检索结果-内蒙古大学图书馆

IEEE International Conference on Communications in China Workshops (ICCC)

作者： Xuguo Jiao Hao Luo Liuyang Jiang Lin Wang Xin Wang Zuqiang Huang State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China School of Information and Control Engineering Qingdao University of Technology Qingdao China Zhejiang Windey Co. Ltd. Hangzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Shandong Academy of Sciences Qilu University of Technology Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of Civil Engineering Zhengzhou University Zhengzhou China

ISBN: (数字)9798350377675

ISBN: (纸本)9798350377682

Recently, offshore wind power has rapidly developed due to its low environmental interference and abundant wind resources. However, due to its remote geographical location and high demand for communication infrastructure, off-shore wind turbines (OWTs) are vulnerable to potential threats from false data injection (FDI) attack. FDI attack can interfere with active power control strategies by tampering with the rotor speed data measured by sensors and pose a threat to the stability of the power grid. To ensure that OWTs can accurately track the active power instructions set by wind farm's control center under FDI attack, this paper proposes a rotor speed control (RSC) strategy based on Kalman filtering technology (RSC- KF). This strategy can estimate the rotor speed of the wind turbine in real-time, and then a residual detection and compensation mechanism is designed to effectively detect and correct attacked rotor speed information caused by FDI attack. Further, based on the corrected rotor speed, the RSC method is developed, which can flexibly switch control strategies according to different rotor speed values, ensuring the efficient operation of OWTs under different wind speed conditions. The proposed approach's effectiveness is proved via simulations conducted on the OpenFAST platform.

关键词： Filtering Velocity control Power control Rotors Power system stability Stability analysis Real-time systems Wind turbines Kalman filters Cyberattack

来源：评论

学校读者我要写书评

暂无评论

DifAttack: Query-Efficient Black-Box Attack via Disentangled Feature Space

arXiv

引用

arXiv 2023年

作者： Liu, Jun Zhou, Jiantao Zeng, Jiandian Tian, Jinyu State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China Institute of Artificial Intelligence and Future Networks Beijing Normal University China School of Computer Science and Engineering Macau University of Science and Technology China

This work investigates efficient score-based black-box adversarial attacks with a high Attack Success Rate (ASR) and good generalizability. We design a novel attack method based on a Disentangled Feature space, called DifAttack, which differs significantly from the existing ones operating over the entire feature space. Specifically, DifAttack firstly disentangles an image's latent feature into an adversarial feature and a visual feature, where the former dominates the adversarial capability of an image, while the latter largely determines its visual appearance. We train an autoencoder for the disentanglement by using pairs of clean images and their Adversarial Examples (AEs) generated from available surrogate models via white-box attack methods. Eventually, DifAttack iteratively optimizes the adversarial feature according to the query feedback from the victim model until a successful AE is generated, while keeping the visual feature unaltered. In addition, due to the avoidance of using surrogate models' gradient information when optimizing AEs for black-box models, our proposed DifAttack inherently possesses better attack capability in the open-set scenario, where the training dataset of the victim model is unknown. Extensive experimental results demonstrate that our method achieves significant improvements in ASR and query efficiency simultaneously, especially in the targeted attack and open-set scenarios. The code is available at https://***/csjunjun/***. © 2023, CC BY-NC-ND.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

RLink: Accelerate On-Device Deep Reinforcement Learning with Inference Knowledge at the Edge

RLink: Accelerate On-Device Deep Reinforcement Learning with...

