检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Liu, Xiaogeng Li, Minghui Wang, Haoyu Hu, Shengshan Ye, Dengpan Jin, Hai Wu, Libing Xiao, Chaowei 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 National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab China School of Cyber Science and Engineering Wuhan University China Arizona State University United States

Deep neural networks are proven to be vulnerable to backdoor attacks. Detecting the trigger samples during the inference stage, i.e., the test-time trigger sample detection, can prevent the backdoor from being triggered. However, existing detection methods often require the defenders to have high accessibility to victim models, extra clean data, or knowledge about the appearance of backdoor triggers, limiting their practicality. In this paper, we propose the test-time corruption robustness consistency evaluation (TeCo)1, a novel test-time trigger sample detection method that only needs the hard-label outputs of the victim models without any extra information. Our journey begins with the intriguing observation that the backdoor-infected models have similar performance across different image corruptions for the clean images, but perform discrepantly for the trigger samples. Based on this phenomenon, we design TeCo to evaluate test-time robustness consistency by calculating the deviation of severity that leads to predictions' transition across different corruptions. Extensive experiments demonstrate that compared with state-of-the-art defenses, which even require either certain information about the trigger types or accessibility of clean data, TeCo outperforms them on different backdoor attacks, datasets, and model architectures, enjoying a higher AUROC by 10% and 5 times of stability. Copyright © 2023, The Authors. All rights reserved.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

CMD: A Cache-assisted GPU Memory Deduplication Architecture

arXiv

引用

arXiv 2024年

作者： Zhao, Wei Feng, Dan Tong, Wei Wei, Xueliang Wu, Bing The Wuhan National Laboratory for Optoelectronics Key Laboratory of Information Storage System Engineering Research Center of Data Storage Systems and Technology Ministry of Education of China School of Computer Science and Technology Huazhong University of Science and Technology China

Massive off-chip accesses in GPUs are the main performance bottleneck, and we divided these accesses into three types: (1) Write, (2) Data-Read, and (3) Read-Only. Besides, We find that many writes are duplicate, and the duplication can be inter-dup and intra-dup. While inter-dup means different memory blocks are identical, and intra-dup means all the 4B elements in a line are the same. In this work, we propose a cache-assisted GPU memory deduplication architecture named CMD to reduce the off-chip accesses via utilizing the data duplication in GPU applications. CMD includes three key design contributions which aim to reduce the three kinds of accesses: (1) A novel GPU memory deduplication architecture that removes the inter-dup and inter-dup lines. As for the inter-dup detection, we reduce the extra read requests caused by the traditional read-verify hash process. Besides, we design several techniques to manage duplicate blocks. (2) We propose a cache-assisted read scheme to reduce the reads to duplicate data. When an L2 cache miss wants to read the duplicate block, if the reference block has been fetched to L2 and it is clean, we can copy it to the L2 missed block without accessing off-chip DRAM. As for the reads to intra-dup data, CMD uses the on-chip metadata cache to get the data. (3) When a cache line is evicted, the clean sectors in the line are invalidated while the dirty sectors are written back. However, most read-only victims are re-referenced from DRAM more than twice. Therefore, we add a full-associate FIFO to accommodate the read-only (it is also clean) victims to reduce the re-reference counts. Experiments show that CMD can decrease the off-chip accesses by 31.01%, reduce the energy by 32.78% and improve performance by 37.79%. Besides, CMD can improve the performance of memory-intensive workloads by 50.18%. © 2024, CC BY-NC-ND.

关键词： Cache memory

来源：评论

学校读者我要写书评

暂无评论

A Simultaneous Wireless Information and Power Transfer-based Multi-hop Clustering Routing Protocol for RF Energy Harvesting-Cognitive Radio Sensor Networks

Journal of Network Intelligence

引用

Journal of Network Intelligence 2023年第3期8卷 991-1007页

作者： Wang, Ji-Hong Su, Xi-Tong Ge, Yi-Yang Chen, Yeh-Cheng Key Laboratory of Modern Power System Simulation and Control & Renewable Energy Technology Ministry of Education Northeast Electric Power University China School of Electrical Engineering Northeast Electric Power University 169 Changchun Road Jilin132012 China Department of Computer Science University of California DavisCA001313 United States

