检索结果-内蒙古大学图书馆

TGAC: traffic graph adaptive convolutional neural network-based decentralized application encrypted traffic classification

引用

Journal of Supercomputing 2025年第8期81卷

作者： Ren, Chunni Wang, Jinsong Zhao, Zening School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin300457 China

The rise of blockchain technology has accelerated the development of decentralized applications (DApps), bringing user and network security threats. Efficient decentralized application (DApp) identification is essential for safeguarding user privacy and ensuring blockchain network stability. However, the similarity in communication interfaces and traffic encryption complicates classification. Existing methods also face limitations in feature processing and extraction, leading to lower accuracy. To address these challenges, this paper presents TGAC (traffic graph adaptive convolutional neural network), a DApp identification method based on a graph adaptive convolutional neural network. The method constructs traffic topology graphs by leveraging temporal traffic data, and designs a GAC (graph adaptive convolutional neural network) model to extract key information. It learns local node representations through graph convolution layers and introduces adaptive weights to enhance node features. The method’s effectiveness was validated using a real decentralized encrypted traffic dataset, achieving a classification accuracy of 99.4%, representing a 5% improvement over existing methods. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Byzantine-robust federated learning considering distributed Non-IID data in privacy-sensitive scenarios

引用

Information Fusion 2025年 124卷

作者： Wei, Zongpu Wang, Jinsong Zhao, Zening Zhao, Zhao School of Computer Science and Engineering Tianjin University of technology Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin300457 China

For federated learning (FL), its decentralized training approach is vulnerable to the targeted or untargeted attacks from Byzantine clients, which results in decreased model accuracy. In privacy-sensitive scenarios, the Byzantine clients identification is extremely difficult, due to the fact that gradient information is encrypted. To preserve privacy while identifying Byzantine clients in these scenarios, many schemes on identifying malicious local gradients over ciphertexts are proposed. However, existing works suffer from the problems of inefficiency in non-independent identically distributed (Non-IID) data and potential privacy leakage. To address the issues, we propose a privacy-preserving and byzantine-robust FL scheme (ProFL), which can resist encrypted malicious gradients effectively and protect the privacy of gradients. In ProFL, the linearly homomorphic encryption (LHE) technique is adopted to safeguard the gradient parameters. Specifically, ProFL designs two secure protocols that effectively mitigate potential threats in existing methods while maintaining computation complexity within a linear range. A robust aggregation method based on Manhattan distance is proposed to effectively enhance the robustness of federated aggregation in Non-IID data scenarios. The security and convergence proof of ProFL is given. Finally, extensive evaluations demonstrate that ProFL outperforms other privacy-preserving and byzantine-robust FL schemes in defending against various poisoning attacks. © 2025

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Distributed exact quantum algorithms for Deutsch-Jozsa problem

arXiv

引用

arXiv 2023年

作者： Li, Hao Qiu, Daowen Luo, Le Institute of Quantum Computing and Computer Theory School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China The Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University 510006 China School of Physics and Astronomy Sun Yat-sen University Zhuhai519082 China QUDOOR Technologies Inc. Guangzhou China

Deutsch-Jozsa (DJ) problem is one of the most important problems demonstrating the power of quantum algorithm. DJ problem can be described as a Boolean function f: {0, 1}n → {0, 1} with promising it is either constant or balanced, and the purpose is to determine which type it is. DJ algorithm can solve it exactly with one query. In this paper, we first discover the inherent structure of DJ problem in distributed scenario by giving a number of equivalence characterizations between f being constant (balanced) and some properties of f’s subfunctions, and then we propose three distributed exact quantum algorithms for solving DJ problem. Our algorithms have essential acceleration over distributed classical deterministic algorithm, and can be extended to the case of multiple computing nodes. Compared with DJ algorithm, our algorithms can reduce the number of qubits and the depth of circuit implementing a single query operator. Therefore, we find that the structure of problem should be clarified for designing distributed quantum algorithm to solve it. Copyright © 2023, The Authors. All rights reserved.

