检索结果-内蒙古大学图书馆

Annual International Symposium on Computer Architecture, ISCA

作者： Haifeng Liu Long Zheng Yu Huang Jingyi Zhou Chaoqiang Liu Runze Wang Xiaofei Liaot Hai Jinf Jingling Xue National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab Huazhong University of Science and Technology China School of Computer Science and Engineering University of New South Wales Australia Zhejiang Lab Hangzhou China

ISBN: (数字)9798350326581

ISBN: (纸本)9798350326598

Personalized recommendation systems have become one of the most important Internet services nowadays. A critical challenge of training and deploying the recommendation models is their high memory capacity and bandwidth demands, with the embedding layers occupying hundreds of GBs to TBs of storage. The advent of memory disaggregation technology and Compute Express Link (CXL) provides a promising solution for memory capacity scaling. However, relocating memory-intensive embedding layers to CXL memory incurs noticeable performance degradation due to its limited transmission bandwidth, which is significantly lower than the host memory bandwidth. To address this, we introduce ReCXL, a CXL memory disaggregation system that utilizes near-memory processing for scalable, efficient recommendation model training. ReCXL features a unified, hardwareefficient NMP architecture that processes the entire embedding training within CXL memory, minimizing data transfers over the bandwidth-limited CXL and enhancing internal bandwidth. To further improve the performance, ReCXL incorporates softwarehardware co-optimizations, including sophisticated dependencyfree prefetching and fine-grained update scheduling, to maximize hardware utilization. Evaluation results show that ReCXL outperforms the CPU-GPU baseline and the naïve CXL memory by $7.1 \times \sim 10.6 \times(9.4 \times$ on average) and $12.7 \times \sim 31.3 \times(22.6 \times$ on average), respectively.

关键词： Training Degradation Scalability Prefetching Memory management Web and internet services Bandwidth

来源：评论

学校读者我要写书评

暂无评论

ECLIPSE: Expunging Clean-label Indiscriminate Poisons via Sparse Diffusion Purification

arXiv

引用

arXiv 2024年

作者： Wang, Xianlong Hu, Shengshan Zhang, Yechao Zhou, Ziqi Zhang, Leo Yu Xu, Peng Wan, Wei 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 Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Information and Communication Technology Griffith University SouthportQLD4215 Australia

Clean-label indiscriminate poisoning attacks add invisible perturbations to correctly labeled training images, thus dramatically reducing the generalization capability of the victim models. Recently, defense mechanisms such as adversarial training, image transformation techniques, and image purification have been proposed. However, these schemes are either susceptible to adaptive attacks, built on unrealistic assumptions, or only effective against specific poison types, limiting their universal applicability. In this research, we propose a more universally effective, practical, and robust defense scheme called ECLIPSE. We first investigate the impact of Gaussian noise on the poisons and theoretically prove that any kind of poison will be largely assimilated when imposing sufficient random noise. In light of this, we assume the victim has access to an extremely limited number of clean images (a more practical scene) and subsequently enlarge this sparse set for training a denoising probabilistic model (a universal denoising tool). We then introduce Gaussian noise to absorb the poisons and apply the model for denoising, resulting in a roughly purified dataset. Finally, to address the trade-off of the inconsistency in the assimilation sensitivity of different poisons by Gaussian noise, we propose a lightweight corruption compensation module to effectively eliminate residual poisons, providing a more universal defense approach. Extensive experiments demonstrate that our defense approach outperforms 10 state-of-the-art defenses. We also propose an adaptive attack against ECLIPSE and verify the robustness of our defense scheme. Our code is available at https://***/CGCL-codes/ECLIPSE. Copyright © 2024, The Authors. 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

Establishment of a diagnostic model of coronary heart disease in elderly patients with diabetes mellitus based on machine learning algorithms

