检索结果-内蒙古大学图书馆

IEEE International Conference on Robotics and Automation (ICRA)

作者： ShouGuang Wang MengChu Zhou MengDi Gan Dan You Yue Li School of Information & Electronic Engineering Zhejiang Gongshang University Hangzhou China State Key Laboratory for Manufacturing Systems Engineering Xi'an Jiaotong University Xi'an China MoE Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China Department of Electrical and Computer Engineering New Jersey Institute of Technology Newark NJ USA

ISBN: (纸本)9781479969241

Reachability is an important dynamic property of Petri nets. Its determination given an unbounded net and initial marking has remained an open problem since 1960s. Due to its extreme difficulty, a great deal of research has been focused on some subclasses of unbounded nets. For arbitrary ones, this work intends to propose a new reachability tree (NRT), which consists of only but all reachable markings from its initial marking. Furthermore, an NRT-based method to decide deadlocks of unbounded nets is presented. An example is provided to show the new results.

关键词： system recovery Petri nets Manufacturing systems Solids Gallium nitride Embedded systems

来源：评论

学校读者我要写书评

暂无评论

AIBench Training: Balanced Industry-Standard AI Training Benchmarking

AIBench Training: Balanced Industry-Standard AI Training Ben...

引用

IEEE International Symposium on Performance Analysis of systems and Software

作者： Fei Tang Wanling Gao Jianfeng Zhan Chuanxin Lan Xu Wen Lei Wang Chunjie Luo Zheng Cao Xingwang Xiong Zihan Jiang Tianshu Hao Fanda Fan Fan Zhang Yunyou Huang Jianan Chen Mengjia Du Rui Ren Chen Zheng Daoyi Zheng Haoning Tang Kunlin Zhan Biao Wang Defei Kong Minghe Yu Chongkang Tan Huan Li Xinhui Tian Yatao Li Junchao Shao Zhenyu Wang Xiaoyu Wang Jiahui Dai Hainan Ye University of Chinese Academy of Sciences State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Alibaba International Open Benchmark Council (BenchCouncil) Baidu Tencent *** NetEase ByteDance Zhihu Lenovo Paypal Moqi Microsoft Research Asia *** CloudTa Intellifusion

Earlier-stage evaluations of a new AI architecture/system need affordable AI benchmarks. Only using a few AI component benchmarks like MLPerf alone in the other stages may lead to misleading conclusions. Moreover, the learning dynamics are not well understood, and the benchmarks' shelf-life is short. This paper proposes a balanced benchmarking methodology. We use real-world benchmarks to cover the factors space that impacts the learning dynamics to the most considerable extent. After performing an exhaustive survey on Internet service AI domains, we identify and implement nineteen representative AI tasks with state-of-the-art models. For repeatable performance ranking (RPR subset) and workload characterization (WC subset), we keep two subsets to a minimum for affordability. We contribute by far the most comprehensive AI training benchmark suite. The evaluations show: (1) AIBench Training (v1.1) outperforms MLPerf Training (v0.7) in terms of diversity and representativeness of model complexity, computational cost, convergent rate, computation, and memory access patterns, and hotspot functions; (2) Against the AIBench full benchmarks, its RPR subset shortens the benchmarking cost by 64%, while maintaining the primary workload characteristics; (3) The performance ranking shows the single-purpose AI accelerator like TPU with the optimized TensorFlow framework performs better than that of GPUs while losing the latter's general support for various AI models. The specification, source code, and performance numbers are available from the AIBench homepage https://***/aibench-training/***.

关键词： Training Computational modeling Web and internet services Optical wavelength conversion Benchmark testing Software Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

A systematic view of leakage risks in deep neural network systems

TechRxiv

引用

TechRxiv 2021年

作者： Hu, Xing Liang, Ling Chen, Xiaobing Deng, Lei Ji, Yu Ding, Yufei Du, Zidong Guo, Qi Sherwood, Timothy Xie, Yuan State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Department of Electrical and Computer Engineering University of California Santa Barbara United States Department of Computer Science University of California Santa Barbara United States Tsinghua University China University of California Santa Barbara United States

As deep neural networks (DNNs) continue their reach into a wide range of application domains, the neural network architecture of DNN models becomes an increasingly sensitive subject, due to either intellectual property protection or risks of adversarial attacks. In observing the large gap between the architectural surfaces exploration and the model integrity study, this paper first presents the formulated schema of the model leakage risks. Then, we propose DeepSniffer, a learning-based model extraction framework, to obtain the complete model architecture information without any prior knowledge of the victim model. It is robust to architectural and system noises introduced by the complex memory hierarchy and diverse run-time system optimizations. Taking GPU platforms as a showcase, DeepSniffer performs model extraction by learning both the architecture-level execution features of kernels and the inter-layer temporal association information introduced by the common practice of DNN design. We demonstrate that DeepSniffer works experimentally in the context of an off-the-shelf Nvidia GPU platform running a variety of DNN models. The extracted models are directly helpful to the attempting of crafting adversarial inputs. The DeepSniffer project has been released in https://***/xinghu7788/DeepSniffer. © 2021, CC0.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Joint Entity and Relation Extraction Based on Prompt Learning and Multi-channel Heterogeneous Graph Enhancement

