检索结果-内蒙古大学图书馆

6th International Conference on Electronics, Communications and Control engineering, ICECC 2023

作者： Chen, Xingyu Lu, Bin Sun, Rongbo Jiang, Mi State Key Laboratory of Mathematical Engineering and Advanced Computing Information Engineering University China Cyber Security College Information Engineering University China

ISBN: (纸本)9798400700002

Honeypot detection is a popular technology in the current cyber security, which can be used to check the disguise and protection level of deployed honeypots. To address the problem of low detection accuracy of existing honeypot detection techniques, this paper proposes a honeypot detection method based on the differences of anomalous requests' response. The method uses the anomalous request packet construction method designed in this paper to construct anomalous request packets, and sends the constructed anomalous request packets to the identity-known devices to collect the responses. Combined with the responses analysis method designed in this paper, the responses are analyzed in terms of similarity in both content and structure dimensions, which enables the evaluation of anomalous request packets in turn, and the selection of those that can consistently trigger a differential response from the honeypots to form a probing packets set based on anomaly. A deep learning model aiming at honeypot detection is designed using the responses of the identity-known devices in response to the probing packets set based on anomaly. The model and the responses of the nodes to detect to the probing packets set based on anomaly are used to detect honeypots. Experiment shows that the method is able to detect the nodes to detect with an accuracy of 96.4%. © 2023 ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

HM-QCNN: Hybrid Multi-branches Quantum-Classical Neural Network for Image Classification 9th

HM-QCNN: Hybrid Multi-branches Quantum-Classical Neural Netw...

引用

19th International Conference on advanced Data Mining and Applications, ADMA 2023

作者： Liu, Haowen Gao, Yufei Shi, Lei Wei, Lin Shan, Zheng Zhao, Bo School of Cyber Science and Engineering Songshan Laboratory Zhengzhou University Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou China

ISBN: (纸本)9783031466632

Quantum machine learning has been developing in recent years, demonstrating great potential in various research domains and promising applications for pattern recognition. However, due to the constraints of quantum hardware, the input qubits are restricted caused by small circuit size, and the fuzziness in all dimensions caused by the features that are difficult to be effectively mined. Besides, previous studies focus on binary classification, but multi-classification received little attention. To address the difficulty in multi-classification, this paper proposed a hybrid multi-branches quantum-classical neural network (HM-QCNN) that utilizes a multi-branch strategy to construct the convolutional part. The part consists of three branches to extract the features of different scales and morphologies. Two quantum convolutional layers apply quantum CRZ gates and rotational gates to design a random quantum circuit (RQC) with 4 qubits and full qubits measurements. The experiments on three public datasets (MNIST, Fashion MNIST, and MedMNIST) demonstrate that HM-QCNN outperforms other prevalent methods with accuracy, precision, and convergence speed. Compared with the classical CNN and the hybrid neural network without multi-branches, HM-QCNN reached 97.40% and improved the accuracy of classification by 6.45% and 1.36% on the MNIST dataset, respectively. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Binary vulnerability mining technology based on neural network feature fusion 5

Binary vulnerability mining technology based on neural netwo...

引用

5th International Conference on advanced Electronic Materials, Computers and Software engineering, AEMCSE 2022

作者： Han, Wenjie Pang, Jianmin Zhou, Xin Zhu, Di State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450002 China

ISBN: (数字)9781665484749

ISBN: (纸本)9781665484749

The high complexity of software and the diversity of security vulnerabilities have brought severe challenges to the research of software security vulnerabilities Traditional vulnerability mining methods are inefficient and have problems such as high false positives and high false negatives, which can not meet the growing needs of software security. To solve the above problems, this paper proposes a binary vulnerability mining technology based on neural network feature fusion. Firstly, this method constructs binary vulnerability data sets containing multiple vulnerability types, then decompile them to the pcode intermediate language level, and then extracts relevant feature vectors from binary vulnerability data sets according to Bert fine tuning model and bilstm model respectively. In order to fully obtain the semantic information of vulnerabilities, this method standardized the two, fused them, and carried out relevant experiments. The experimental results show that the accuracy of vulnerability detection on SARD data set is 96.92%, which is higher than other binary vulnerability detection methods based on neural network. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of security capability of MVX based on probabilistic attack and defense models 3

Analysis of security capability of MVX based on probabilisti...