Radio frequency energy harvesting (RF EH) and clustering are promising solutions to solve the energy constraint problem faced by cognitive radio sensor networks (CRSNs). However, study on clustering routing protocol design for RF EH-CRSNs is still in the initial stage, and there lacks of solutions for inter-cluster routing problem, which restricts the network scalability. In addition, unbalanced harvested energy and energy consumption may result in premature death of nodes in key position, which will significantly reduce the network performance. In this paper, a simultaneous wireless information and power transfer (SWIPT)-based multi-hop clustering routing protocol (SMCRP) is proposed for RF EH-CRSNs to well balance the residual energy distribution among nodes and postpone node death. Apart from the RF energy harvested from dedicated or ambi-ent energy sources, the energy obtained through intra-cluster and inter-cluster SWIPT is also considered to facilitate high-quality cluster heads selection, cluster formation and inter-cluster route establishment. Power splitting ratio is derived based on the residual energy of CRSNs nodes and their energy consumption to enable effective implementation of SWIPT in CRSNs. Simulation results show that SMCRP is effective in balancing the residual energy distribution among nodes and improving node sustainability. To be specific, compared with current clustering protocols, the network lifetime is extended by 64.07% while intra-cluster energy balance degree and network energy balance degree are improved by 15.1% and 7.82%, respectively. © 2023 ISSN 2414-8105 (Online).

关键词： Cognitive radio

来源：评论

学校读者我要写书评

暂无评论

NeuVSA: A Unified and Efficient Accelerator for Neural Vector Search

NeuVSA: A Unified and Efficient Accelerator for Neural Vecto...

引用

IEEE Symposium on High-Performance computer Architecture

作者： Ziming Yuan Lei Dai Wen Li Jie Zhang Shengwen Liang Ying Wang Cheng Liu Huawei Li Xiaowei Li Jiafeng Guo Peng Wang Renhai Chen Gong Zhang State Key Lab of Processors Institute of Computing TechnologyCAS University of Chinese Academy of Sciences School of Computer and Information Technology Shanxi University School of Computer Science Peking University Zhongguancun National Laboratory Beijing Key Lab of Network Data Science and Technology Institute of Computing Technology CAS Huawei Technologies Co. Ltd. China

ISBN: (数字)9798331506476

ISBN: (纸本)9798331506483

Neural Vector Search (NVS) has exhibited superior search quality over traditional key-based strategies for information retrieval tasks. An effective NVS architecture requires high recall, low latency, and high throughput to enhance user experience and cost-efficiency. However, implementing NVS on existing neural network accelerators and vector search accelerators is sub-optimal due to the separation between the embedding stage and vector search stage at both algorithm and architecture levels. Fortunately, we unveil that Product Quantization (PQ) opens up an opportunity to break separation. However, existing PQ algorithms and accelerators still focus on either the embedding stage or the vector search stage, rather than both simultaneously. Simply combining existing solutions still follows the beaten track of separation and suffers from insufficient parallelization, frequent data access conflicts, and the absence of scheduling, thus failing to reach optimal recall, latency, and throughput. To this end, we propose a unified and efficient NVS accelerator dubbed NeuVSA based on algorithm and architecture co-design philosophy. Specifically, on the algorithm level, we propose a learned PQ-based unified NVS algorithm that consolidates two separate stages into the same computing and memory access paradigm. It integrates an end-to-end joint training strategy to learn the optimal codebook and index for enhanced recall and reduced PQ complexity, thus achieving smoother acceleration. On the architecture level, we customize a homogeneous NVS accelerator based on the unified NVS algorithm. Each sub-accelerator is optimized to exploit all parallelism exposed by unified NVS, incorporating a structured index assignment strategy and an elastic on-chip buffer to alleviate buffer conflicts for reduced latency. All sub-accelerators are coordinated using a hardware-aware scheduling strategy for boosted throughput. Experimental results show that the joint training strategy improves recall

关键词： Training Quantization (signal) Philosophical considerations Graphics processing units computer architecture Throughput Vectors User experience system-on-chip Indexes

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection 41

Size-Invariance Matters: Rethinking Metrics and Losses for I...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright 2024 by the author(s)

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Over-the-RIS Modulation: A Reconfigurable Intelligent Surface Assisted Modulation Design 8

Over-the-RIS Modulation: A Reconfigurable Intelligent Surfac...

引用

8th International Conference on Communication, Image and Signal Processing, CCISP 2023

作者： Huang, Yiqian Zammit, Saviour Yang, Ping Xiao, Yue Zhang, Bo Chen, Jienan Xiang, Wei University of Electronic Science and Technology of China National Key Laboratory of Sciencec and Technology on Communications Sichuan China University of Malta Department of Communications and Computer Engineering Msida Malta 32806 Troops Beijing China School of Computing Engineering and Mathematical Sciences La Trobe University Melbourne Australia

ISBN: (纸本)9798350305838

This paper proposes an improved over the air modulation (OTAM) scheme by using the powerful reconfigurable intelligent surfaces (RISs), namely over-the-RIS modulation (ORM). In the design framework, we reconstruct multipath channels by employing several RISs to increase the attenuation difference between multiple paths. Compared with conventional OTAM, ORM can be used in more generic fading scenarios, e.g., channels with non-ideal attenuation properties, and thus extends the application of OTAM. Based on the Bayesian criterion, we propose an optimal likelihood detector for the ORM system and derive a closed-form expression of the bit error rate (BER). Furthermore, we investigate the phase optimization of the RISs to improve its BER and deduce its closed-form solutions. Simulation results are presented to show that the proposed ORM system can achieve a better BER performance and higher transmission rate than the conventional OTAM systems, especially for environments with severe shadow fading. © 2023 IEEE.