Joint Entity and Relation Extraction Based on Prompt Learnin...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Haiqing Lv Xiaohui Han Peipei Wang Wenbo Zuo Jing Guo Lijuan Xu 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 Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China Information Research Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Joint extraction of entity and relation is crucial in information extraction, aiming to extract all relation triples from unstructured text. However, current joint extraction methods face two main issues. Firstly, they rarely consider the semantic information of entity and relation labels, leading to models that fail to fully understand and utilize the rich semantics in these labels, thereby limiting their performance. Secondly, although table-filling methods are widely used, they focus only on the start or end positions and ignore deep interactions between tables, relying solely on word-level information. To address these issues, we propose the P-MHE framework based on prompt learning and multi-channel heterogeneous graph enhancement. First, we use prompt templates to construct semantic nodes for entity and relation type labels, initializing them along with words as nodes in a heterogeneous graph. We iteratively fuse these semantic nodes through a message-passing mechanism to obtain node representations suitable for entity and relation extraction tasks. Secondly, we design a multi-channel heterogeneous graph to model node relationships from different perspectives, enhancing feature interactions among different types of nodes. Finally, we aggregate the semantic node information of entity and relation type labels after iteration, constructing separate decoding tables for each entity and relation type to better adapt to their respective characteristics. We evaluated our model on four public datasets. Experimental results show that P-MHE outperforms existing models on multiple public datasets. Extensive additional experiments further validate the effectiveness of our model.

关键词： Training Adaptation models Limiting Fuses Semantics Natural languages Information retrieval Feature extraction Data mining Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Real-Time Task Scheduling for Joint Energy Efficiency Optimization in Data Centers

Real-Time Task Scheduling for Joint Energy Efficiency Optimi...

引用

IEEE Symposium on computers and Communications

作者： Youshi Wang Fa Zhang Rui Wang Yangguang Shi Hua Guo Zhiyong Liu Chinese Academy of Sciences (CAS) Institute of Computing Technology (ICT) Beijing China University of Chinese Academy of Sciences Beijing China ICT Key Laboratory of Intelligent Information Processing Beijing China Hong Kong University of Science and Technology Hong Kong China Technion - Israel Institute of Technology Haifa Israel State Grid Jingzhou Electric Power Company Jingzhou Hubei China ICT State Key Laboratory for Computer Architecture Beijing China

The high energy consumption has become one bottleneck in the development of the data centers (DCs), where the main energy consumers are the cooling system and the servers. Therefore, the joint optimization for the energy efficiency of the cooling system and the servers is a crucial problem, while most of previous works on energy saving only studies one of these two components in an isolated manner. In this paper, we propose a real-time strategy, rTCS (real-time Task Classification and Scheduling strategy), to jointly optimize the energy efficiency of these two components in the scenario where the tasks arrive dynamically. Strategy rTCS first labels the tasks to classify them according to their run time and end time with a time complexity of O(1) and a bounded space complexity. Then, rTCS schedules the tasks in real time based on their labels and the energy consumption model of the DC. Simulation results show that rTCS can effectively improve the energy efficiency of DCs.

关键词： Energy efficiency Data center Cooling system Task classification Real-time scheduling algorithm

来源：评论

学校读者我要写书评

暂无评论

The Power of Bamboo: On the Post-Compromise Security for Searchable Symmetric Encryption

arXiv

引用

arXiv 2024年

作者： Chen, Tianyang Xu, Peng Picek, Stjepan Luo, Bo Susilo, Willy Jin, Hai Liang, Kaitai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering China Cluster and Grid Computing Lab School of Computer Science and Technology China Huazhong University of Science and Technology Wuhan430074 China Digital Security Group Radboud University Nijmegen Netherlands Department of EECS Institute of Information Sciences The University of Kansas LawrenceKS United States Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia Faculty of Electrical Engineering Mathematics and Computer Science Delft University of Technology Delft2628 CD Netherlands

Dynamic searchable symmetric encryption (DSSE) enables users to delegate the keyword search over dynamically updated encrypted databases to an honest-but-curious server without losing keyword privacy. This paper studies a new and practical security risk to DSSE, namely, secret key compromise (e.g., a user’s secret key is leaked or stolen), which threatens all the security guarantees offered by existing DSSE schemes. To address this open problem, we introduce the notion of searchable encryption with key-update (SEKU) that provides users with the option of non-interactive key updates. We further define the notion of post-compromise secure with respect to leakage functions to study whether DSSE schemes can still provide data security after the client’s secret key is compromised. We demonstrate that post-compromise security is achievable with a proposed protocol called "Bamboo". Interestingly, the leakage functions of Bamboo satisfy the requirements for both forward and backward security. We conduct a performance evaluation of Bamboo using a real-world dataset and compare its runtime efficiency with the existing forward-and-backward secure DSSE schemes. The result shows that Bamboo provides strong security with better or comparable performance. © 2024, CC BY.

