response methods, has been developed. Considering the material zoning, load characteristics, and layout of the safety monitoring system specific to high core wall dams and considering the impacts of flood control capacity, foundation conditions, structural safety, operational status, and slope conditions, a safety evaluation method for high core wall dams on the basis of construction data has been proposed. The model dynamically determines the weights of evaluation factors via evaluation criteria and the term frequency-inverse document frequency (TF-IDF) method. It constructs a comprehensive evaluation subordination feature vector, calculates the degree of match between the current safety evaluation result and historical safety evaluation results, and identifies the matching operational conditions. Finally, on the basis of the risk analysis matrix, the risk level of each tier of evaluation factors is determined, and emergency response measures are formulated. This system provides an online monitoring platform for the operational safety of high core wall dams. This approach enhances the capacity for safety analysis and risk emergency decision-making in hydraulic and hydroelectric engineering.

关键词： Matched filters Dams Current measurement Inspection Emergency services Vectors Floods Risk analysis Personnel Monitoring

来源：评论

学校读者我要写书评

暂无评论

An Efficient Intrusion Detection System using Advanced Machine Learning Techniques in SDN for Healthcare System

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Asif, Muhammad Waseem Aqdus, Aqsa Amin, Rashid Chaudhry, Shehzad Ashraf Alsubaei, Faisal S. Iqbal, Sajid Department of Computer Science and IT The University of Lahore Lahore54000 Pakistan Department of Computer Science University of Chakwal Chakwal48800 Pakistan Department of Computer Science and Information Technology College of Engineering Abu Dhabi University Abu Dhabi United Arab Emirates Department of Software Engineering Faculty of Engineering and Architecture Nisantasi University Istanbul Turkey The Department of Cybersecurity College of Computer Science and Engineering University of Jeddah Jeddah Saudi Arabia

The quick advancement of healthcare systems necessitates robust and efficient network security keys to defend sensitive patient records and guarantee uninterrupted service delivery. The current IDS has many challenges, such as a high false positive rate, poor accuracy of detection, slow response to threats, and inability to scale well. This paper proposes an efficient and real-time intrusion detection system (IDS) using advanced machine learning techniques within a software-defined networking (SDN) framework specifically tailored for healthcare systems. The proposed architecture implements a Machine Learning (ML) model that combines the SVM and KNN to better identify malicious activities. Full sets of detection and mitigation capabilities are implemented to address different types of traffic in the network with the least interference. Through the different evaluation measures, the efficiency of the proposed model is assured. Network performance is determined by success rate queries, packet losses in each domain path, and the CPU being used by the system. Responsiveness is measured through delay metrics grounded on end-to-end delay, hop-to-hop packet delay, latency rate, and propagation delay. Moreover, model accuracy fidelity is reviewed via precision assessment, alpha (α) affecting the accuracy of the model, and confusion matrix with different techniques with the proposed hybrid SVM-KNN model. Last of all, a comparison of the security of the models in question strengthens the argument in favor of the proposed model. More specifically, flow and network topology diagrams are included to show how integration may be accomplished in linkage or merger with existing healthcare networks. The results also present a 30% overall advancement in detection and mitigation by presenting the hybrid SVM-KNN model to overcome other traditional models. This proposed model shows significant improvements not less than 20-30% improvement in CPU use, 30-50% reduction in end-to-end delay,

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：