引用

3rd International Conference on Computer Science and Communication Technology, ICCSCT 2022

作者： Liu, Zijing Zhang, Zheng Xi, Ruicheng Zhu, Pengzhe State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China

ISBN: (纸本)9781510661240

Multi Variant eXecution (MVX) is a security defense technique that uses software diversity to protect system from attacks. MVX improves security capability by enhancing system endogenous security compared to traditional passive defense techniques. However, the current MVX technique lacks formal theoretical analysis and cannot effectively assess the overall security of the system. To address the constraint relationship between complex attack means and dynamic defense environment, we construct a novel atomic combination attack chain model, which decomposes macro attack means into single atomic attack behaviors and provides theoretical support for analyzing the security capability of dynamic systems. Then, the defense model of the MVX system is established, and the defense model's security capability is analyzed using the attack model. Finally, the advantages and shortcomings of the security defense capability of the MVX system are evaluated based on a typical kernel attack example, and system optimization improvement measures are proposed. © 2022 SPIE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

A survey of proactive defense in industrial control system

A survey of proactive defense in industrial control system

引用

2022 International Conference on Electronic Information Technology, EIT 2022

作者： Liu, Ke Wu, Qianqiong Geng, Yangyang Ma, Rongkuan Wei, Qiang State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China

ISBN: (纸本)9781510655096

With the development of Industrial 4.0, the popularity of information technology (IT) systems in industrial control systems (ICSs) has brought great cyber-attack risk. The proactive defense technology, an important defense approach, plays a vital role in ICSs. This paper introduces the definition, taxonomy and application of proactive defense in ICSs. We divide the existing ICS proactive defense approaches into three categories and summarize their technical characteristics. Finally, the application prospects and open issues of proactive defense in ICS are summarized. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Research on Cascading Failures of Power Grid

Research on Cascading Failures of Power Grid

引用

2021 International Conference on Applied Mathematics, Modeling and Computer Simulation, AMMCS 2021

作者： Wang, Hongmin Wei, Qiang Xie, Yaobin State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China

ISBN: (纸本)9781643682549

The safe and stable operation of power system is related to the national economy and people's livelihood of the whole country. Blackouts are almost always caused by cascading failures. This paper first analyzes the global blackouts in the past 20 years, and points out that the scale and probability distribution of blackouts obey the power-law relationship. Secondly, it is concluded that transmission line fault, bus fault, large-scale power flow transfer and relay protection device misoperation are the main factors causing cascading failures. Then, the five stages of cascading failure evolution are analyzed, which are slow successive interruption process, fast successive interruption process, transient oscillation, avalanche blackout and long recovery. Finally, the research results of cascading failure at home and abroad in recent years are analyzed from three research points: small world network, topological network and two-layer coupling network. © 2022 The authors and IOS Press.

关键词： Cyber Physical System

来源：评论

学校读者我要写书评

暂无评论

Recommender system based on adaptive threshold filtering GCN

Recommender system based on adaptive threshold filtering GCN

引用

2022 International Conference on Neural Networks, Information, and Communication engineering, NNICE 2022

作者： Qiao, Meng Gui, Hairen Tang, Ke State Key Laboratory of Mathematical Engineering and Advanced Computing Henan450001 China

ISBN: (纸本)9781510655171

We introduce the AT-GCN (Adaptive Threshold filtering Graph Convolutional Neural network model). AT-GCN is a recommendation model based on graph structure. Compared with the commonly used graph structure recommendation model, AT-GCN can effectively solve the problem of edge representation and information transfer, and improve the recommendation effect. In the experimental part, several groups of experiments were carried out on AT-GCN, and the above conclusions were finally verified by the experimental results. © 2022 SPIE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Research on key Techniques for Reverse engineering of Deep Learning Models for x86 Executable Files 24

Research on Key Techniques for Reverse Engineering of Deep L...

