检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhou, Jiajun Yao, Jiacheng Chen, Xuanze Yu, Shanqing Xuan, Qi Yang, Xiaoniu Institute of Cyberspace Security Zhejiang University of Technology Hangzhou310023 China Binjiang Institute of Artificial Intelligence ZJUT Hangzhou310056 China College of Computer Science and Technology Zhejiang University of Technology Hangzhou310023 China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033 China

Lateral movement is a crucial component of advanced persistent threat (APT) attacks in networks. Attackers exploit security vulnerabilities in internal networks or IoT devices, expanding their control after initial infiltration to steal sensitive data or carry out other malicious activities, posing a serious threat to system security. Existing research suggests that attackers generally employ seemingly unrelated operations to mask their malicious intentions, thereby evading existing lateral movement detection methods and hiding their intrusion traces. In this regard, we analyze host authentication log data from a graph perspective and propose a multi-scale lateral movement detection framework called LMDetect. The main workflow of this framework proceeds as follows: 1) Construct a heterogeneous multigraph from host authentication log data to strengthen the correlations among internal system entities;2) Design a time-aware subgraph generator to extract subgraphs centered on authentication events from the heterogeneous authentication multigraph;3) Design a multi-scale attention encoder that leverages both local and global attention to capture hidden anomalous behavior patterns in the authentication subgraphs, thereby achieving lateral movement detection. Extensive experiments on two real-world authentication log datasets demonstrate the effectiveness and superiority of our framework in detecting lateral movement behaviors. Copyright © 2024, The Authors. All rights reserved.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

An Anti-jamming Intelligent Decision-Making Method for Multi-user Communication Based on Deep Reinforcement Learning 22

An Anti-jamming Intelligent Decision-Making Method for Multi...

引用

22nd IEEE International Conference on Communication technology, ICCT 2022

作者： Zhang, Lan Ma, Liang Tian, Feng Liang, Tianyi Science and Technology on Communication Information Security Control Laboratory Jiaxing314000 China The 36th Research Institution of China Electronics Technology Group Corporation Jiaxing341000 China Nanjing University of Posts and Telecommunications Nanjing210023 China

ISBN: (纸本)9781665470674

In order to effectively cope with the external malicious jamming from jammers and avoid mutual interference caused by competitive channels among users, an intelligent antijamming decision-making method based on deep reinforcement learning for multi-user communication is proposed in this paper. In multiple jamming modes, the base station perceives the current spectrum information of the multi-user and the jammer and makes it as the input of the deep reinforcement learning strategy neural network, then selects the joint action according to the dynamic greedy algorithm, which will help the users intelligently select the communication frequency band via the feedback from the base station. The simulation results show that the proposed method effectively overcome the communication jamming induced by external jammers and internal users. Moreover, the normalized throughput of each user in the proposed algorithm is much higher than the random frequency hopping and fixed ϵ deep reinforcement learning algorithm with faster convergence speed. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Study on the Medium Fusion Data Storage technology for High Performance Airborne Sensors

Study on the Medium Fusion Data Storage Technology for High ...

引用

Intelligent technology and Embedded Systems (ICITES), International Conference on

作者： Dan Xie Haishan Tian Yuxin Sun Mingru Zhang Yawei Huang Chang Tang School of Physics and Electronics Hunan Normal University Changsha China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjing China

The data rate of high-performance airborne sensors is much higher than the wireless data transfer rate in many detection applications, so the onboard data storage systems are usually used to store the sensor data. There is a problem in the onboard data storage that the frequency of address jumps among incontinuous areas is very high due to the high data updating frequency of the FAT (File Allocation Table) and FDT (File Directory Table), which would significantly reduce the data storage speed. This is because the most widely used NAND (Not And) flash has a long response time when storing the data in the incontinuous areas. In order to solve the problem, a called medium fusion storage method, which uses multiple mediums time sharing to store the data of file areas and data region, is proposed in this study. The performance of the proposed method is tested on an actual data storage system of the airborne sensor. The experimental results show that medium fusion storage method significantly reduces the data updating frequency of the FAT and FDT in the data storage, and the response time is negligible compared with the actual data writing time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of High-Speed Serial Transmission for ADC Based on JESD204B

Design and Implementation of High-Speed Serial Transmission ...

引用

Intelligent technology and Embedded Systems (ICITES), International Conference on

作者： Yawei Huang Haishan Tian Mingru Zhang Yuxin Sun Dan Xie Chang Tang School of Physics and Electronics Hunan Normal University Changsha China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjing China

Currently, as the resolution of sensors such as radar continues to improve, the signal bandwidth is rapidly increasing. There is a growing demand for higher sampling rates and data transmission rates in Analog-to-Digital Converters (ADCs). However, the parallel transmission commonly used in ADCs faces issues such as high crosstalk and difficulties in transmission synchronization. In response to this problem, this paper proposes a method for the design and implementation of a high-speed serial data transmission interface based on JESD204B. Specifically, it utilizes Xilinx's ZYNQ-7 series FPGA and ADC as the core components and presents clock synchronization design, ADC circuit design, and FPGA 204B IP design methods. Experimental testing was conducted using selected link parameters (LMFS=4222) as an example. The experimental results demonstrate that correct JESD204B interface data transmission for four channels was achieved at a data rate of 10 Gbps, thus validating the feasibility of the proposed high-speed transmission link design based on JESD204B in this paper.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-Aid OTFS Receiver: Design and Performance Evaluation

Artificial Intelligence-Aid OTFS Receiver: Design and Perfor...