关键词： Bamboo

来源：评论

学校读者我要写书评

暂无评论

Distilled Transformers with Locally Enhanced Global Representations for Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Li, Qiufu Yu, Zitong Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Shenzhen518060 China Shenzhen Institute of Artificial Intelligence and Robotics for Society Guangdong Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Guangdong Shenzhen518060 China School of Computing and Information Technology Great Bay University Guangdong Dongguan523000 China

Face forgery detection (FFD) is devoted to detecting the authenticity of face images. Although current CNN-based works achieve outstanding performance in FFD, they are susceptible to capturing local forgery patterns generated by various manipulation methods. Though transformer-based detectors exhibit improvements in modeling global dependencies, they are not good at exploring local forgery artifacts. Hybrid transformer-based networks are designed to capture local and global manipulated traces, but they tend to suffer from the attention collapse issue as the transformer block goes deeper. Besides, soft labels are rarely available. In this paper, we propose a distilled transformer network (DTN) to capture both rich local and global forgery traces and learn general and common representations for different forgery faces. Specifically, we design a mixture of expert (MoE) module to mine various robust forgery embeddings. Moreover, a locally-enhanced vision transformer (LEVT) module is proposed to learn locally-enhanced global representations. We design a lightweight multi-attention scaling (MAS) module to avoid attention collapse, which can be plugged and played in any transformer-based models with only a slight increase in computational costs. In addition, we propose a deepfake self-distillation (DSD) scheme to provide the model with abundant soft label information. Extensive experiments show that the proposed method surpasses the state of the arts on five deepfake datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence for geoscience:Progress,challenges,and perspectives

引用

The Innovation 2024年第5期5卷 136-160,135页

作者： Tianjie Zhao Sheng Wang Chaojun Ouyang Min Chen Chenying Liu Jin Zhang Long Yu Fei Wang Yong Xie Jun Li Fang Wang Sabine Grunwald Bryan MWong Fan Zhang Zhen Qian Yongjun Xu Chengqing Yu Wei Han Tao Sun Zezhi Shao Tangwen Qian Zhao Chen Jiangyuan Zeng Huai Zhang Husi Letu Bing Zhang Li Wang Lei Luo Chong Shi Hongjun Su Hongsheng Zhang Shuai Yin Ni Huang Wei Zhao Nan Li Chaolei Zheng Yang Zhou Changping Huang Defeng Feng Qingsong Xu Yan Wu Danfeng Hong Zhenyu Wang Yinyi Lin Tangtang Zhang Prashant Kumar Antonio Plaza Jocelyn Chanussot Jiabao Zhang Jiancheng Shi Lizhe Wang Aerospace Information Research Institute Chinese Academy of SciencesBeijing 100094China School of Computer Science China University of GeosciencesWuhan 430078China State Key Laboratory of Mountain Hazards and Engineering Resilience Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengdu 610299China Key Laboratory of Virtual Geographic Environment(Ministry of Education of PRC) Nanjing Normal UniversityNanjing 210023China Data Science in Earth Observation Technical University of Munich80333 MunichGermany The National Key Laboratory of Water Disaster Prevention Yangtze Institute for Conservation and DevelopmentHohai UniversityNanjing 210098China Institute of Computing Technology Chinese Academy of SciencesBeijing 100190China School of Geographical Sciences Nanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Soil and Sustainable Agriculture Institute of Soil ScienceChinese Academy of SciencesNanjing 210008China Soil Water and Ecosystem Sciences DepartmentUniversity of FloridaPO Box 110290GainesvilleFLUSA Materials Science Engineering Program Cooperating Faculty Member in the Department of Chemistry and Department of Physics Astronomy University of CaliforniaCaliforniaRiversideCA 92521USA Institute of Remote Sensing and Geographical Information System School of Earth and Space SciencesPeking UniversityBeijing 100871China Key Laboratory of Computational Geodynamics University of Chinese Academy of SciencesBeijing 100049China International Research Center of Big Data for Sustainable Development Goals Beijing 100094China College of Geography and Remote Sensing Hohai UniversityNanjing 211100China Department of Geography The University of Hong KongHong Kong 999077SARChina Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Nanjing 210044China School of Environmental Science and Engineering Nanjing University of Information Science&TechnologyNanjing 210044China Collaborative Inno