关键词： Boolean functions

来源：评论

学校读者我要写书评

暂无评论

Thermodynamics up to the melting point in a TaVCrW high entropy alloy: Systematic ab initio study aided by machine learning potentials

引用

Physical Review B 2022年第21期105卷 214302-214302页

作者： Ying Zhou Prashanth Srinivasan Fritz Körmann Blazej Grabowski Roger Smith Pooja Goddard Andrew Ian Duff School of Science Loughborough University LE11 3TU United Kingdom Institute of Materials Science University of Stuttgart Pfaffenwaldring 55 D-70569 Stuttgart Germany Materials Science and Engineering Delft University of Technology 2628 CD Delft The Netherlands Department for Computational Materials Design Max-Planck-Institut für Eisenforschung GmbH 40237 Düsseldorf Germany Scientific Computing Department STFC Daresbury Laboratory Warrington WA4 4AD United Kingdom

Multi-principal-component alloys have attracted great interest as a novel paradigm in alloy design, with often unique properties and a vast compositional space auspicious for materials discovery. High entropy alloys (HEAs) belong to this class and are being investigated for prospective nuclear applications with reported superior mechanical properties including high-temperature strength and stability compared to conventional alloys. Computational materials design has the potential to play a key role in screening such alloys, yet for high-temperature properties, challenges remain in finding an appropriate balance between accuracy and computational cost. Here we develop an approach based on density-functional theory (DFT) and thermodynamic integration aided by machine learning based interatomic potential models to address this challenge. We systematically evaluate and compare the efficiency of computing the full free energy surface and thermodynamic properties up to the melting point at different stages of the thermodynamic integration scheme. Our new approach provides a ×4 speed-up with respect to comparable free energy approaches at the level of DFT, with errors on high-temperature free energy predictions less than 1 meV/atom. Calculations are performed on an equiatomic HEA, TaVCrW—a low-activation composition and therefore of potential interest for next generation fission and fusion reactors.

关键词： Thermodynamics Disordered alloys Ab initio molecular dynamics Density functional theory

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Tiny Machine Learning for Human Behavior Analysis

引用

IEEE Internet of Things Journal 2025年

作者： Lamaakal, Ismail Essahraui, Siham Maleh, Yassine Makkaoui, Khalid El Ouahbi, Ibrahim Bouami, Mouncef Filali El-Latif, Ahmed A. Abd Almousa, May Peng, Jialiang Sultan Moulay Slimane University Laboratory LaSTI ENSAK Khouribga Morocco Prince Sultan University EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Riyadh11586 Saudi Arabia Menoufia University Faculty of Science Department of Mathematics and Computer Science Shebin El-Koom32511 Egypt Princess Nourah Bint Abdulrahman University College of Computer and Information Sciences Information Technology Department Riyadh Saudi Arabia Heilongjiang University School of Data Science and Technology Harbin150080 China Nanyang Technological University School of Computer Science and Engineering Nanyang Avenue Singapore639798 Singapore

The integration of Tiny Machine Learning (TinyML) with Human Behavior Analysis (HBA) represents a significant advancement in the field of Artificial Intelligence (AI), enabling real-time, efficient, and privacy-preserving analysis on resource-constrained devices. This paper provides the first comprehensive survey exploring this integration, presenting a detailed overview of TinyML, including its definitions, key concepts and advantages. The survey proposes a systematic taxonomy of TinyML applications in HBA, categorizing state-of-the-art implementations based on their use cases and specific methodologies. Furthermore, the challenges and limitations of integrating TinyML in HBA are thoroughly discussed, including technical constraints, data quality issues, and ethical considerations. Finally, future research directions and open issues are outlined, emphasizing the potential advancements and emerging trends in this field. This survey serves as a foundational resource, guiding researchers and practitioners in harnessing the capabilities of TinyML to advance HBA. © 2014 IEEE.