引用

2024 7th International Conference on Computer Information Science and Artificial Intelligence, CISAI 2024

作者： Shi, Meng Lin, Wei Deng, Wenbo College of Cyberspace Security Information Engineering University Henan Zhengzhou China State Key Laboratory of Mathematical Engineering and Advanced Computing Department of Cyberspace Security Henan Zhengzhou China

ISBN: (纸本)9798400707254

In recent years, with the continuous development of machine learning and deep learning, their related applications have gradually appeared in our field of vision, showing explosive growth. A deep learning compiler optimizes a deep learning model, compiles it, and generates a binary file. When this binary file is placed into an edge device, the device can perform model inference. However, the generated binary file shares characteristics with ordinary executable files, meaning that important information within the binary file could potentially be leaked through disassembly. This paper leverages this critical characteristic by reverse-engineering the binary library files of the model to extract key parameters and thereby restore the model’s framework. Using model library files deployed on edge devices, combined with disassembly, model prediction, dynamic analysis, and other methods, this study successfully recovers the model’s operators, topology, and network hyperparameters. Experimental evaluations demonstrate that the framework of the model can be accurately reconstructed, and the substitute model trained using the original dataset achieves accuracy comparable to that of the original model. © 2024 Copyright held by the owner/author(s).

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Bidirectional Data Packet Tampering Method for Linux System

A Bidirectional Data Packet Tampering Method for Linux Syste...

引用

2022 International Conference on Network Communication and Information Security, ICNCIS 2022

作者： Lv, Siou Yang, Pengfei Liu, Shengli State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou450001 China

ISBN: (纸本)9781510661134

Network data security is very important for each user and service provider, and every process of network data transmission is at risk of being tampered with. In this paper, we proposed a bidirectional tampering method of network data for Linux system. In this method we uses the combination of Netfilter and iptables, and uses the NetfilterQueue module in Python to tamper with the packets entering and leaving a Linux host. This tampering operation is transparent to upper users and may cause domain name redirection or many other serious consequences which threaten the security of hosts. Finally, the feasibility of this tampering method is verified by experiments. © 2022 SPIE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

An Opposition-Based Learning Adaptive Chaotic Particle Swarm Optimization Algorithm

引用

Journal of Bionic engineering 2024年第6期21卷 3076-3097页

作者： Chongyang Jiao Kunjie Yu Qinglei Zhou State Key Laboratory of Mathematical Engineering and Advanced Computing PLA Strategic Support Force Information Engineering UniversityZhengzhou450001China Henan Information Engineering School Zhengzhou Vocational College of Industrial SafetyZhengzhou450000China School of Electrical and Information Engineering Zhengzhou UniversityZhengzhou450001China School of Computer and Artificial Intelligence Zhengzhou UniversityZhengzhou450001China

To solve the shortcomings of Particle Swarm Optimization(PSO)algorithm,local optimization and slow convergence,an Opposition-based Learning Adaptive Chaotic PSO(LCPSO)algorithm was *** chaotic elite opposition-based learning process was applied to initialize the entire population,which enhanced the quality of the initial individuals and the population diversity,made the initial individuals distribute in the better quality areas,and accelerated the search efficiency of the *** inertia weights were adaptively customized during evolution in the light of the degree of premature convergence to balance the local and global search abilities of the algorithm,and the reverse search strategy was introduced to increase the chances of the algorithm escaping the local *** LCPSO algorithm is contrasted to other intelligent algorithms on 10 benchmark test functions with different characteristics,and the simulation experiments display that the proposed algorithm is superior to other intelligence algorithms in the global search ability,search accuracy and convergence *** addition,the robustness and effectiveness of the proposed algorithm are also verified by the simulation results of engineering design problems.

关键词： PSO Opposition-based learning Chaotic motion Inertia weight Intelligent algorithm

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：