检索结果-内蒙古大学图书馆

Online Network traffic anomaly detection method combining OS-ELM and SADE

IEEE Access 2023年 1-1页

作者： Dai, Shiyong Zhao, Yufei Huang, Jinhua Wang, Xuxian Zhao, Guifei Zhang, Lei Xie, Ming Guo, Ziyue China Southern Power Grid Key Laboratory of Power Grid Automation Laboratory Guangzhou Guangdong China State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co.Ltd Beijing China Beijing Institute of Electronic Information Technology Beijing China Power Research Institute of State Grid Gansu Electric Power Company Gansu China Guangxi Power Grid Co. Ltd Nanning Guangxi China Qingyuan Power Supply Bureau of Guangdong Power Grid Co. Ltd Qingyuan Guangdong China

Network traffic anomaly detection methods can detect traffic that is significantly different from normal traffic by analyzing network traffic, and are seen as an effective means to detect unknown new attacks because they do not rely on static feature codes. However, most of the current network traffic anomaly detection methods have low accuracy and high false alarm rate. In this paper, an OS-ELM (Online Sequential Extreme Learning Machine) network traffic anomaly detection method is proposed. First, we use SMOTE to balance the data samples to improve the classification detection performance. In order to reduce the high dimensionality between data features and eliminate the redundancy, the Stacked Denoising Autoencoder (SDAE) network is adopt to reduce the dimension of the feature vectors. Finally, we test the real network traffic and analyze the effect of model structure and external noise on the detection performance, and the experimental results verify the correctness of our scheme. Compared with other detection methods based on data reconstruction, the proposed method has higher detection accuracy and better detection performance. Author

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

APT Attack Investigation via Fine-grained Sequence Construction and Learning

APT Attack Investigation via Fine-grained Sequence Construct...

引用

Computer technology and Information Science (ISCTIS), International Symposium on

作者： Tianqi Wu Zhuo Lv Daojuan Zhang Kexiang Qian Ming Wang State Grid Smart Grid Research Institute co. Ltd SGRI Power Grid Digitizing Technology Department State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Henan Electric Power Company State Grid Henan Electric Power Research Institute State Grid Laboratory of Power Monitoring System Cyber Security Technical Standard Verification School of Information and Communication Engineering Beijing University of Posts and Telecommunications State Grid Corporation of China co. Ltd Beijing China

APT attack investigation aims to provide the security investigators a causal subgraph of the whole causal graph, so that they can easily analyze attacks. However, existing methods either output subgraphs that miss critical attack steps, or are too large and thus challenging to utilize. To address these limitations, we propose a new APT attack investigation approach based on fine-grained sequence construction and learning. Specifically, our approach is built upon the ATLAS framework, and constructs more attack sequences with a finer granularity. It then learns the attack behavior patterns from these constructed sequences. During inference, when presented with an attack symptom, our approach first predicts attack-related nodes in the causal graph and then constructs the causal subgraph based on these nodes. To evaluate our method, we conduct experiments using a simulated environment and four real attacks. The results demonstrate the effectiveness of the proposed approach compared to the state-of-the-art method ATLAS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detecting Anomalous Behaviours Based on System Logs: A Dynamic Graph Perspective

Detecting Anomalous Behaviours Based on System Logs: A Dynam...

引用

6th International Conference on Intelligent Computing and Signal Processing (ICSP)

作者： Ming Wang Yuman Wang Tianqi Wu Cen Chen Kexiang Qian State Grid Corporation of China co. Ltd Beijing China State Grid Smart Grid Research Institute co. Ltd SGRI Power Grid Digitizing Technology Department State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Henan Electric Power Company State Grid Henan Electric Power Research Institute State Grid Laboratory of Power Monitoring System Cyber Security Technical Standard Verification School of Information and Communication Engineering Beijing University of Posts and Telecommunications

System logs provide rich information about the current system’s state. To make use of system logs, various existing work extracts a causal graph from the log events, and then applies graph-based machine learning algorithms to detect the anomalous behaviors. One limitation of these work is that they treat the graph in a static way, neglecting the dynamic nature of anomalous behaviors. In this paper, we propose to detect anomalous behaviors based on system logs using dynamic graph modeling. Our method consists of several key steps, including negative sampling which helps to balance the dataset, edge encoding which encodes the spatial information for each behavior, and sequence modeling which further models the temporal information. Experimental evaluations on real datasets demonstrate the effectiveness of the proposed approach.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of a Data Provenance Scheme with Virtual Tuple-Based Database Watermarking

Design of a Data Provenance Scheme with Virtual Tuple-Based ...