引用

Journal of Geriatric Cardiology 2022年第6期19卷 445-455页

作者： Hu XU Wen-Zhe CAO Yong-Yi BAI Jing DONG He-Bin CHE Po BAI Jian-Dong WANG Feng CAO Li FAN Chinese PLA Medical School Chinese PLA General HospitalBeijingChina Department of Cardiology the Second Medical CenterNational Clinical Research Center for Geriatric DiseasesChinese PLA General HospitalBeijingChina Department of General Surgery the First Medical CenterChinese PLA General HospitalBeijingChina Institute of Geriatrics the Second Medical CenterChinese PLA General HospitalBeijingChina Medical Big Data Research Center&National Engineering Laboratory for Medical Big Data Application Technology Chinese PLA General HospitalBeijingChina Department of Respiratory Diseases Chinese PLA Rocket Force Characteristic Medical CenterBeijingChina

OBJECTIVE To establish a prediction model of coronary heart disease(CHD)in elderly patients with diabetes mellitus(DM)based on machine learning(ML)*** Based on the Medical big data research Centre of Chinese PLA General Hospital in Beijing,China,we identified a cohort of elderly inpatients(≥60 years),including 10,533 patients with DM complicated with CHD and 12,634 patients with DM without CHD,from January 2008 to December *** collected demographic characteristics and clinical *** selecting the important features,we established five ML models,including extreme gradient boosting(XGBoost),random forest(RF),decision tree(DT),adaptive boosting(Adaboost)and logistic regression(LR).We compared the receiver operating characteristic curves,area under the curve(AUC)and other relevant parameters of different models and determined the optimal classification *** model was then applied to 7447 elderly patients with DM admitted from January 2018 to December 2019 to further validate the performance of the *** Fifteen features were selected and included in the ML *** classification precision in the test set of the XGBoost,RF,DT,Adaboost and LR models was 0.778,0.789,0.753,0.750 and 0.689,respectively;and the AUCs of the subjects were 0.851,0.845,0.823,0.833 and 0.731,*** the XGBoost model with optimal performance to a newly recruited dataset for validation,the diagnostic sensitivity,specificity,precision,and AUC were 0.792,0.808,0.748 and 0.880,*** The XGBoost model established in the present study had certain predictive value for elderly patients with DM complicated with CHD.

关键词： patients admitted coronary

来源：评论

学校读者我要写书评

暂无评论

Challenges and Approaches for Mitigating Byzantine Attacks in Federated Learning

Challenges and Approaches for Mitigating Byzantine Attacks i...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Junyu Shi Wei Wan Shengshan Hu Jianrong Lu Leo Yu Zhang School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security School of Information Technology Deakin University

Recently emerged federated learning (FL) is an attractive distributed learning framework in which numerous wireless end-user devices can train a global model with the data remained autochthonous. Compared with the traditional machine learning framework that collects user data for centralized storage, which brings huge communication burden and concerns about data privacy, this approach can not only save the network bandwidth but also protect the data privacy. Despite the promising prospect, Byzantine attack, an intractable threat in conventional distributed network, is discovered to be rather efficacious against FL as well. In this paper, we conduct a comprehensive investigation of the state-of-the-art strategies for defending against Byzantine attacks in FL. We first provide a taxonomy for the existing defense solutions according to the techniques they used, followed by an across-the-board comparison and discussion. Then we propose a new Byzantine attack method called weight attack to defeat those defense schemes, and conduct experiments to demonstrate its threat. The results show that existing defense solutions, although abundant, are still far from fully protecting FL. Finally, we indicate possible countermeasures for weight attack, and highlight several challenges and future research directions for mitigating Byzantine attacks in FL.

关键词： Wireless communication Training Privacy data privacy Federated learning Distance learning Taxonomy

来源：评论

学校读者我要写书评

暂无评论

Spatial–temporal variations of NDVI and its response to climate in China from 2001 to 2020

引用

International Journal of Digital Earth 2022年第1期15卷 1463-1484页

作者： Yuanyuan Wei Shougang Sun Dong Liang Zhaohong Jia School of Internet Anhui UniversityHefeiPeople’s Republic of China National Engineering Research Center for Agro-Ecological Big Data Analysis & Application Anhui UniversityHefeiPeople’s Republic of China School of Computer Science and Technology Anhui UniversityHefeiPeople’s Republic of China