引用

Ubiquitous Communication (Ucom), International Conference on

作者： Chenxi Wang Li Ping Qian Huijie Zhu College of Information Engineering Zhejiang University of Technology Hangzhou China Science and Technology on Communication Information Security Control Laboratory The 36th Research Institute of China Electronics Technology Jiaxing China

OTFS technology is attracting much attention due to its strong adaptability to high-speed mobility and high spectrum efficiency. Studies show that applying deep learning (DL) to traditional communication systems significantly improves their performance. To this end, this paper proposes an AI-aid OTFS receiver to enhance the performance of OTFS systems in high-speed mobile communication scenarios. The proposed receiver employs two networks - a channel estimation network called TFNet and a decoding network called RecovNet. In the channel estimation module, TFNet performs more accurate channel estimation based on the results of traditional channel estimation methods. In the decoding module, RecovNet decodes the signal based on the equalized signals. To validate the superiority of our proposed receiver, we conduct comparative testing with a traditional receiver under the integer Doppler channel. The experimental results demonstrate that integrating DL technology in OTFS systems effectively enhances their performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fast Informer-Based Time Series Detection

Fast Informer-Based Time Series Detection

引用

International Symposium on Antennas, Propagation and EM Theory (ISAPE)

作者： Weiguo Shen Tianhao Xia Dongwei Xu Qi Xuan Yun Lin Wei Wang Science and Technology on Communication Information Security Control Laboratory Jiaxing China Zhejiang University of Technology College of Information Engineering Institute of Cyberspace Security Binjiang Institute of Artificial Intelligence HangZhou China Zhejiang University of Technology Institute of Cyberspace Security Binjiang Institute of Artificial Intelligence HangZhou China College of Information and Communication Engineering Harbin Engineering University Binjiang Institute of Artificial Intelligence Harbin China

ISBN: (数字)9798350353129

ISBN: (纸本)9798350353136

Time series data are pivotal in modern technology and industrial applications,but they are frequently impacted by anomalies due to system failures,cyberattacks,or unexpected events. Therefore,swift and accurate anomaly detection in time series is crucial. This paper introduces ‘TransIDS’,an intrusion detection method that focuses on the efficient extraction and detection of time series features. TransIDS uses the Informer model to capture temporal features within data frames more effectively,improving detection performance and reducing runtime. We also fine-tune the Informer model and introduce an automatic anomaly threshold selection method,optimizing it for anomaly detection tasks. We validate TransIDS through experiments on various datasets and compare it with three existing methods. The results show that TransIDS outperforms the compared models in detection performance.

关键词： Runtime Accuracy Antenna theory Time series analysis Intrusion detection Predictive models Feature extraction Transformers Data models Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

DEEPCON: Improving Distributed Deep Learning Model Consistency in Edge-Cloud Environments via Distillation

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Qian, Bin Qian, Jiaxu Wen, Zhenyu Wu, Di He, Shibo Chen, Jiming Ranjan, Rajiv Zhejiang University State Key Laboratory of Industrial Control Technology Hangzhou China Zhejiang University of Technology Institute of Cyberspace Security College of Information Engineering Hangzhou China University of St Andrews School of Computer Science United Kingdom Newcastle University United Kingdom

In a typical distributed Deep Learning (DL) based application, models are configured differently to meet the requirements of resource constraints. For instance, a large ResNet56 model is deployed on the cloud server while a small lightweight MobileNet model is more suitable for the end-user device with fewer computation resources. However, the heterogeneity of the model architectures and configurations may bring a systemic problem -models may produce different outputs when given the same input. This inconsistency problem may cause severe system failure of prediction agreement inside the application. Current research has not studied the systemic design for efficiently detecting and reducing the inconsistency among models in distributed DL applications. With the increasing scale of distributed DL applications, the challenges of inconsistency mitigation should consider both algorithm and system design. To this end, we design and implement DEEPCON, an adaptive deployment system across the edge-cloud layer with over-the-air model updates. We implement ASRS sampling for efficiently sampling data to reveal the real data distribution as well as model prediction inconsistency. Then, we implement DMML-Par, an asynchronous parallel training algorithm for quickly updating the models and reducing inconsistency. implements over-the-air updates with a set of APIS to enable seamless inconsistency detection and reduction in such deep learning applications. Our experiment results on both vision and language tasks demonstrate that DMML could improve the model consistency up to 4%, 7%, and 13% at CIFAR10/100 and IMDB datasets without sacrificing the accuracy of individual models. We also show that the ASRS sampling can save 90% network bandwidth of data transmission and that DMML-Par is up to 60% faster compared to simple synchronous parallel training. 2015 IEEE.