引用

Chinese Automation Congress (CAC)

作者： Qi Wang Aihua Zhou Yiqing Wang Zhen Zheng Jing Jiang Ruxia Yang State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute co. LTD Nanjing China State Grid XuZhou Power Supply Company Xuzhou China Qingpu Power Supply Company State Grid Shanghai Municipal Electric Power Company Shanghai China

The security of power grid is closely related to national security and social stability. With the development of smart grid and big data, grid data security has ushered in new challenges. The data provenance is one of the key issues. Considering the complexity of grid data storage types, this paper designs a virtual tuple-based data provenance scheme. This scheme firstly embedding the watermark with user identity through virtual tuple injection. Then, the data with watermark is distributed in the form of table splitting, which makes it possible to quickly locate the suspect user when a data leakage event occurs. Finally, the leaker is identified through watermark extraction and comparison. The simulation experiments show that our scheme has good robustness against insertion, replacement and deletion attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research and Implementation of Spatial Layout Algorithm and Optimization technology for Digital Twin Objects of Distribution Network Facilities

Research and Implementation of Spatial Layout Algorithm and ...

引用

International Conference on Applied Machine Learning (ICAML)

作者： Junfeng Qiao Lin Peng Aihua Zhou Zhujian Ou Xiaoyi Xu Jianguang Yao State Grid Laboratory of Power cyber-Security Protection & Monitoring Technology State Grid Smart Grid Research Institute Co. LTD Nanjing Jiangsu China Nantong Power Supply Company State Grid Jiangsu Electric Power Co. LTD Nanjing Jiangsu China

The equipment and facilities in the distribution network include not only primary equipment such as transformers, circuit breakers, lightning arr-esters, capacitors, but also secondary equipment such as transfer switches, buttons, indicator lights, current and voltage meters. The total number of equipment types exceeds 200, and the average number of equipment in provincial areas exceeds 100 million. Equipment management is very arduous. The equipment management system in the power industry records the basic archive information of all these equipment, including equipment nameplate, equipment type, equipment operation mode, and geographic information. With the rapid development of power applications, the two-dimensional information description in device management systems cannot meet the needs of more complex power applications. The spatial description and layout of device objects is the foundation for the next step of power business applications. To address this issue, this paper proposes a layout and optimization algorithm for the digital twin object space of distribution network facilities, which visualizes distribution network equipment and facilities, and describes the three-dimensional features of the equipment using point cloud description methods, providing a spatial layout and optimization method for the equipment. The method proposed in this paper has been applied and verified in actual power production and maintenance business, improving the efficiency of power operation and maintenance work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Device Identification based on Network Traffic Fingerprint

Device Identification based on Network Traffic Fingerprint

引用

Artificial Intelligence and Intelligent Information Processing (AIIIP), International Conference on

作者： Tianqi Wu Xiaoming Zhou Hongbin Wu Daojuan Zhang Yingjie Zhang Xiao Han State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute co. Ltd Beijing China Operations Safety and Technology Department State Grid Liaoning Electric Power Supply Co. Ltd. Liaoning China

The devices connected to the LAN have the security risk of being counterfeited and remotely controlled. To identify and understand the devices in the network in advance, the administrator can monitor and handle the abnormal devices in advance. At present, the device recognition method based on deep learning has some limitations. In this paper, the fingerprint information related to the device type is extracted from the network traffic, and the deep learning algorithm based on graph neural network is used to deeply mine the traffic feature hiding relationship between devices, and effectively identify various device types and device models. The effect of the model in this paper on the task of device identification of public data sets has been greatly improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comprehensive assessment method for the power structured data classification and grading based on hierarchical analysis

A comprehensive assessment method for the power structured d...