关键词： Embedded systems

来源：评论

学校读者我要写书评

暂无评论

EGRC-Net: Embedding-induced Graph Refinement Clustering Network

arXiv

引用

arXiv 2022年

作者： Peng, Zhihao Liu, Hui Jia, Yuheng Hou, Junhui The Department of Computer Science City University of Hong Kong Kowloon999077 Hong Kong The School of Computing & Information Sciences Caritas In-stitute of Higher Education Hong Kong School of Computer Science and Engineering SoutheastUniversity Nanjing210096 China Key Laboratory of Computer Network and Information Integration Southeast University Ministry of Education China

Existing graph clustering networks heavily rely on a predefined yet fixed graph, which can lead to failures when the initial graph fails to accurately capture the data topology structure of the embedding space. In order to address this issue, we propose a novel clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net), which effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. To begin, we leverage both semantic and topological information by employing a vanilla auto-encoder and a graph convolution network, respectively, to learn a latent feature representation. Subsequently, we utilize the local geometric structure within the feature embedding space to construct an adjacency matrix for the graph. This adjacency matrix is dynamically fused with the initial one using our proposed fusion architecture. To train the network in an unsupervised manner, we minimize the Jeffreys divergence between multiple derived distributions. Additionally, we introduce an improved approximate personalized propagation of neural predictions to replace the standard graph convolution network, enabling EGRC-Net to scale effectively. Through extensive experiments conducted on nine widely-used benchmark datasets, we demonstrate that our proposed methods consistently outperform several state-of-the-art approaches. Notably, EGRC-Net achieves an improvement of more than 11.99% in Adjusted Rand Index (ARI) over the best baseline on the DBLP dataset. Furthermore, our scalable approach exhibits a 10.73% gain in ARI while reducing memory usage by 33.73% and decreasing running time by 19.71%. The code for EGRC-Net will be made publicly available at https://***/ZhihaoPENG-CityU/EGRC-Net. Copyright © 2022, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Stringent Tests of Lorentz Invariance Violation from LHAASO Observations of GRB 221009A