Vegetation plays an important role in global or regional environmental *** this study,the spatial–temporal variations of NDVI and its response to climate in China and its seven sub-regions were investigated based on MODIS NDVI data,ERA5-land precipitation(PRE)and temperature(TEM)data from 2001 to *** inter-annual growth rate of NDVI in China was 0.0021/yr in the past 20 *** inter-annual growth rates of NDVI in seven sub-regions had significant differences at regional or seasonal *** ratio of improved vegetation area to the total studied area reached about 70%.In summer,vegetation degradation was concentrated in East China and Southwest *** vegetation in Central China and South China improved more obviously in autumn than in the other *** vegetation of Northeast China had a remarkable degradation in autumn and winter,especially in *** influence degree of PRE(q=0.54,P<0.01)was greater than that of TEM(q=0.27,P<0.01)in the control of the spatial distribution of *** interaction influence degree q of PRE∩TEM was about 0.71 in the last 20 ***,the PRE and TEM played different roles in vegetation growth in seven sub-regions.

关键词： NDVI spatial–temporal variations climate change MK test Geodetector

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

Efficient and Verifiable Multi-server Framework for Secure Information Classification and Storage 20th

Efficient and Verifiable Multi-server Framework for Secure...

引用

20th International Conference on Information Security and Cryptology, Inscrypt 2024

作者： Guo, Ziqing Wang, Yaohui Jin, Xuanyu Wang, Xiuhua He, Yuanyuan Dai, Yueyue 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 Wuhan430074 China

ISBN: (纸本)9789819647330

With the rapid development of digital technology, the complexity and diversity of data sources present significant security and privacy challenges. To address these issues, this paper proposes an efficient and verifiable Multi-Server Framework for Secure Information Classification and Storage (MSF-SCS). The framework distributes sensitive data across multiple servers, proposing an opening authority to manage classified information and a semi-honest sanitizer to ensure strong authentication while preserving user anonymity. We formalize the security model of our scheme and prove that it satisfies the no-read rule, no-write rule, and unforgeability. We instantiate the scheme and conduct comprehensive experimental evaluations, which demonstrate that MSF-SCS significantly outperforms traditional architectures in terms of scalability and efficiency, making it particularly suitable for industries with stringent data protection requirements. Future work will focus on further improving the system’s security while maintaining its high performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Cardiovascular risk of gonadotropin-releasing hormone antagonist versus agonist in men with prostate cancer: an observational study in Taiwan (Jun, 10.1038/s41391-022-00555-0, 2022)

引用

PROSTATE CANCER AND PROSTATIC DISEASES 2023年第3期26卷 631-632页

作者： Shao, Yu-Hsuan Joni Hong, Jian-Hua Chen, Chun-Kai Huang, Chao-Yuan Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan Clinical Big Data Research Center Taipei Medical University Hospital Taipei Taiwan Department of Urology National Taiwan University Hospital College of Medicine National Taiwan University Taipei Taiwan Institute of Biomedical Engineering National Taiwan University Taipei Taiwan Division of Cardiology Department of Internal Medicine National Taiwan University Hospital Hsinchu Branch Hsinchu Taiwan