引用

International Conference on Mobile Ad-hoc and Sensor networks, MSN

作者： Tianyu Zeng Xiaoxi Zhang Daipeng Feng Jingpu Duan Zhi Zhou Xu Chen School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Institute of Future Networks Southern University of Science and Technology Shenzhen China Department of Communications Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9798350358261

ISBN: (纸本)9798350358278

Deep reinforcement learning (DRL) has been a successful paradigm in machine learning that enables solving complex control problems at the human level. However, the sampling and training efficiency of state-of-the-art DRL frameworks can not satisfy the stringent latency and throughput requirements of today’s mobile environments. Existing distributed and offline reinforcement learning algorithms along with the libraries for training acceleration are inherently designed for DRL tasks performed in the cloud rather than on distributed mobile devices, on which the computing resources are highly constrained, heterogeneous, and possibly dynamically changing. With the rise of edge computing and intelligence services, this paper presents RLink, a novel distributed training library to accelerate on-device deep reinforcement learning with inference knowledge at the edge. We leverage knowledge distillation to realize lightweight interaction between our on-device training task and the remote models that can provide inference knowledge. In this way, RLink is designed to be event-driven and agnostic to heterogeneous deep reinforcement learning algorithms and libraries. To tackle the communication bottleneck, a novel asynchronous sampling algorithm is proposed to facilitate real-time training in RLink. Tuned for unstable-connected mobile devices, RLink is robust and efficient by using a semantic-aware communication pipeline for lossless data compression. Extensive experimental results show that, compared with state-of-the-art algorithms and libraries, RLink can accelerate deep reinforcement learning at the edge with up to decuple speedups in convergence and ideal computational performance.

关键词： Training Performance evaluation Computational modeling Pipelines Deep reinforcement learning Libraries Inference algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-ID2R: An Intelligent Device Disaster Recovery Mechanism in Multipath Scenarios

Multi-ID2R: An Intelligent Device Disaster Recovery Mechanis...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Wenxiao Wang Yuyang Zhang Ping Dong Xiaojiang Du Chengxiao Yu Hongke Zhang Nadjib Aitsaadi School of Electronic and Information Engineering Beijing Jiaotong University P. R. China Dept. of New Networks Pengcheng Laboratory Shenzhen China Dept. of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA Université Paris-Saclay UVSQ DAVID France

ISBN: (数字)9798350351255

ISBN: (纸本)9798350351262

At present, multipath transmission realized by multi-interface devices and bandwidth aggregation technology meets user demand for high-bandwidth communication in 6G wireless networks. However, multipath transmission systems face the threat of single-point failure by multi-interface servers themselves. Existing solutions for such failure are not suitable for multipath transmission scenarios, and this seriously limits the ability to bandwidth aggregation and reduces the reliability and invulnerability of the multipath transmission system in 6G wireless networks. In this paper, we propose a novel Intelligent Device Disaster Recovery (Multi-ID 2 R) mechanism to solve the single-point failure in multipath and aggregated environments for the first time. In particular, we establish the Multi-Dimensional Parameter Joint Analysis model (MDPJA) and propose an algorithm for judging the running state of multi-interface devices. The algorithm takes into account the different network parameters of the paths, including delay, packet loss rate, and throughput. Moreover, an intelligent switching mechanism based on service quality is designed. Multi-ID 2 R comprehensively considers the characteristics of the business and the current parameters of multipath networks to determine the moment of switching to flexibly adjust switching strategies. Finally, we deploy the mechanism on multi-interface servers in actual networks. Experiments demonstrate that, compared with Virtual Router Redundancy Protocol, Gateway Load Balancing Protocol, and Hot Standby Router Protocol, Multi-ID 2 R effectively improves the reliability and invulnerability of multi-interface server in 6G wireless networks.

关键词： 6G mobile communication Wireless networks Disasters Switches Bandwidth Throughput Routing protocols Servers Reliability Standards

来源：评论

学校读者我要写书评

暂无评论

Data security and privacy computing in artificial intelligence

引用

Journal of Information and Intelligence 2024年第2期2卷 99-101页

作者： Dengguo Feng Hui Li Rongxing Lu Zheli Liu Jianbing Ni Hui Zhu Institute of Software Academy of SciencesBeijing 100190China State Key Laboratory of Integrated Services Networks School of Cyber EngineeringXidian UniversityXi’an 710071China Faculty of Computer Science University of New BrunswickFredericton E3B 5A3Canada College of Computer Science Nankai UniversityTianjin 300071China Department of Electrical and Computer Engineering Queen’s UniversityKingston K7L 3N6Canada