关键词： Bit error rate

来源：评论

学校读者我要写书评

暂无评论

Covert Communication in Satellite-Terrestrial systems with a Full-Duplex Receiver

Covert Communication in Satellite-Terrestrial Systems with a...

引用

2024 International Conference on Satellite Internet, SAT-NET 2024

作者： Guo, Zewei Sun, Ranran He, Ji Shen, Yulong Jiang, Xiaohong Future University Hakodate School of Systems Information Science Hakodate041-8655 Japan Hangzhou Institute of Technology Xidian University Hangzhou311200 China Xidian University School of Computer Science and Technology Xi'an710071 China Institute of Systems General Academy of Systems Engineering Academy of Military Sciences Beijing100101 China Xidian University Shaanxi Key Laboratory of Network and System Security Xi'an710071 China

ISBN: (纸本)9798350375176

This paper investigates the covert communication in a satellite-terrestrial system, including a satellite transmitter Alice, a terrestrial full-duplex receiver Bob and a terrestrial warden Willie. To help the covert transmission from Alice, the full-duplex Bob transmits the jamming signal to confuse Willie and also receives the signal from Alice simultaneously. To explore the fundamental covertness in such a system, we first provide theoretical modelings for satellite-terrestrial downlink, and the detection error probability of Willie. Based on these models, we then study the transmit power optimization for covert rate maximization. Finally, we present extensive numerical results to validate our theoretical analysis and to illustrate the impact of various system parameters on the maximum covert rate. © 2024 IEEE.

关键词： Satellite communication systems

来源：评论

学校读者我要写书评

暂无评论

ESNet: evolution and succession network for high-resolution salient object detection 24

ESNet: evolution and succession network for high-resolution ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Hongyu Liu Runmin Cong Hua Li Qianqian Xu Qingming Huang Wei Zhang Institute of Information Science Beijing Jiaotong University & Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University & Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature; the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HeavyTracker: An Efficient Algorithm for Heavy-Hitter Detection in High-Speed Networks

HeavyTracker: An Efficient Algorithm for Heavy-Hitter Detect...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Jiakun Yu Yu-E Sun He Huang Yang Du Guoju Gao Hongli Xu Shigang Chen School of Computer Science and Technology Soochow University Suzhou China School of Rail Transportation Soochow University Suzhou China Ministry of Education Key Laboratory of Embedded System and Service Computing (Tongji University) Shanghai China School of Computer Science and Technology University of Science and Technology of China Hefei China

Detecting heavy hitters that constitute the majority of network traffic is a critical task in network measurement. However, the highly skewed network traffic and the size-limited on-chip memory pose great challenges for heavy-hitter detection. The prior arts either use sketches to track all flows or maintain a fix-sized tracking list for recording elephant flows, resulting in limited detection precision or time-consuming tracking list exchanges. This paper presents HeavyTracker, an efficient algorithm that detects heavy hitters based on a count-with-threshold strategy. A two-dimensional tracker unit array is employed in our design to capture the heavy hitters, where each flow is randomly mapped to one unit in all rows. The tracker unit is designed to accept many flows and precisely report the largest two with frequencies that reach a predefined threshold. This design eliminates the frequent and time-consuming exchanges for maintaining the tracking list, allowing us to use a hash table to track the reported elephant flows. Experimental results based on real Internet traces show that HeavyTracker achieves a high $\mathbf{F}_{\beta}$-Score of threshold-t detection (0.97) and over 99% precision of top-k detection under a tight memory size. Besides, it reduces the frequency estimation error by 97.4% compared to the state-of-the-art.

关键词： Art High-speed networks Measurement uncertainty Telecommunication traffic Size measurement Frequency estimation Internet

来源：评论

学校读者我要写书评

暂无评论

Human action recognition using a time-delayed photonic reservoir computing

引用

science China(Information sciences) 2023年第11期66卷 309-310页

作者： Chao KAI Pu LI Yi YANG Bingjie WANG K.Alan SHORE Yuncai WANG Key Laboratory of Advanced Transducers and Intelligent Control System Ministry of Education Taiyuan University of Technology Guangdong Provincial Key Laboratory of Photonics Information Technology School of Information Engineering School of Computer Science and Electronic Engineering Bangor University

Human action recognition(HAR) has important applications, including video retrieval, entertainment, autonomous navigation systems, and visual surveillance systems [1]. Unfortunately, accurate and efficient HAR remains a challenging task in the field of computer vision because its modeling and characteristic representation belong to threedimensional space-time instead of common two-dimensional space [2].

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：