引用

Physical Review Letters 2024年第7期133卷 071501-071501页

作者： Zhen Cao F. Aharonian Axikegu Y. X. Bai Y. W. Bao D. Bastieri X. J. Bi Y. J. Bi W. Bian A. V. Bukevich Q. Cao W. Y. Cao Zhe Cao J. Chang J. F. Chang A. M. Chen E. S. Chen H. X. Chen Liang Chen Lin Chen Long Chen M. J. Chen M. L. Chen Q. H. Chen S. Chen S. H. Chen S. Z. Chen T. L. Chen Y. Chen N. Cheng Y. D. Cheng M. Y. Cui S. W. Cui X. H. Cui Y. D. Cui B. Z. Dai H. L. Dai Z. G. Dai Danzengluobu X. Q. Dong K. K. Duan J. H. Fan Y. Z. Fan J. Fang J. H. Fang K. Fang C. F. Feng H. Feng L. Feng S. H. Feng X. T. Feng Y. Feng Y. L. Feng S. Gabici B. Gao C. D. Gao Q. Gao W. Gao W. K. Gao M. M. Ge L. S. Geng G. Giacinti G. H. Gong Q. B. Gou M. H. Gu F. L. Guo X. L. Guo Y. Q. Guo Y. Y. Guo Y. A. Han M. Hasan H. H. He H. N. He J. Y. He Y. He Y. K. Hor B. W. Hou C. Hou X. Hou H. B. Hu Q. Hu S. C. Hu D. H. Huang T. Q. Huang W. J. Huang X. T. Huang X. Y. Huang Y. Huang X. L. Ji H. Y. Jia K. Jia K. Jiang X. W. Jiang Z. J. Jiang M. Jin M. M. Kang I. Karpikov D. Kuleshov K. Kurinov B. B. Li C. M. Li Cheng Li Cong Li D. Li F. Li H. B. Li H. C. Li Jian Li Jie Li K. Li S. D. Li W. L. Li X. R. Li Xin Li Y. Z. Li Zhe Li Zhuo Li E. W. Liang Y. F. Liang S. J. Lin B. Liu C. Liu D. Liu D. B. Liu H. Liu H. D. Liu J. Liu J. L. Liu M. Y. Liu R. Y. Liu S. M. Liu W. Liu Y. Liu Y. N. Liu Q. Luo Y. Luo H. K. Lv B. Q. Ma L. L. Ma X. H. Ma J. R. Mao Z. Min W. Mitthumsiri H. J. Mu Y. C. Nan A. Neronov L. J. Ou P. Pattarakijwanich Z. Y. Pei J. C. Qi M. Y. Qi B. Q. Qiao J. J. Qin A. Raza D. Ruffolo A. Sáiz M. Saeed D. Semikoz L. Shao O. Shchegolev X. D. Sheng F. W. Shu H. C. Song Yu. V. Stenkin V. Stepanov Y. Su D. X. Sun Q. N. Sun X. N. Sun Z. B. Sun J. Takata P. H. T. Tam Q. W. Tang R. Tang Z. B. Tang W. W. Tian C. Wang C. B. Wang G. W. Wang H. G. Wang H. H. Wang J. C. Wang Kai Wang L. P. Wang L. Y. Wang P. H. Wang R. Wang W. Wang X. G. Wang X. Y. Wang Y. Wang Y. D. Wang Y. J. Wang Z. H. Wang Z. X. Wang Zhen Wang Zheng Wang D. M. Wei J. J. Wei Y. J. Wei T. Wen C. Y. Wu H. R. Wu Q. W. Wu S. Wu X. F. Wu Y. S. Wu S. Q. Xi J. Xia G. M. Xiang D. X. Xiao Key Laboratory of Particle Astrophysics and Experimental Physics Division and Computing Center Institute of High Energy Physics Chinese Academy of Sciences 100049 Beijing China University of Chinese Academy of Sciences 100049 Beijing China Tianfu Cosmic Ray Research Center 610000 Chengdu Sichuan China Dublin Institute for Advanced Studies 31 Fitzwilliam Place 2 Dublin Ireland Max-Planck-Institut for Nuclear Physics P.O. Box 103980 69029 Heidelberg Germany School of Physical Science and Technology and School of Information Science and Technology Southwest Jiaotong University 610031 Chengdu Sichuan China School of Astronomy and Space Science Nanjing University 210023 Nanjing Jiangsu China Center for Astrophysics Guangzhou University 510006 Guangzhou Guangdong China Tsung-Dao Lee Institute and School of Physics and Astronomy Shanghai Jiao Tong University 200240 Shanghai China Institute for Nuclear Research of Russian Academy of Sciences 117312 Moscow Russia Hebei Normal University 050024 Shijiazhuang Hebei China University of Science and Technology of China 230026 Hefei Anhui China State Key Laboratory of Particle Detection and Electronics China Key Laboratory of Dark Matter and Space Astronomy and Key Laboratory of Radio Astronomy Research Center for Astronomical Computing Zhejiang Laboratory 311121 Hangzhou Zhejiang China Key Laboratory for Research in Galaxies and Cosmology Shanghai Astronomical Observatory Chinese Academy of Sciences 200030 Shanghai China School of Physics and Astronomy Yunnan University 650091 Kunming Yunnan China Key Laboratory of Cosmic Rays (Tibet University) Ministry of Education 850000 Lhasa Tibet China National Astronomical Observatories Chinese Academy of Sciences 100101 Beijing China School of Physics and Astronomy (Zhuhai) and School of Physics (Guangzhou) and Sino-French Institute of Nuclear Engineering and Technology (Zhuhai) Sun Yat-sen University 519000 Zhuhai and 510275 Guangzhou Guangdong China Institute of Frontier a

On 9 October 2022, the Large High Altitude Air Shower Observatory (LHAASO) reported the observation of the very early TeV afterglow of the brightest-of-all-time gamma-ray burst 221009A, recording the highest photon statistics in the TeV band ever obtained from a gamma-ray burst. We use this unique observation to place stringent constraints on the energy dependence of the speed of light in vacuum, a manifestation of Lorentz invariance violation (LIV) predicted by some quantum gravity (QG) theories. Our results show that the 95% confidence level lower limits on the QG energy scales are EQG,1>10 times the Planck energy EPl for the linear LIV effect, and EQG,2>6×10−8EPl for the quadratic LIV effect. Our limits on the quadratic LIV case improve previous best bounds by factors of 5–7.

关键词： Gamma ray bursts Gravitation Quantum gravity

来源：评论

学校读者我要写书评

暂无评论

A Heuristic Sparsification Method to Improve the Performance of Neural Networks on Autism Spectrum Disorder Identification Tasks

A Heuristic Sparsification Method to Improve the Performance...

