检索结果-内蒙古大学图书馆

Interactive Intelligent Systems and Techniques (IIST), International Conference on

作者： Yong Li YuanYuan Ma Mu Chen Chao Wang State Grid Key Laboratory of Information & Network Security State Grid Smart Grid Research Enstitute Co. Ltd Nanjing China State Grid Beijing Electric Power Research Institute Beijing China

ISBN: (数字)9798350374421

ISBN: (纸本)9798350374438

In the new power system scenario, power IoT terminals have new characteristics such as diverse hardware heterogeneity and complex subject ownership, which make it technically difficult to achieve secure access authentication based on traditional terminal hardware fingerprint recognition technology. A power IoT terminal fingerprint recognition technology suitable for the Modbus protocol is proposed to solve this problem. This method combines the characteristics of Modbus protocol packet parsing, which is a common industrial control communication protocol. Firstly, based on active packet detection technology, it realizes the survival judgment of business terminals and constructs a coarse-grained topology image of terminal production. Then, by passively monitoring and analyzing the characteristics of terminal interaction traffic behavior, a terminal behavior fingerprint recognition model is constructed based on the deep learning algorithm BiLSTM to achieve accurate terminal type discrimination, thereby establishing a power IoT terminal fingerprint recognition model. The experimental results in a distributed photovoltaic scenario show that the method has an average classification and recognition accuracy of 89.6% for common power business terminals, which can basically meet the lightweight and non-invasive business requirements of terminal fingerprint recognition in new power system scenarios.

关键词： Photovoltaic systems Analytical models Protocols Accuracy Fingerprint recognition power systems Topology Monitoring Business Load modeling

来源：评论

学校读者我要写书评

暂无评论

BrInstFlip: A Universal Tool for Attacking DNN-Based power Line Fault Detection Models

BrInstFlip: A Universal Tool for Attacking DNN-Based Power L...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Yixin Jiang Yanbo Xu Zhihong Liang Wenqian Xu Tian Dong Ximing Zhang Yiwei Yang Yan Meng Haojin Zhu Electric Power Research Institute China Southern Power Grid Guangzhou China Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China School of Electronics Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China China Southern Power Grid Guangzhou China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

Deep learning neural network (DNN) models are currently experiencing significant success in domains like image classification. In the realm of power grids, there have been numerous attempts to leverage DNN models for fault diagnosis in power grid systems. However, they are also susceptible to various attacks, such as adversarial samples, model poisoning, backdoors, and other attack vectors. These existing attacks exhibit limitations to varying degrees, hampering their ability to execute generalized attacks across models. Designing a universal attack strategy for different DNN models poses challenges. In this paper, we present a novel attack strategy centered around runtime code fault injection, aiming to disrupt the inference capability of DNN architectural fault detection models in smart grid. Our approach meticulously identifies vulnerable bits within common code segments, such as underlying libraries, susceptible to functional bias through automated searches. Leveraging the DRAM Rowhammer Bug, we manipulate memory bits, inducing bias in the functionality of the affected library, consequently impacting all higher-level machine learning frameworks utilizing it. We conducted tests on the VGG-16, ResNet34, and ResNet50 models for the Vari-grip fault detection task using the InsPLAD dataset. Before the attack, the models achieved accuracies of 86.62%, 92.88%, and 97.12% on the test set, respectively. However, after the attack, their accuracies dropped to 0%, which can lead to severe consequences like failure of power grid repair. These results underscore the effectiveness and generalizability of our attack strategy.

关键词： Accuracy Codes Runtime Fault detection Neural networks Random access memory Libraries

来源：评论

学校读者我要写书评

暂无评论

Intelligent Contract Vulnerability Detection Method Based on Bic-RL

Intelligent Contract Vulnerability Detection Method Based on...

