检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wan, Wei Hu, Shengshan Li, Minghui Lu, Jianrong Zhang, Longling Zhang, Leo Yu Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia School of Computer Science and Technology Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China Cluster and Grid Computing Lab

Federated learning (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could independently or collusively upload well-crafted updates to deteriorate the performance of the global model. However, existing defenses could only mitigate part of Byzantine attacks, without providing an all-sided shield for FL. It is difficult to simply combine them as they rely on totally contradictory assumptions. In this paper, we propose FPD, a four-pronged defense against both non-colluding and colluding Byzantine attacks. Our main idea is to utilize absolute similarity to filter updates rather than relative similarity used in existingI works. To this end, we first propose a reliable client selection strategy to prevent the majority of threats in the bud. Then we design a simple but effective score-based detection method to mitigate colluding attacks. Third, we construct an enhanced spectral-based outlier detector to accurately discard abnormal updates when the training data is not independent and identically distributed (non-IID). Finally, we design update denoising to rectify the direction of the slightly noisy but harmful updates. The four sequentially combined modules can effectively reconcile the contradiction in addressing non-colluding and colluding Byzantine attacks. Extensive experiments over three benchmark image classification datasets against four state-of-the-art Byzantine attacks demonstrate that FPD drastically outperforms existing defenses in IID and non-IID scenarios (with 30% improvement on model accuracy). © 2023, CC BY.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

PANDA: Prompt Transfer Meets Knowledge Distillation for Efficient Model Adaptation

arXiv

引用

arXiv 2022年

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Tao, Dacheng The School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China The School of Computer Science Faculty of Engineering The University of Sydney Sydney Australia The College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue Singapore639798 Singapore

Prompt Transfer (PoT) is a recently-proposed approach to improve prompt-tuning, by initializing the target prompt with the existing prompt trained on similar source tasks. However, such a vanilla PoT approach usually achieves sub-optimal performance, as (i) the PoT is sensitive to the similarity of source-target pair and (ii) directly fine-tuning the prompt initialized with source prompt on target task might lead to forgetting of the useful general knowledge learned from source task. To tackle these issues, we propose a new metric to accurately predict the prompt transferability (regarding (i)), and a novel PoT approach (namely PANDA) that leverages the knowledge distillation technique to alleviate the knowledge forgetting effectively (regarding (ii)). Extensive and systematic experiments on 189 combinations of 21 source and 9 target datasets across 5 scales of PLMs demonstrate that: 1) our proposed metric works well to predict the prompt transferability;2) our PANDA consistently outperforms the vanilla PoT approach by 2.3% average score (up to 24.1%) among all tasks and model sizes;3) with our PANDA approach, prompt-tuning can achieve competitive and even better performance than model-tuning in various PLM scales scenarios. We have publicly released our code in https://***/WHU-ZQH/PANDA. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Real-time rendering for sea water based on height field model and light interaction

引用

ICIC Express Letters, Part B: Applications 2016年第9期7卷 1975-1981页

作者： Xu, Jie Zhang, Yang Fu, Jinhua School of Software Zhengzhou University of Light Industry No. 5 Dongfeng Road Zhengzhou450002 China College of Mathematics and Information Science Zhengzhou University of Light Industry No. 5 Dongfeng Road Zhengzhou450002 China State Key-Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Information Science and Technology Institute Zhengzhou450000 China School of Computer and Communication Engineering Zhengzhou University of Light Industry No. 5 Dongfeng Road Zhengzhou450002 China

Real-time simulation of liquids like sea water is an important task nowadays in the field of computer graphics. In this paper, combined with simulation of light interaction, rendering of sea water at interactive rates is implemented based on the height field model. The focus of the sea rendering is a real-time and graphically realistic simulation, capable of handling different types of illumination such as refraction and reflection. In order to improve the realism of sea water, surface details are efficiently acquired by normal mapping. The effects of lighting and shading via our method are more obvious and clear in such as reflection, refraction, foam and soft shadow, which are in accord with physical interaction between light and water. © 2016 ICIC International.

关键词： Refraction

来源：评论

学校读者我要写书评

暂无评论

Advanced NOMA Assisted Semi-Grant-Free Transmission Schemes for Randomly Distributed Users

arXiv

引用

arXiv 2020年

作者： Lu, Huabing Xie, Xianzhong Shi, Zhaoyuan Lei, Hongjiang Yang, Helin Cai, Jun The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian University of Technology Dalian116024 China The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Key Laboratory of Intelligent Perception and Computing of Anhui Province Anqing Normal University Anqing246011 China The School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China The Department of Information and Communication Engineering School of Informatics Xiamen University Xiamen361005 China Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada

Non-orthogonal multiple access (NOMA) assisted semi-grant-free (SGF) transmission has recently received significant research attention due to its outstanding ability of serving grant-free (GF) users with grant-based (GB) users' spectrum, which greatly improves the spectrum efficiency and effectively relieves the massive access problem of 5G and beyond networks. In this paper, we first study the outage performance of the greedy best user scheduling SGF scheme (BU-SGF) by considering the impacts of Rayleigh fading, path loss, and random user locations. In order to tackle the admission fairness problem of the BU-SGF scheme, we propose a fair SGF scheme by applying cumulative distribution function (CDF)-based scheduling (CS-SGF), in which the GF user with the best channel relative to its own statistics will be admitted. Moreover, by employing the theories of order statistics and stochastic geometry, the outage performances of both BU-SGF and CS-SGF schemes are analyzed. Theoretical results show that both schemes can achieve full diversity orders only when the served users' data rate is capped, which severely limits the rate performance of SGF schemes. To further address this issue, we propose a distributed power control strategy to relax such data rate constraint, and derive analytical expressions of the two schemes' outage performances under this strategy. Finally, simulation results validate the fairness performance of the proposed CS-SGF scheme, the effectiveness of the power control strategy, and the accuracy of the theoretical analyses. Copyright © 2020, The Authors. All rights reserved.

关键词： Spectrum efficiency

来源：评论

学校读者我要写书评

暂无评论

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

arXiv

引用

arXiv 2024年

作者： Ye, Maoyuan Zhang, Jing Liu, Juhua Liu, Chenyu Yin, Baocai Liu, Cong Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China IFLYTEK Research IFLYTEK CO. LTD. China College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue 639798 Singapore

The Segment Anything Model (SAM), a profound vision foundation model pretrained on a large-scale dataset, breaks the boundaries of general segmentation and sparks various downstream applications. This paper introduces Hi-SAM, a unified model leveraging SAM for hierarchical text segmentation. Hi-SAM excels in segmentation across four hierarchies, including pixel-level text, word, text-line, and paragraph, while realizing layout analysis as well. Specifically, we first turn SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach. We use this TS model to iteratively generate the pixel-level text labels in a semi-automatical manner, unifying labels across the four text hierarchies in the HierText dataset. Subsequently, with these complete labels, we launch the end-to-end trainable Hi-SAM based on the TS architecture with a customized hierarchical mask decoder. During inference, Hi-SAM offers both automatic mask generation (AMG) mode and promptable segmentation (PS) mode. In the AMG mode, Hi-SAM segments pixel-level text foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing. As for the PS mode, Hi-SAM provides word, text-line, and paragraph masks with a single point click. Experimental results show the state-of-the-art performance of our TS model: 84.86% fgIOU on Total-Text and 88.96% fgIOU on TextSeg for pixel-level text segmentation. Moreover, compared to the previous specialist for joint hierarchical detection and layout analysis on HierText, Hi-SAM achieves significant improvements: 4.73% PQ and 5.39% F1 on the text-line level, 5.49% PQ and 7.39% F1 on the paragraph level layout analysis, requiring 20× fewer training epochs. The code is available at Hi-SAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Masks

来源：评论

学校读者我要写书评

暂无评论

Outage Performance of Uplink Rate Splitting Multiple Access with Randomly Deployed Users

arXiv

引用

arXiv 2022年

作者： Lu, Huabing Xie, Xianzhong Shi, Zhaoyuan Lei, Hongjiang Zhao, Nan Cai, Jun The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian University of Technology Dalian116024 China The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Key Laboratory of Intelligent Perception and Computing of Anhui Province Anqing Normal University Anqing246011 China The School of Communication and Information Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada

With the rapid proliferation of smart devices in wireless networks, more powerful technologies are expected to fulfill the network requirements of high throughput, massive connectivity, and diversify quality of service. To this end, rate splitting multiple access (RSMA) is proposed as a promising solution to improve spectral efficiency and provide better fairness for the next-generation mobile networks. In this paper, the outage performance of uplink RSMA transmission with randomly deployed users is investigated, taking both user scheduling schemes and power allocation strategies into consideration. Specifically, the greedy user scheduling (GUS) and cumulative distribution function (CDF) based user scheduling (CUS) schemes are considered, which could maximize the rate performance and guarantee scheduling fairness, respectively. Meanwhile, we re-investigate cognitive power allocation (CPA) strategy, and propose a new rate fairness-oriented power allocation (FPA) strategy to enhance the scheduled users' rate fairness. By employing order statistics and stochastic geometry, an analytical expression of the outage probability for each scheduling scheme combining power allocation is derived to characterize the performance. To get more insights, the achieved diversity order of each scheme is also derived. Theoretical results demonstrate that both GUS and CUS schemes applying CPA or FPA strategy can achieve full diversity orders, and the application of CPA strategy in RSMA can effectively eliminate the secondary user's diversity order constraint from the primary user. Simulation results corroborate the accuracy of the analytical expressions, and show that the proposed FPA strategy can achieve excellent rate fairness performance in high signal-to-noise ratio region. Copyright © 2022, The Authors. All rights reserved.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