This paper explores the evolution of geoscientific inquiry,tracing the progression from traditional physics-based models to modern data-driven approaches facilitated by significant advancements in artificial intelligence(AI)and data collection *** models,which are grounded in physical and numerical frameworks,provide robust explanations by explicitly reconstructing underlying physical ***,their limitations in comprehensively capturing Earth’s complexities and uncertainties pose challenges in optimization and real-world *** contrast,contemporary data-driven models,particularly those utilizing machine learning(ML)and deep learning(DL),leverage extensive geoscience data to glean insights without requiring exhaustive theoretical *** techniques have shown promise in addressing Earth science-related ***,challenges such as data scarcity,computational demands,data privacy concerns,and the“black-box”nature of AI models hinder their seamless integration into *** integration of physics-based and data-driven methodologies into hybrid models presents an alternative *** models,which incorporate domain knowledge to guide AI methodologies,demonstrate enhanced efficiency and performance with reduced training data *** review provides a comprehensive overview of geoscientific research paradigms,emphasizing untapped opportunities at the intersection of advanced AI techniques and *** examines major methodologies,showcases advances in large-scale models,and discusses the challenges and prospects that will shape the future landscape of AI in *** paper outlines a dynamic field ripe with possibilities,poised to unlock new understandings of Earth’s complexities and further advance geoscience exploration.

关键词： Earth utilizing landscape

来源：评论

学校读者我要写书评

暂无评论

Sample hardness based gradient loss for long-tailed cervical cell detection

arXiv

引用

arXiv 2022年

作者： Liu, Minmin Li, Xuechen Gao, Xiangbo Chen, Junliang Shen, Linlin Wu, Huisi Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence of Robotics of Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China University of California Irvine United States

Due to the difficulty of cancer samples collection and annotation, cervical cancer datasets usually exhibit a long-tailed data distribution. When training a detector to detect the cancer cells in a WSI (Whole Slice Image) image captured from the TCT (Thinprep Cytology Test) specimen, head categories (e.g. normal cells and inflammatory cells) typically have a much larger number of samples than tail categories (e.g. cancer cells). Most existing state-of-the-art long-tailed learning methods in object detection focus on category distribution statistics to solve the problem in the long-tailed scenario, without considering the "hardness" of each sample. To address this problem, in this work we propose a Grad-Libra Loss that leverages the gradients to dynamically calibrate the degree of hardness of each sample for different categories, and re-balance the gradients of positive and negative samples. Our loss can thus help the detector to put more emphasis on those hard samples in both head and tail categories. Extensive experiments on a long-tailed TCT WSI image dataset show that the mainstream detectors, e.g. RepPoints, FCOS, ATSS, YOLOF, etc. trained using our proposed Gradient-Libra Loss, achieved much higher (7.8%) mAP than that trained using cross-entropy classification loss. Copyright © 2022, The Authors. All rights reserved.

关键词： Cytology

来源：评论

学校读者我要写书评

暂无评论

Prototype Guided Personalized Federated Intrusion Detection system

Prototype Guided Personalized Federated Intrusion Detection ...

引用

Smart World Congress (SWC), IEEE

作者： Long Cheng Huiru Yan Hanlin Zhou Ying Wang Haichuan Tang Fang Fang State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources School of Control and Computer Engineering North China Electric Power University Beijing China Chinese Academy of Sciences Institute of Computing Technology Beijing China AI Lab of CRRC Academy Beijing China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Preventing network attacks and protecting user privacy are consistently hot research topics in the Internet of Things (IoT) and edge computing fields. Recent advancements in Federated Learning (FL) have shown promise in addressing these challenges. FL allows various clients to collaboratively build an intrusion detection system (IDS) without sharing their private data. However, most existing methods train a single intrusion detection model for all clients and assume that the training and test data distribution are identical, leading to unsatisfactory detection accuracy and generalization abilities in practice. To overcome these challenges, this paper introduces a prototype-guided personalized FL approach named PG-FedIDS. We propose two novel mechanisms within this method. Firstly, we utilize class prototypes as auxiliary information carriers to generate personalized models for each client, rather than generating a single global model as in previous works. Secondly, we propose a prototype-guided ensemble learning strategy, which can leverage the global knowledge in prototypes to enhance detection accuracy and generalization abilities for each client. We conduct extensive experiments on two benchmark datasets with different evaluation test settings. The results demonstrate that our PG-FedIDS achieves promising detection accuracy and consistently outperforms other FL baselines.

关键词： Training Privacy Accuracy Federated learning Image edge detection Prototypes Intrusion detection Data models Ensemble learning Internet of Things

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：