检索结果-内蒙古大学图书馆

International Conference on Dependable systems and Networks (DSN)

作者： Yu Zhao Wenjie Xue Weijie Chen Weizhong Qiang Deqing Zou Hai Jin National Engineering Research Center for Big Data Technology and System Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Jinyinhu Laboratory Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350341058

ISBN: (纸本)9798350341065

Over the past decade, various methods for detecting side-channel leakage have been proposed and proven to be effective against CPU side-channel attacks. These methods are valuable in assisting developers to identify and patch side-channel vulnerabilities. Nevertheless, recent research has revealed the feasibility of exploiting side-channel vulnerabilities to steal sensitive information from GPU applications, which are beyond the reach of previous side-channel detection methods. Therefore, in this paper, we conduct an in-depth examination of various GPU features and present Owl, a novel side-channel detection tool targeting CUDA applications on NVIDIA GPUs. Owl is designed to detect and locate side-channel leakage in various types of CUDA applications. When tracking the execution of CUDA applications, we design a hierarchical tracing scheme and extend the A-DCFG (Attributed Dynamic Control Flow Graph) to address the massively parallel execution in CUDA, ensuring Owl's detection scalability. After completing the initial assessment and filtering, we conduct statistical tests on the differences in program traces to determine whether they are indeed caused by input variations, subsequently facilitating the positioning of side-channel leaks. We evaluate Owl's capability to detect side-channel leaks by testing it on Libgpucrypto, PyTorch, and nvJPEG. Meanwhile, we verify that our solution effectively handles a large number of threads. Owl has successfully identified hundreds of leaks within these applications. To the best of our knowledge, we are the first to implement side-channel leakage detection for general CUDA applications.

关键词： Target tracking Statistical analysis Filtering Scalability Graphics processing units Side-channel attacks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Learning the continuous-time optimal decision law from discrete-time rewards

引用

national science Open 2024年第5期3卷 130-147页

作者： Ci Chen Lihua Xie Kan Xie Frank Leroy Lewis Yilu Liu Shengli Xie School of Automation Guangdong University of TechnologyGuangdong Key Laboratory of IoT Information TechnologyGuangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore 111 Center for Intelligent Batch Manufacturing Based on IoT Technology Guangzhou 510006China UTA Research Institute the University of Texas at ArlingtonFort Worth 76118USA Department of Electrical Engineering and Computer Science University of TennesseeKnoxville 37996USA Oak Ridge National Laboratory Oak Ridge 37830USA Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou 510006China

The concept of reward is fundamental in reinforcement learning with a wide range of applications in natural and social *** an interpretable reward for decision-making that largely shapes the system's behavior has always been a challenge in reinforcement *** this work,we explore a discrete-time reward for reinforcement learning in continuous time and action spaces that represent many phenomena captured by applying physical *** find that the discrete-time reward leads to the extraction of the unique continuous-time decision law and improved computational efficiency by dropping the integrator operator that appears in classical results with integral *** apply this finding to solve output-feedback design problems in power *** results reveal that our approach removes an intermediate stage of identifying dynamical *** work suggests that the discrete-time reward is efficient in search of the desired decision law,which provides a computational tool to understand and modify the behavior of large-scale engineering systems using the optimal learned decision.

关键词： continuous-time state and action decision law learning discrete-time reward dynamical systems reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Data-driven modeling fast-slow coupling delayed dynamics using noisy data and sparse enhancement 5

Data-driven modeling fast-slow coupling delayed dynamics usi...

引用

5th International Conference on Industrial Artificial Intelligence, IAI 2023

作者： Tang, Huifang Wu, Yuqiang Dong, Yingming Cheng, Cheng Li, Xiuting Huazhong Agricultural University College of Science Wuhan China Yunnan Mechanical Research and Design Institute of Machinery Research Institute Group Yunnan Key Laboratory of Mechatronics Applied Technology Yunnan China Ministry of Education of China Huazhong University of Science and Technology Autonomous Intelligent Unmanned System Engineering Research Center Wuhan430074 China Huazhong University of Science and Techonology School of Artificial Intelligence and Automation Wuhan430074 China

ISBN: (纸本)9798350325294

In this work, we focus on fast-slow delayed dynamical systems, which are usually described by coupled delayed differential equations with two-time scales. The purpose of this article is to propose a data-driven discovery method to identify the fast-slow delayed differential equations from noisy measurements. The proposed method blends delay dictionary-based sparse identification of nonlinear dynamics (SINDy) framework and a fixed interval sampling strategy. Specifically, we leverage the SINDy methodology to describe the fast-slow delayed differential equations by a few active terms of a large dictionary containing the delay terms and many candidate nonlinear basis functions. To identify the active terms and the corresponding coefficients, a sequential thresholded re-weighted 2 least squares algorithm is used to solve the resulting sparse regression problem to enhance the sparsity. Once a sparse model with fixed delay is selected, the proposed method further estimates the delayed time by calculating the reconstruction error from the sparse model until the one that makes the reconstruction error minimum. We verify the effectiveness of the proposed method with several classical fast-slow coupling delayed systems. The experimental results show that the proposed method can well automate the fast-slow delayed differential equations from noisy data and the delayed terms also can be detected accurately. © 2023 IEEE.