引用

International Conference on Communications, Information System and Computer Engineering (CISCE)

作者： Yujia Zhai Xiuli Huang Congcong Shi Shenglong Liu Hao Zhang State Grid Laboratory of Power cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co. LTD Nanjing China Big Data Center of State Grid Corporation of China Beijing China State Grid Shandong Electric Power Company Jinan China

With the transformation of the digital development of power grids, the classification and grading of structured data for electricity is an important basis for data security protection. Existing methods for assessing data classification and grading results are mostly always based on individual indicators of the model's operational results. However, such methods can only evaluate a single performance indicator of that result, and cannot provide a comprehensive evaluation of all performance indicators. This paper proposes a comprehensive assessment method for the power structured data classification and grading based on hierarchical analysis, which allows various quality elements of the model to be extracted according to different needs, establishes a hierarchical indicator system, and determines the weights of each indicator in the system by means of hierarchical analysis, and finally calculates a comprehensive quality score for the classification and grading results. Finally, the method is systematically validated using different classification and grading models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Secure Data Circulation and Sharing protection technology Framework for power monitoring System

Research on Secure Data Circulation and Sharing Protection T...

引用

International Conference on Networking and Network Applications (NaNA)

作者： Weicong Huang Jieying Zhou Minghui Jin Zheng Han Sijia Wei State Grid Laboratory of Power cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co. LTD. Nanjing China National Power Dispatching and Control Center State Grid Corporation of China Beijing China State Grid Shanghai Municipal Electric Power Company Shanghai China

With the increasing frequency of data circulation and sharing in power monitoring systems, traditional network-centric protection strategies are insufficient to resist the growing risk of data leakage. This article analyzes the security risks in existing typical data circulation and sharing scenarios based on the demand for data security sharing in power monitoring systems. A data security protection technology framework covering the source layer, interaction layer, and terminal layer has been proposed from the perspectives of basic protection capabilities and key protection technologies, as well as an evaluation method for the protection technology capabilities of data circulation and sharing. This provides a reference idea for effectively enhancing the data circulation and sharing protection capabilities of power monitoring systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research and Application of Distribution Network Dispatching Operation Based on Digital Twinning technology

Research and Application of Distribution Network Dispatching...

引用

Information and Communication technology (ICTech), International Conference of

作者： Junfeng Qiao Zhujian Ou Lin Peng Fuyun Zhu Aihua Zhou Pei Yang State Grid Laboratory of Power cyber-Security Protection & Monitoring Technology State Grid Smart Grid Research Institute Co.ltd. Nanjing Jiangsu China Nantong Power Supply Company State Grid Jiangsu Electric Power Co. LTD. Nanjing Jiangsu China

In the electric distribution grid, the access of distributed electric power generation also brings new technical challenges. From the perspective of operation, after the distributed generation is related to the electric distribution grid, due to the uncertainty of wind energy, solar energy and other new energy, there will be higher harmonics in the distribution network that affect the power quality and power supply reliability. On the other hand, it is necessary to consider the economic cost and reasonably distribute the output status of different units in the distribution network to achieve the unity of economic and ecological benefits. While, it has occasion to research the dispatching method of electric distribution grid with distributed generation. This paper uses digital twinning technology to build virtual equipment modeling scheme, which integrates equipment basic data, system single line diagram and grid geographic coordinate data. With rapid processing governance as the core and electric grid topology computing function, it realizes the whole process management of electric distribution grid dispatching and management, and provides production management personnel with distribution network digital simulation platform and auxiliary decision-making function.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Classification and Grading for power Sensitive Data Based on Hybrid Data Distribution Learning

Classification and Grading for Power Sensitive Data Based on...

引用

IEEE Joint International Information technology and Artificial Intelligence Conference (ITAIC)

作者： Xiuli Huang Yujia Zhai Congcong Shi Yiwen Jiang Shijun Zhang State Grid Laboratory of Power cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co. LTD. Nanjing China Big Data Center of State Grid Corporation of China Beijing China State Grid Jibei Electric Power Co. LTD. Beijing China

power industry data contain various sensitive information, and the leakage of such data will cause critical damage to both the company and the country. However, the unbalanced and various data types make the traditional data classification and grading method fail to achieve enough performance. To better classify and grade the power sensitive data, we propose a Hybrid Data Distribution Learning Network, which simultaneously learns the distribution of multiple data types, including Character-based, Text-based, and Numerical data. Furthermore, we use an optimized nonlinear Support Vector Machine model to detect the grade of power data based on the learned data distribution. The experimental results show that our method outperforms other baselines and achieves a precision of 0.994, a recall of 0.985, and an F 1 of 0.989. The visualization results also show that our method effectively learns the distribution of multiple types of power data.

关键词：

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：