Artificial intelligence(AI)is a field of computer science dedicated to creating systems and algorithms that can perform tasks typically requiring human intelligence,such as learning,problem-solving,language understanding,and decision-making,contributing to a wide array of applications across diverse *** development of AI,such as machine learning and deep learning,has revolutionized data processing and *** transformation is rapidly changing human life and has allowed for many practical AI based applications,including biometric recognition,text/sentimental analysis,and attack detection in the fields of health care,finance,autonomous vehicles,personalized ***,the potential benefits of AI are hindered by issues,such as insecurity and privacy violations in data processing and communication.

关键词： such has finance

来源：评论

学校读者我要写书评

暂无评论

GrayINT – Detection and Localization of Gray Failures via Hybrid In-band Network Telemetry

GrayINT – Detection and Localization of Gray Failures via H...

引用

Asia-Pacific Network Operations and Management Symposium (APNOMS)

作者： Kuichao Zhang Wei Su Huiling Shi Kai Zhang Wei Zhang 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 Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China National Engineering Laboratory for Next Generation Internet Interconnection Devices (NGIID) School of Electronics and Information Engineering Beijing Jiaotong University Beijing China

As the underlying infrastructure, data center networks (DCNs) provide an important platform for cloud computing and next-generation networks. However, due to the influence of many factors, such as network, hardware, and software, various failures may occur during the operation of the DCN, which brings great challenges to its reliability. Particularly, a more insidious type of network failure, known as gray failure, presents a significant threat to system stability. In response to this challenge, in this work, we propose GrayINT, a gray failure detection and localization system that leverages In-band Network Telemetry (INT) technology to monitor all paths within the data center network in real-time. To verify the feasibility of our design, we build a fat-tree data center network on a virtual network testbed. A large number of experimental results demonstrate that our system can monitor device and link status in real-time, achieving gray failure detection and localization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security and Privacy in Federated Learning using Low-Dimensional Update Representation and Proximity-Based Defense

arXiv

引用

arXiv 2024年

作者： Li, Wenjie Fan, Kai Zhang, Jingyuan Li, Hui Lim, Wei Yang Bryan Yang, Qiang The State Key Laboratory of Integrated Service Networks Xidian University Xi’an710071 China The College of Computing and Data Science Nanyang Technological University 639798 Singapore The Department of Computer Science and Engineering Hong Kong University of Science and Technology 999077 Hong Kong

Federated Learning (FL) is a promising privacy-preserving machine learning paradigm that allows data owners to collaboratively train models while keeping their data localized. Despite its potential, FL faces challenges related to the trustworthiness of both clients and servers, particularly against curious or malicious adversaries. In this paper, we introduce a novel framework named Federated Learning with Low-Dimensional Update Representation and Proximity-Based defense (FLURP), designed to address privacy preservation and resistance to Byzantine attacks in distributed learning environments. FLURP employs LinfSample method, enabling clients to compute the l∞ norm across sliding windows of updates, resulting in a Low-Dimensional Update Representation (LUR). Calculating the shared distance matrix among LURs, rather than updates, significantly reduces the overhead of Secure MultiParty Computation (SMPC) by three orders of magnitude while effectively distinguishing between benign and poisoned updates. Additionally, FLURP integrates a privacy-preserving proximity-based defense mechanism utilizing optimized SMPC protocols to minimize communication rounds. Our experiments demonstrate FLURP’s effectiveness in countering Byzantine adversaries with low communication and runtime overhead. FLURP offers a scalable framework for secure and reliable FL in distributed environments, facilitating its application in scenarios requiring robust data management and security. Copyright © 2024, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Impact of Hardware Impairments on Covert Cooperative Backscatter Communications

Impact of Hardware Impairments on Covert Cooperative Backsca...