引用

Data security and Privacy Protection (DSPP), International Conference on

作者： Shuhui Zhang Changdong Hu Tian Lan LianHai Wang Shujiang Xu Wei Shao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

Blockchain technology is praised for its decentralization, anonymity, and tamper-proof nature, but its complex architecture has led to numerous attacks, particularly against smart contracts. These attacks have caused significant economic losses and hindered the development of blockchain technology. Therefore, research on smart contract vulnerability detection methods has significant practical and application value. Existing detection technologies (such as symbolic execution, formal verification, and so on) have limitations, including heavy reliance on contract source code and incomplete feature extraction. This paper proposes a fully automated smart contract vulnerability detection method based on Bic-RL(Smart contracts Detection Based on Bicubic interpolation and Deep Residual Neural networks - Long short-term memory) to address these issues. This method not only simplifies the data processing process but also realizes the complete feature extraction and ensures the high efficiency of detection performance. Performance evaluation shows this method has higher detection accuracy and generalization ability, with an accuracy rate of 84.5%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FP-OCS: A Fingerprint Based Ownership Detection System for Insulator Fault Detection Model

FP-OCS: A Fingerprint Based Ownership Detection System for I...

引用

IEEE International Conference on Communications in China (ICCC)

作者： Wenqian Xu Fazhong Liu Ximing Zhang Yixin Jiang Tian Dong Zhihong Liang Yiwei Yang Yan Meng Haojin Zhu China Southern Power Grid Electric Power Research Institute Guangzhou China Guangdong Provincial Key Laboratory of Power System Network Security Guangzhou China School of Electronics Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China China Southern Power Grid Guangzhou China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

In smart grids, the robustness and reliability of the transmission system depend on the operational integrity of the insulators. The success of deep learning has facilitated the development of advanced fault detection algorithms for classifying and identifying insulator states. However, these machine learning based detection systems rely on high-quality datasets, making them potential targets for intellectual property theft, and model extraction attacks pose risks of privacy breaches and unauthorized exploitation. To address the challenge of protecting neural network ownership in this situation, we introduce a fingerprint based ownership detection system for insulator fault detection model FP-OCS. FP-OCS uses model extraction attack to generate a series of piracy models, and uses white-box access victim models to generate similarity models and universal adversarial perturbation. The system’s fingerprint generation module augments the original dataset to craft distinctive model fingerprints. Subsequently, FP-OCS’s encoder training module extends the fingerprint dataset using K-means methods and uses contrast learning to train the encoder network and the projection network. Upon finalization of training, FP-OCS evaluates a model’s authenticity by matching its derived fingerprint against the victim model. We evaluated the effectiveness of the system using data-enhanced InsPLAD datasets. Our findings prove that FP-OCS can achieve 100% accuracy in Ownership Detection tasks with 50% similarity dividing line.

关键词： Training Fault detection Perturbation methods Fingerprint recognition Insulators Privacy breach Robustness

来源：评论

学校读者我要写书评

暂无评论

Multi-Classification Segmentation Method of Gastric Cancer Pathological Images Based on Deep Learning

Multi-Classification Segmentation Method of Gastric Cancer P...

引用

Advanced information, Mechanical Engineering, Robotics and Automation (AIMERA), IEEE International Conference on

作者： Hehu Zhou Jingshan Pan Li Na Qingyan Ding Chengjun Zhou Wantong Du Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Department of Pathology The Second Hospital of Shandong University Jinan China

ISBN: (数字)9798350343335

ISBN: (纸本)9798350343342

Gastric cancer is a serious health threat, and pathological imaging is important in detecting it. These images can assist doctors in accurately determining the location of the cancer, thereby providing an important reference for clinical decision-making. In the field of image processing, deep learning technology is leading to more and more excellent segmentation models. The Trans-Unet model has achieved success in the image segmentation. However, when applying this model to gastric cancer pathological section data, the segmentation boundary appears jagged. We propose three possible solutions. First, we designed an attention connection module to replace the skip connections in the model to enhance the prediction accuracy of the model. Second, we designed a prediction processing unit that takes the model’s prediction results as input and uses a Conditional Random Field (CRF) for further prediction calculations. To enable the model to meet the requirements of multi-classification of images, we designed a dynamic weight selection module to enhance the model’s accuracy for multi-classification tasks. After our optimization, the optimized model improved by 8% on the DSC evaluation index and 39% on the HD evaluation index. In addition, the jagged boundary problem in the prediction results has also been effectively improved. Through comparative experiments and erosion experiments, we found that the improved method enhances the accuracy of model prediction and reduces the jagged results at the boundary.