关键词： Dynamical systems

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature 39

Breaking Barriers in Physical-World Adversarial Examples: Im...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China

ISBN: (纸本)157735897X

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model's incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method's superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method's effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Characterization of the Oxide Film and Deuterium Permeation Behavior of Cocrmnfeni High Entropy Alloy Oxidized at 550 °C for 24 Hours

SSRN

引用

SSRN 2023年

作者： Yin, Chunyu Li, Wenxuan Qiu, Xi Luo, Bin Huang, Hongtao Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China Sino-French Institute of Nuclear Energy and Technology Sun Yat-Sen University Zhuhai519082 China

High entropy alloys have become potential candidate materials for high temperature nuclear reactor due to its high strength, high hardness, excellent corrosion resistance and radiation resistance, therefore the compatibility of hydrogen isotopes with HEAs becomes a key issue that has attracted a lot of attentions. The deuterium permeation behavior of the CoCrMnFeNi high entropy alloy after oxidation at 550 °C for 24 h was investigated by gas-phase deuterium permeation testing, SEM, X-ray diffraction methods in this paper. The results show that a dense oxide film with a thickness of about 1μm was formed on the surface of the sample after oxidation. The outer layer of the oxide film is rich in Mn2O3 and the inner layer is rich in Cr2O3. The deuterium permeability of the CoCrMnFeNi sample after oxidation was reduced by an order of magnitude and was 1/7-1/17 times as high as that for the unoxidized one. © 2023, The Authors. All rights reserved.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Optimal design of water immersion sensor layout for helicopter emergency flotation system based on the nsgaII algorithm 2

Optimal design of water immersion sensor layout for helicopt...

引用

2023 2nd International Conference on Aerospace and Control Engineering, ICoACE 2023

作者： Wang, Bingqian Wang, Zhe Sun, Zhi Hou, Bin College of Civil Aviation Nanjing University of Aeronautics and Astronautics Nanjing211106 China Key Laboratory of Aircraft Environment Control and Life Support MIIT Nanjing University of Aeronautics and Astronautics Nanjing210016 China Key Laboratory of Civil Aviation Emergency Science and Technology CAAC Nanjing University of Aeronautics and Astronautics Nanjing211106 China Environment Control System Research Department COMAC Shanghai Aircraft Design & Research Institute Shanghai201210 China

Aiming at the problem of sensor layout in an emergency flotation system, a sensor layout scheme design method based on the NSGAII method is proposed. The ALE method is used to simulate the water landing process of the helicopter on different pitch angles. The logic relationship of the 4/5 voting system is used to improve the sensor module reliability. Further, a mathematical model of layout scheme is established to maximize the detection coverage and minimize the force acting on the water immersion sensors when helicopter emergent water landing as the objective functions. Based on the mathematical model of water immersion sensor layout optimization constructed in this paper, NSGAII is used to solve this problem. The results show that the proposed method can realize the optimization of the layout of the water immersion sensor, the detection coverage of optimized schemes is increased by 3.26% on average compared with the value under the original scheme, and the force acting on the water immersion sensors is reduced by 61.86%. © Published under licence by IOP Publishing Ltd.

关键词： Flotation

来源：评论

学校读者我要写书评

暂无评论

Towards High-resolution 3D Anomaly Detection via Group-Level Feature Contrastive Learning 24

Towards High-resolution 3D Anomaly Detection via Group-Level...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Zhu, Hongze Xie, Guoyang Hou, Chengbin Dai, Tao Gao, Can Wang, Jinbao Shen, Linlin National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong Department of Intelligent Manufacturing CATL Ningde China Fuzhou Fuyao Institute for Advanced Study Fuyao University of Science and Technology Fuzhou China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China

ISBN: (纸本)9798400706868

High-resolution point clouds (HRPCD) anomaly detection (AD) plays a critical role in precision machining and high-end equipment manufacturing. Despite considerable 3D-AD methods that have been proposed recently, they still cannot meet the requirements of the HRPCD-AD task. There are several challenges: i) It is difficult to directly capture HRPCD information due to large amounts of points at the sample level;ii) The advanced transformer-based methods usually obtain anisotropic features, leading to degradation of the representation;iii) The proportion of abnormal areas is very small, which makes it difficult to characterize. To address these challenges, we propose a novel group-level feature-based network, called Group3AD, which has a significantly efficient representation ability. First, we design an Intercluster Uniformity Network (IUN) to present the mapping of different groups in the feature space as several clusters, and obtain a more uniform distribution between clusters representing different parts of the point clouds in the feature space. Then, an Intracluster Alignment Network (IAN) is designed to encourage groups within the cluster to be distributed tightly in the feature space. In addition, we propose an Adaptive Group-Center Selection (AGCS) based on geometric information to improve the pixel density of potential anomalous regions during inference. The experimental results verify the effectiveness of our proposed Group3AD, which surpasses Reg3D-AD by the margin of 5% in terms of object-level AUROC on Real3D-AD. We provide the code and supplementary information on our website: https://***/M-3LAB/Group3AD. © 2024 ACM.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Representation Learning based and Interpretable reactor system Diagnosis Using Denoising Padded Autoencoder

arXiv

引用

arXiv 2022年

作者： Li, Chengyuan Qiu, Zhifang Yan, Zhangrui Li, Meifu Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu610213 China CNNC Key Laboratory on Nuclear Reactor Thermal Hydraulics Technology Nuclear Power Institute of China Chengdu610213 China