引用

IEEE Conference on Global Communications (GLOBECOM)

作者： Huan Li Yinghui Ye Lu Lv Guangyue Lu Naofal Al-Dhahir Shaanxi information communication network and security Laboratory Xi'an University of Posts and Telecommunications Xi'an China State Key Laboratory of Integrated Services Networks Xidian University Xi'an China Department of Electrical and Computer Engineering The University of Texas at Dallas Richardson TX USA

In this paper, we investigate a covert cooperative backscatter communication (BackCom) network under residual hardware impairments (RHIs) that are unavoidable in practical radio frequency transceivers and may have an impact on the communication covertness and reliability. By exploiting the availability of statistical channel state information, we derive analytic expressions for the eavesdropper's detection error probability (DEP) and system outage probability (SOP) to evaluate the system covertness and communication reliability, respectively. Using the derived results, we prove that RHIs can improve the communication covertness but significantly degrade the outage performance. We also show that under RHIs and extremely high transmit signal-to-noise levels, the system outage performance has a non-zero asymptote, while the DEP still approaches one, similar to the scenario with perfect hardware. computer simulations corroborate our analytical results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Terabit Ultra-high-speed NFDM Transmission over G.654E Fiber with 103Gbaud Probabilistic Shaped 64QAM Signals

Terabit Ultra-high-speed NFDM Transmission over G.654E Fiber...

引用

Conference on Lasers and Electro-Optics (CLEO)

作者： Xinyu Chen Xiansong Fang Xiang Cai Lingjun Zhou Chao Li Zhixue He Fan Zhang State Key Laboratory of Advanced Optical Communication System and Networks Frontiers Science Center for Nano-Optoelectronics School of Electronics Peking University Beijing China School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China

We experimentally demonstrate a record ultra-high-speed 1.004 Tb/s dual-polarization NFDM transmission system over 300 km G.654E fiber with probabilistic shaped 64QAM signals, achieving a spectral efficiency at 7.65 b... 详细信息

ISBN: (纸本)9781957171258

关键词： Frequency division multiplexing Optical amplifiers Optical signals Quadrature amplitude modulation Signal processing Signal transmission

来源：评论

学校读者我要写书评

暂无评论

1080-Nm dispersion-managed figure-8 fiber laser with a phase-biased nonlinear amplifying loop mirror

引用

Optics Communications 2025年 589卷

作者： Gao, Kong Dong, Li Pan, Zhongben Chu, Hongwei Pan, Han Wang, Aimin Liu, Yizhou Li, Dechun School of Information Science and Engineering Shandong University Qingdao266237 China College of Physics Science Qingdao University Qingdao266071 China State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Engineering and Computer Science Peking University Beijing100871 China Center for Optics Research and Engineering Shandong University Qingdao266237 China

We report on a dispersion-managed figure-8 fiber laser with a phase-biased nonlinear amplifying loop mirror (NALM). This figure-8 fiber laser incorporated a non-reciprocal phase bias and an unparallel grating pair in the optical cavity, enabling a self-starting mode-locking state with good wavelength tunability. Numerical simulations were employed to simulate the optical dynamics of the mode-locking laser pulse inside the fiber cavity, indicating the evolution of the spectral bandwidth, pulse duration, and pulse energy at different intracavity positions. A 26.4-MHz, 1080.3-nm mode-locking laser was realized from experiment based on the numerical results. The output powers delivered from the polarization beam splitter (PBS) and the fiber output coupler (FOC) were 1.04 mW and 0.15 mW, with the corresponding pulse durations of 0.97 ps and 0.84 ps, respectively. The integrated relative intensity noise (RIN) of the 1080.3-nm mode-locking laser was 0.059 % [10 Hz, 1 MHz]. The central wavelength of the figure-8 mode-locking fiber laser can be further tuned from 1040.8 nm to 1083.6 nm, based on the intracavity optical spectral filter introduced by the grating pair. This work can provide a reliable seed source for high-energy fiber laser systems. © 2025 Elsevier B.V.

关键词： Laser mirrors

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：