关键词： Training Image segmentation Pathology Adaptation models Accuracy Computational modeling Predictive models Data models Conditional random fields Cancer

来源：评论

学校读者我要写书评

暂无评论

MRLATO: An Adaptive Task Offloading Mechanism Based on Meta Reinforcement Learning in Edge computing Environment

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Zhang, Peiying Liu, Jiamin Guizani, Maher Wang, Jian Kumar, Neeraj Tan, Lizhuang Qingdao Institute of Software College of Computer Science and Technology Qingdao266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao266580 China Ministry of Education Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Jinan250014 China University of Texas Arlington Computer Science and Engineering Department TX United States College of Science Qingdao266580 China Thapar University Department of Computer Science and Engineering Patiala147004 India Jinan250014 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan250014 China

Traditional cloud computing models struggle to meet the requirements of latency-sensitive applications when processing large amounts of data. As a solution, Multi-access Edge computing (MEC) extends computing resources to the edge of the network to reduce processing delays and improve user experience. However, in dynamically changing edge computing environments, effective decision making on whether to offload tasks to edge servers remains a core challenge. For this purpose, we propose MRLATO, an adaptive task offloading mechanism based on Meta Reinforcement Learning (MRL), which exploits a large amount of a priori knowledge of different tasks to achieve fast adaptation. The task offloading process is modelled as multiple Markov Decision Processes (MDPs) and solved using a Sequence to Sequence (Seq2Seq) neural network integrating multi-head attention and recursive task sequencing. It is shown by the experimental results that the proposed method has the lowest latency in all experimental settings and the convergence efficiency is improved by 14.06% compared to the traditional Deep Reinforcement Learning (DRL) algorithm. This research fully demonstrates the significant benefits of the deep integration of MRL with the edge computing domain, providing new optimisation ideas for task offloading decisions. © 1967-2012 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Privacy Protection Methods of power Grid Communication Data Aggregation Based on Federated Learning 7

Privacy Protection Methods of Power Grid Communication Data ...

引用

7th International Symposium on Advances in Electrical, Electronics, and Computer Engineering

作者： He, Weimin Huang, Xiuli Wang, He Zhao, Lei State Grid Jiangsu Electric Power Co. Ltd. Nanjing210000 China State Grid Key Laboratory of Information & Network Security Global Energy Interconnection Research Institute Co. Ltd. Nanjing Branch Nanjing210003 China

ISBN: (纸本)9781510656437

In recent years, as more and more countries attach importance to the next generation grid, a large amount of human and financial resources have been invested in the research and development of smart grid. In order to carry out real-time monitoring and intelligent control of the power grid, the control center of the smart power grid needs to c out inn on sly collect users' electricity consumption data, which, if leaked, will reveal individual users' electricity consumption rules and living habits. How to monitor regional power consumption without revealing how much individual users use has become a challenge. Therefore, the power grid communication data aggregation privacy protection method is designed based on federated learning. Firstly, the power grid communication data privacy types and encryption tools are analyzed. Secondly, the power grid communication data aggregation privacy protection scheme is designed based on federated learning, so as to realize the power grid communication data aggregation privacy protection. The results show that the privacy protection method designed for power grid communication data aggregation is effective and has certain application value. © 2022 SPIE. All rights reserved.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Time Series Anomaly Detection Based on Normalized Flow and Bayesian networks

Time Series Anomaly Detection Based on Normalized Flow and B...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Honglei Yao Donglan Liu Yingxian Chang Xin Liu Chaofan Tang State Grid Shandong Electric Power Research Institute Jinan China State Grid Shandong Electric Power Company Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Time series anomaly detection often faces significant challenges due to the high dimensionality, interdependence, and label sparsity of the data. Traditional methods struggle to model the intricate relationships between multiple time series components and often fail to accurately detect anomalies due to insufficient data dependence mining. To address these issues, we introduce GCRNF, a novel Graph-Enhanced Standardized Flow Model that incorporates a Bayesian network for causality modeling. This model decomposes joint probabilities into conditional probabilities and utilizes a graph dependency encoder with hybrid CNN-RNN models and Graph Convolutional networks (GCNs). Our experimental results demonstrate that GCRNF outperforms existing methods in density estimation, anomaly detection, and drift identification within time series distributions. Specifically, GCRNF showed a significant improvement in detection accuracy and robustness compared to traditional methods, providing a more effective solution for identifying anomalies in complex multivariate time series data.