MISA: UNVEILING THE VULNERABILITIES IN SPLIT FEDERATED LEARNING

arXiv

引用

arXiv 2023年

作者： Wan, Wei Ning, Yuxuan Hu, Shengshan Xue, Lulu Li, Minghui Zhang, Leo Yu Jin, Hai 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 School of Information and Communication Technology Griffith University Australia 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

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users' devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of robustness. In this paper, we present a novel poisoning attack known as MISA. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention. Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai 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 Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Active RIS-aided EH-NOMA Networks: A Deep Reinforcement Learning Approach

arXiv

引用

arXiv 2023年

作者： Shi, Zhaoyuan Lu, Huabing Xie, Xianzhong Yang, Helin Huang, Chongwen Cai, Jun Ding, Zhiguo The Key Laboratory of Intelligent Perception and Computing of Anhui Province Anqing Normal University Anqing China The Key Laboratory of Intelligent Control and Optimization for Industrial Equipment Ministry of Education Dalian University of Technology Dalian116024 China Chongqing Key Lab of Computer networks and Communication Technology Chongqing University of Posts and Telecommunications Chongqing China The Department of Information and Communication Engineering School of Informatics Xiamen University Xiamen361005 China The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Department of Electrical and Computer Engineering Concordia University MontrealQCH3G 1M8 Canada The Department of Electrical Engineering Princeton University PrincetonNJ08544 United States The School of Electrical and Electronic Engineering The University of Manchester Manchester United Kingdom

An active reconfigurable intelligent surface (RIS)-aided multi-user downlink communication system is investigated, where non-orthogonal multiple access (NOMA) is employed to improve spectral efficiency, and the active RIS is powered by energy harvesting (EH). The problem of joint control of the RIS’s amplification matrix and phase shift matrix is formulated to maximize the communication success ratio with considering the quality of service (QoS) requirements of users, dynamic communication state, and dynamic available energy of RIS. To tackle this non-convex problem, a cascaded deep learning algorithm namely long short-term memory-deep deterministic policy gradient (LSTM-DDPG) is designed. First, an advanced LSTM based algorithm is developed to predict users’ dynamic communication state. Then, based on the prediction results, a DDPG based algorithm is proposed to joint control the amplification matrix and phase shift matrix of the RIS. Finally, simulation results verify the accuracy of the prediction of the proposed LSTM algorithm, and demonstrate that the LSTM-DDPG algorithm has a significant advantage over other benchmark algorithms in terms of communication success ratio performance. Copyright © 2023, The Authors. All rights reserved.

关键词： Energy harvesting

来源：评论

学校读者我要写书评

暂无评论

BuildSenSys: Reusing building sensing data for traffic prediction with cross-domain learning

arXiv

引用

arXiv 2020年

作者： Fan, Xiaochen Xiang, Chaocan Chen, Chao Yang, Panlong Gong, Liangyi Song, Xudong Nanda, Priyadarsi He, Xiangjian School of Electrical and Data Engineering Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia Key Laboratory of Dependable Service Computing in Cyber Physical Society Chongqing University Ministry of Education China College of Computer Science Chongqing University Chongqing400044 China School of Computer Science and Technology University of Science and Technology of China Hefei Anhui230026 China School of Software BNRist Tsinghua University Beijing100084 China

With the rapid development of smart cities, smart buildings are generating a massive amount of building sensing data by the equipped sensors. Indeed, building sensing data provides a promising way to enrich a series of data-demanding and cost-expensive urban mobile applications. In this paper, as a preliminary exploration, we study how to reuse building sensing data to predict traffic volume on nearby roads. Compared with existing studies, reusing building sensing data has considerable merits of cost-efficiency and high-reliability. Nevertheless, it is non-trivial to achieve accurate prediction on such cross-domain data with two major challenges. First, relationships between building sensing data and traffic data are not unknown as prior, and the spatio-temporal complexities impose more difficulties to uncover the underlying reasons behind the above relationships. Second, it is even more daunting to accurately predict traffic volume with dynamic building-traffic correlations, which are cross-domain, non-linear, and time-varying. To address the above challenges, we design and implement BuildSenSys, a first-of-its-kind system for nearby traffic volume prediction by reusing building sensing data. Our work consists of two parts, i.e., Correlation Analysis and Cross-domain Learning. First, we conduct a comprehensive building-traffic analysis based on multi-source datasets, disclosing how and why building sensing data is correlated with nearby traffic volume. Second, we propose a novel recurrent neural network for traffic volume prediction based on cross-domain learning with two attention mechanisms. Specifically, a cross-domain attention mechanism captures the building-traffic correlations and adaptively extracts the most relevant building sensing data at each predicting step. Then, a temporal attention mechanism is employed to model the temporal dependencies of data across historical time intervals. The extensive experimental studies demonstrate that BuildSenSys outperf

关键词： 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：