关键词： Distributed cloud

来源：评论

学校读者我要写书评

暂无评论

Thermal camera based on frequency upconversion and its NETD characterization

arXiv

引用

arXiv 2023年

作者： Ge, Zheng Zhou, Zhi-Yuan Ceng, Jing-Xin Chen, Li Li, Yin-Hai Li, Yan Niu, Su-Jian Shi, Bao-Sen CAS Key Laboratory of Quantum Information University of Science and Technology of China Anhui Hefei230026 China CAS Center for Excellence in Quantum Information and Quantum Physics University of Science and Technology of China Hefei230026 China Science and Technology on Electro-Optical Information Security Control Laboratory Tianjin300308 China

We present a scheme for estimating the noise-equivalent temperature difference (NETD) of frequency upconversion detectors (UCDs) that detect mid-infrared (MIR) light. In particular, this letter investigates the frequency upconversion of a periodically polarized crystal based on lithium niobate, where a mid-infrared conversion bandwidth of 220 nm can be achieved in a single poled period by a special design. Experimentally for a temperature target with a central wavelength of 7.89 μm in mid-infrared radiation, we estimated the NETD of the device to be 56 mK. Meanwhile, a direct measurement of the NETD was performed utilizing conventional methods, which resulted in 48 mK. We also compared the NETD of our UCD with commercially available direct mid-infrared detectors. Here, we showed that the limiting factor for further NETD reduction of our device is not primarily from the upconversion process and camera noise, but from the limitations of the heat source performance. Our detectors have good temperature measurement performance and can be used for a variety of applications involving temperature object identification and material structure detection. Copyright © 2023, The Authors. All rights reserved.

关键词： Temperature measurement

来源：评论

学校读者我要写书评

暂无评论

IMPROVED GNSS-IR HEIGHT MEASUREMENT METHOD BASED ON LOCALLY WEIGHTED REGRESSION 9

IMPROVED GNSS-IR HEIGHT MEASUREMENT METHOD BASED ON LOCALLY ...

引用

9th International Symposium on Test Automation and Instrumentation, ISTAI 2022

作者： Luo, Zhaowang Shang, Junna Li, Fangzhou Pang, Run Wang, Yiteng College of Telecommunication Engineering Hangzhou Dianzi University Hangzhou310018 China Science and Technology on Communication Information Security Control Laboratory Jiaxing314033 China The 36th Research Institute of China Electronics Technology Group Corporation Jiaxing314033 China

ISBN: (纸本)9781839538391

Global Navigation Satellite System Interferometric reflectance measurement (GNSS-IR) is a new remote sensing technology which uses satellite reflectance signals for monitoring. Aiming at the problems that the current GNSS-IR altimetry in land scenes is rarely applied and the accuracy of the traditional method is low under the reflection surface with high roughness, the traditional GNSS-IR altimetry is improved based on the local weighted regression method. A general navigation receiver method is proposed here, and does not need to use expensive special receiver or geodesic receiver. The local weighted regression method is used to separate the reflected signals to solve the problem of low local fitting accuracy of traditional methods when dealing with complex SNR changes in land scenes. The normalized Lomb-Scargle is used for spectrum analysis to improve the stability when there are few valid observations. The simulation and test results show that the proposed method has a significant improvement in the measurement accuracy compared with the traditional GNSS-IR method in the high-roughness ground scene. The single satellite measurement accuracy can reach within 10cm, and the root mean square error of the dual-frequency and multi-satellite combined altimetry measurement result is 2.62cm. © 2022 IET Conference Proceedings. All rights reserved.

关键词： Reflection

来源：评论

学校读者我要写书评

暂无评论

A Generic Layer Pruning Method for Signal Modulation Recognition Deep Learning Models

引用

IEEE Transactions on Cognitive Communications and Networking 2024年

作者： Lu, Yao Zhu, Yutao Li, Yuqi Xu, Dongwei Lin, Yun Xuan, Qi Yang, Xiaoniu Zhejiang University of Technology Binjiang Institute of Artificial Intelligence Hangzhou310056 China Chinese Academy of Sciences Institute of Computing Technology Beijing China Harbin Engineering University College of Information and Communication Engineering Harbin China Zhejiang University of Technology Institute of Cyberspace Security College of Information Engineering Hangzhou China Peng Cheng Laboratory PCL Research Center of Networks and Communications Shenzhen518000 China Hangzhou310056 China Science and Technology on Communication Information Security Control Laboratory Jiaxing China

With the successful application of deep learning in communications systems, deep neural networks are becoming the preferred method for Automatic Modulation Recognition (AMR). Although these AMR models yield impressive results, they often come with high computational complexity and large model sizes, which hinders their practical deployment in communication systems. To address this challenge, we propose a novel layer pruning method, PSR. Specifically, we decompose the AMR model into several consecutive blocks, each containing consecutive layers with similar semantics. Then, we identify layers that need to be preserved within each block based on their contribution. Finally, we reassemble the pruned blocks and fine-tune the compact model. Extensive experiments on five datasets demonstrate the efficiency and effectiveness of PSR over a variety of state-of-the-art baselines, including layer pruning and channel pruning methods. © 2015 IEEE.

关键词： Signal modulation

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：