Background The impact of gonadotropin-releasing hormone (GnRH) antagonist and agonist (GnRHa) treatment on cardiovascular disease (CVD) risk in prostate cancer (PCa) remains inconclusive due to conflicting findings. We compared the effects of GnRH antagonist and GnRHa treatments on CVD risk in patients with PCa and pre-existing CVD, in a Taiwan population-based *** We assessed the risk of major adverse CV events (MACE: ischemic heart disease [IHD], stroke, congestive heart failure [CHF] or all cause deaths) and composite CV events (IHD, stroke, CHF or CV deaths) occurring ≥90 days after androgen deprivation therapy (ADT) initiation in patients with PCa after 90 days of treatment with either GnRH antagonist (degarelix; n = 499) or GnRHa (goserelin, leuprolide, triptorelin; n = 15,127). Patients identified with pre-existing CVD had received cardiac therapy for IHD, reported a stroke or CHF within a year before ADT initiation. Adjusted hazard ratios (aHR) and 95% confidence interval (CI) were obtained for MACE and composite CV events risk after adjusting for age, baseline status of diabetes, hypertension and treatments *** All GnRH antagonist-treated patients showed lower risk of composite CV events than the GnRHa-treated patients. The lower composite CV events risk associated with GnRH antagonist was also observed in patients with metastasis at diagnosis (aHR 0.16; 95% CI, 0.04–0.38; p = 0.013) and those receiving ADT for more than six months (aHR 0.30; 95% CI, 0.16–0.54; p < 0.0001). In patients with pre-existing CVD, the MACE risk was 33% lower (aHR 0.67; 95% CI, 0.46–0.96; p = 0.0299) and composite CV events risk was 84% lower (aHR 0.16; 95% CI, 0.05–0.50; p = 0.0017) in GnRH antagonist-treated than the GnRHa-treated *** In patients with PCa and pre-existing CVD, GnRH antagonist use was associated with lower risks for composite CV events and MACE compared with GnRHa.

关键词： Cancer therapy Prostate cancer

来源：评论

学校读者我要写书评

暂无评论

EagerLog: Active Learning Enhanced Retrieval Augmented Generation for Log-based Anomaly Detection

EagerLog: Active Learning Enhanced Retrieval Augmented Gener...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Duan, Chiming Jia, Tong Yang, Yong Liu, Guiyang Liu, Jinbu Zhang, Huxing Zhou, Qi Li, Ying Huang, Gang School of Software and Microelectronics Peking University Beijing China Institute for Artificial Intelligence Peking University Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China National Key Laboratory of Data Space Technology and System Beijing China Alibaba Cloud Computing Company Hangzhou China

ISBN: (纸本)9798350368741

Logs record essential information about system operations and serve as a critical source for anomaly detection, which has generated growing research interest. Utilizing large language models (LLMs) within a retrieval-augmented generation (RAG) framework for log-based anomaly detection is an effective approach due to its strong generalization capabilities and efficient few-shot performance. However, the effectiveness of this method hinges on the quality of the knowledge source, which can be impacted by noise and changes within the software systems. Facing these problems, in this paper, we propose a novel log-based anomaly detection method named EagerLog, employing active learning to choose the logs for humans to label, thereby adding them to the knowledge source, thus enhancing the knowledge source and maintaining its quality. Our experiments on three open datasets (BGL, Thunderbird, Zookeeper) and one industrial dataset demonstrate that EagerLog can achieve 93.65% F1 score with approximately 10 labeled log sequences, surpassing existing methods by 15.32%. © 2025 IEEE.

关键词： Active Learning Anomaly Detection Log Analysis Retrieval Augmented Generation

来源：评论

学校读者我要写书评

暂无评论

Fed-AugMix: Balancing Privacy and Utility via data Augmentation

arXiv

引用

arXiv 2024年

作者： Li, Haoyang Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China School of Software Engineering Huazhong University of Science and Technology Wuhan430074 China

Gradient leakage attacks pose a significant threat to the privacy guarantees of federated learning. While distortion-based protection mechanisms are commonly employed to mitigate this issue, they often lead to notable performance degradation. Existing methods struggle to preserve model performance while ensuring privacy. To address this challenge, we propose a novel data augmentation-based framework designed to achieve a favorable privacy-utility trade-off, with the potential to enhance model performance in certain cases. Our framework incorporates the AugMix algorithm at the client level, enabling data augmentation with controllable severity. By integrating the Jensen-Shannon divergence into the loss function, we embed the distortion introduced by AugMix into the model gradients, effectively safeguarding privacy against deep leakage attacks. Moreover, the JS divergence promotes model consistency across different augmentations of the same image, enhancing both robustness and performance. Extensive experiments on benchmark datasets demonstrate the effectiveness and stability of our method in protecting privacy. Furthermore, our approach maintains, and in some cases improves, model performance, showcasing its ability to achieve a robust privacy-utility trade-off. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

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：