引用

International Conference on Information science and Technology (ICIST)

作者： Fangyu Zhang Yi Pan Yanjie Wei Jin Liu Zhenli Lin Centre for High Performance Computing Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China Shenzhen Key Laboratory of Intelligent Bioinformatics Chinese Academy of Sciences Shenzhen Institute of Advanced Technology Shenzhen China School of Computer Science and Engineering Central South University Changsha China Department of Ophthalmology Shenzhen University General Hospital Shenzhen China

Deep learning (DL) has been widely used in the detection of neurological diseases such as Autism spectrum disorder (ASD). Most studies in this field manually designed and adjusted the hyperparameters of DL models, but due to the huge search space, few studies have attempted to optimize the topology of neural networks which is another important factor related to the performance of DL models. This paper proposes a heuristic sparsification method named the Evolutionary Connection Sparsification Algorithm (ECSA) which is used to optimize the topology of fully connected neural networks (FC-NNs) and generate the corresponding sparsely connected neural networks (SC-NNs). The algorithm is based on the workflow of the genetic algorithm but with improved coding strategy, fitness evaluation approach, crossover and mutation operator, and including an effective convergence acceleration strategy. Experiments show that the SC-NNs generated by ECSA significantly outperform the original FC-NNs in terms of accuracy, F1-score, and AUC, and the model complexities are greatly reduced.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Defend Against Adversarial Samples by Using Perceptual Hash

引用

Computers, Materials & Continua 2020年第3期62卷 1365-1386页

作者： Changrui Liu Dengpan Ye Yueyun Shang Shunzhi Jiang Shiyu Li Yuan Mei Liqiang Wang Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan430072China School of Mathematics and Statistics South Central University for NationalitiesWuhan430074China University of Central Florida 4000 Central Florida Blvd.OrlandoFlorida32816USA

Image classifiers that based on Deep Neural Networks(DNNs)have been proved to be easily fooled by well-designed *** defense methods have the limitations of requiring expensive computation or reducing the accuracy of the image *** this paper,we propose a novel defense method which based on perceptual *** main goal is to destroy the process of perturbations generation by comparing the similarities of images thus achieve the purpose of *** verify our idea,we defended against two main attack methods(a white-box attack and a black-box attack)in different DNN-based image classifiers and show that,after using our defense method,the attack-success-rate for all DNN-based image classifiers decreases *** specifically,for the white-box attack,the attack-success-rate is reduced by an average of 36.3%.For the black-box attack,the average attack-success-rate of targeted attack and non-targeted attack has been reduced by 72.8%and 76.7%*** proposed method is a simple and effective defense method and provides a new way to defend against adversarial samples.

关键词： Image classifiers deep neural networks adversarial samples attack defense perceptual hash image similarity

来源：评论

学校读者我要写书评

暂无评论

Graph-Neural-Network-Based Transaction Link Prediction Method for Public Blockchain in Heterogeneous Information Networks

引用

Blockchain: Research and Applications 2025年

作者： Zening Zhao Jinsong Wang Jiajia Wei School of Computer Science and Engineering Tianjin University of Technology Tianjin 300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin 300384 China National Engineering Laboratory for Computer Virus Prevention and Control Technology Tianjin 300457 China

Public blockchain has outstanding performance in transaction privacy protection because of its anonymity. The data openness brings feasibility to transaction behavior analysis. At present, the transaction data of the public chain are huge, including complex trading objects and relationships. It is difficult to extract attributes and predict transaction behavior by traditional methods. To solve the problems, we extract the transaction features to construct the Ethereum transaction heterogeneous information network (HIN), and propose graph-neural-network-based transaction prediction method for public blockchain in HINs, which can divide the network into subgraphs according to connectivity and make the prediction results of transaction behavior more accurate. Experiments show that the execution time consumption of the proposed transaction subgraph division method is reduced by 70.61% on average compared with the search method. The accuracy of the proposed behavior prediction method also improve compared with the traditional random walk method, with an average accuracy of 83.82%.

关键词： Blockchain Link prediction Heterogeneous information networks Graph neural networks Random walk

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：