关键词： Training Graph convolutional networks Industrial control Time series analysis Semantics Cause effect analysis Data models Robustness Bayes methods Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Research on Characteristics and Architecture Application Technology of power Grid Digital System 1

引用

4th International Conference on 3D Imaging Technologies- Multidimensional Signal Processing and Deep Learning, 3D IT-MSP and DL 2022

作者： Wu, Xinping Wang, Gang Lv, Changhui Zhao, Bo Pan, Jianhong Dong, Aidi State Grid Economic and Technological Research Institute Co. Ltd Beijing102209 China State Grid Smart Grid Research Institute CO. LTD Nanjing210003 China State Grid Key Laboratory of Information & Network Security Nanjing210003 China Power Economic Research Institute of Jilin Electric Power Co. Ltd Changchun30011 China State Grid Jilin Electric Power Company Limited Changchun130021 China

ISBN: (数字)9789819911455

ISBN: (纸本)9789819911448

Digital technology plays an increasingly important role in the development of the company and the power grid. The traditional project economic and technical analysis method mainly uses fixed indicators to carry out technical and economic analysis, which cannot achieve dynamic indicator adjustment, and the analysis quality is poor. Traditional methods cannot meet the technical and economic evaluation needs of cross-business digitalization in digital construction. This paper studies the enterprise architecture theory, the connotation and technical characteristics of the power grid digital system, and summarizes the characteristics of the power grid digital system as mass data, extensive connection, software definition, data drive, and cross-domain intelligence. Based on the technical characteristics of the new architecture, this paper proposes a technical scheme of enterprise level digital architecture for power grid business. According to the digital needs and construction status of enterprises, combined with the characteristics of the digital report to be reviewed and its business scenarios, the technical and economic dynamic analysis method of digital projects based on the grid architecture can realize dynamic intelligent evaluation oriented to the grid digital scenarios, improve the technical and economic evaluation efficiency of the grid enterprises’ digital benefits, and improve the collaborative management and control level of the grid digital system construction. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Economic analysis

来源：评论

学校读者我要写书评

暂无评论

SGD-YOLOv5: A Small Object Detection Model for Complex Industrial Environments

SGD-YOLOv5: A Small Object Detection Model for Complex Indus...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Jiabin Pei Xiaoming Wu Xiangzhi Liu Longxiang Gao Shui Yu Xi Zheng Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science University of Technology Sydney Sydney Australia Macquarie University Sydney Australia

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Due to the complexity of industrial environments, such as construction sites and production workshops, the objects to be detected are easily occluded and perceived as small objects, which poses certain challenges for object detection. To ensure a safe industrial environment, this study adopts YOLOv5 as the basic framework and integrates the depth-to-space convolution module to improve the model’s ability to extract feature information of small targets. Second, the global attention mechanism is incorporated into the network to enhance the global interaction information, reducing the feature information loss, and improving the model performance. Finally, to alleviate the contradiction between classification and regression tasks in object detection, the YOLOv5 head is replaced with a decoupled head to achieve better classification and accelerate model convergence. To improve data diversity and enhance model robustness, we augmented the open-source safety helmet wearing dataset (SHWD) and smoking behavior detection dataset (SBDD). We test the performance of the proposed model (SGD-YOLOv5) on the large and small object detection dataset (SODA-D) and VisDrone2021-DET datasets. Furthermore, its ability to detect small objects was also evaluated. Experiments show that our model outperforms all baseline models on SHWD and SBDD. Compared to the TPH-YOLOv5 on the SODA-D dataset, AP and Recall achieve improvements of 18.3% to 19.2% and 11.9% to 13.3% respectively. On the Visdrone 2021-DET dataset, mAP@0.5 achieved an improvement from 35.45% to 35.70% compared to the state-of-the-art model YOLO-Drone.

关键词： YOLO Head Neural networks Production Feature extraction Robustness Data models

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：