With the mass construction of Gen III nuclear reactors, it is a popular trend to use deep learning (DL) techniques for fast and effective diagnosis of possible anomalies to ensure the safety of reactor systems under accidents. To improve the robustness of diagnostic model to crippled and noisy monitoring data, and to enhance the interpretability of the diagnostic outputs, this paper focuses on three aspects. First, a novel Denoising Padded Autoencoder (DPAE) model is proposed for representation extraction of monitoring data, and such representation extractor is effective on disturbed data with signal-to-noise ratios up to 25.0 and monitoring data missing up to 40.0%. Secondly, a diagnostic paradigm using DPAE encoder followed by shallow statistical learning algorithms is proposed, and such stepwise diagnostic approach is tested on disturbed datasets with 41.8% and 80.8% higher classification and regression task evaluation metrics, in comparison with the end-to-end diagnostic approaches. Finally, a hierarchical interpretation algorithm using SHAP and feature ablation is presented to analyze the importance of the input monitoring parameters and validate the effectiveness of the high importance parameters. The results of this study inform the development of robust, interpretable, intelligent reactor anomaly diagnosis systems in situations with high safety requirements. Copyright © 2022, The Authors. All rights reserved.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Simulation and analysis of multi-frequency signal superposition with scattering center model

Simulation and analysis of multi-frequency signal superposit...

引用

2020 International Conference on Electronics, Communications and Information technology, CECIT 2020

作者： Yang, R.P. Wang, X. Liu, C.H. Liu, Y. Liu, Y. National Key Laboratory of Antenna and Microwave Technology Xidian University Xi'an Shaan Xi China National Key Laboratory of Science and Technology on Information System Security Beijing China

In this paper, the superposition of time domain scattering signal with different frequency is analyzed. Simulation results shows that the peak value of the sum signal is able to be approximately estimated from scattering center model. Besides, the results show that energy of multi-frequency scattering signal has the potential to accumulate in time domain, which might help to design new kinds of signal to recognize target and resist noise at the same time. © Published under licence by IOP Publishing Ltd.

关键词： Signal processing

来源：评论

学校读者我要写书评

暂无评论

Identification of the non-stationarity of extreme temperature events and teleconnections with solar activity and large-scale atmospheric circulation: A case study in the Yangtze River Economic Belt

引用

Journal of Earth science 2024年

作者： Lin Zhang Jingyun Ling Shengzhi Huang Hongbin Zhan Yi Wu Menggui Jin Qiang Huang State Key Laboratory of Eco-hydraulics in Northwest Arid Region， Xi'an University of Technology College of Design and Engineering， National University of Singapore Yinshanbeilu Grassland Eco-Hydrology National Observation and Research Station， China Institute of Water Resources and Hydropower Research Department of Geology and Geophysics， Texas A&M University， College Station School of Earth System Science， Tianjin University School of Environmental Studies， China University of Geosciences

In recent decades， extreme climate events have become a major problem worldwide. To understand the uncertainty in the response of extreme events to global warming， regional assessments are required for various climatic and geographic regions. The spatiotemporal distribution of extreme temperature events in the Yangtze River Economic Belt (YREB) from 1960 to 2019， including interannual changes and their teleconnections with solar activity and large-scale atmospheric circulation， were analyzed using eight indices of extreme temperature events. Over the past six decades， the climate in the YREB region has seen a warming trend， characterized by an increase in extreme warm events and a decrease in extreme cold events. The extreme temperature indices exhibit strong spatial variability. The warm extremes display a significant upward trend across the YREB， while cold extremes are primarily concentrated in the western part of the region. In recent decades， both warm and cold extremes have significant interannual variations， and these events predominantly oscillate over periods of less than four years. After 1985， the relationship between El Ni?o-Southern Oscillation (ENSO)， Arctic Oscillation (AO)， Pacific Decadal Oscillation (PDO) and extreme temperature events has changed significantly compared with pre-1985， and the direction of the phase angle can determine the positive and negative effects of the two time-series. ENSO， AO and PDO mainly have positive impacts on extreme temperature events， with ENSO and AO exerting greater impacts than PDO. In contrast， solar activity mainly has a negative impact on these events. Furthermore， the notable interdecadal changes in extreme temperature events， especially warm extremes， may be caused by the shift in the PDO phase. Therefore， the results of the study are important for the YREB region to take effective measures to mitigate the potential impacts of human activities on regional warming.

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：