检索结果-内蒙古大学图书馆

6th International Conference on data science, ICDS 2019

作者： Huang, Guang-Li Ji, Yimu Liu, Shangdong Zarei, Roozbeh School of Science RMIT University MelbourneVIC3000 Australia School of Computer Science Nanjing University of Posts and Telecommunications Nanjing210023 China Institute of High Performance Computing and Big Data Nanjing University of Posts and Telecommunications Nanjing210023 China Nanjing Center of HPC China Nanjing210003 China Jiangsu HPC and Intelligent Processing Engineer Research Center Nanjing210003 China School of Information Technology Deakin University GeelongVIC3125 Australia

ISBN: (纸本)9789811528095

Discovering traffic anomaly propagation enables a thorough understanding of traffic anomalies and dynamics. Existing methods, such as STOTree, are not accurate for two reasons. First, they discover the propagation pattern based on the detected anomalies. The imperfection of the detection method itself may introduce false anomalies and miss the real anomaly. Second, they develop a propagation tree of anomalies by searching continuous spatial and temporal neighborhoods rather than considering from a global perspective, and thus cannot find a complete propagation tree if a spatial or temporal gap exists. In this paper, we propose a novel discovering traffic anomaly propagation method using traffic change peaks, which can visualize the change of traffic anomalies (e.g., congestion and evacuation area) and thus accurately captures traffic anomaly propagation. Inspired by image processing techniques, the GPS trajectory dataset in each time period can be converted to one grid traffic image and be stored in the grid density matrix, in which the grid cell corresponds to the pixel and the density of grid cells corresponds to the Gray level (0–255) of pixels. An adaptive filter is developed to generate traffic change graphs from grid traffic images in consecutive periods, and clustering traffic change peaks along the road is to discover the propagation of traffic anomalies. The effectiveness of the proposed method has been demonstrated using a real-world GPS trajectory dataset. © Springer Nature Singapore Pte Ltd 2020.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

The DUDFTO Attack: Towards Down-to-UP Timeout Probing and Dynamically Flow Table Overflowing in SDN

引用

IEEE Transactions on Network and Service Management 2025年

作者： Li, Jiasong Cui, Yunhe Chen, Yi Shen, Guowei Guo, Chun Qian, Qing Guizhou University State Key Laboratory of Public Big Data Engineering Research Center of Text Computing and Cognitive Intelligence Ministry of Education College of Computer Science and Technology Guizhou Provincial Characteristic Key Laboratory of Software Engineering and Information Security Guiyang550000 China Guizhou University of Finance and Economics School of Information Guiyang550000 China

As a new network structure, the decoupling of the control plane and forwarding plane makes Software-Defined Networking (SDN) widely used in large-scale network scenarios. However, the decoupling network architecture also brings new vulnerabilities. The flow table overflow attack is an attack strategy that can overwhelm SDN switches. Nevertheless, the existing flow table overflow attacks may fail in probing timeouts and match fields of flow entries, due to link failure, measurement of the round-trip time (RTT) of different packets, interference of hard-timeout and idle-timeout. Meanwhile, the stealthiness of the existing attacks may also reduce, as these attacks use fixed attack rate. To improve the timeout probing accuracy and the stealthiness of attack, a new flow table overflow attack strategy, DUDFTO, is proposed to accurately probe timeout settings and match fields, then stealthily overflow SDN flow tables. Firstly, it probes the match fields by measuring the one-sided transmission delay of the packets. After that, DUDFTO designs a down-to-up feedback-based timeout probing algorithm to eliminate the issues caused by high RTT, link failure, interference between hard-timeout and idle-timeout. Then, DUDFTO designs a dynamic attack packets sending algorithm to improve its stealthiness. Finally, DUDFTO probes the flow table state to stop sending new attack packets. The evaluation results demonstrate that DUDFTO outperforms the existing attacks in terms of match fields probing ability, timeout probing relative error, number of packet_in and flow_mod messages generated by the attack, rate distribution of packet_in and flow_mod messages generated during the attack, and number of detected attack packets. © 2004-2012 IEEE.

关键词： flow table overflow attack information probing SDN switchs

来源：评论

学校读者我要写书评

暂无评论

Multi-label Contrastive Focal Loss for Pedestrian Attribute Recognition

Multi-label Contrastive Focal Loss for Pedestrian Attribute ...

引用

International Conference on Pattern Recognition

作者： Xiaoqiang Zheng Zhenxia Yu Lin Chen Fan Zhu Shilong Wang Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China School of computer science Chengdu University Of Information Technology Chengdu China Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China

Pedestrian Attribute Recognition (PAR) has received extensive attention during the past few years. With the advances of deep convolutional neural networks (CNNs), the performance of PAR has been significantly improved. Existing methods tend to acquire attribute-specific features by designing various complex network structures with additional modules. Such additional modules, however, dramatically increase the number of network parameters. Meanwhile, the problems of class imbalance and hard attribute retrieving remain underestimated in PAR. In this paper, we explore the optimization mechanism of the training processing to account for these problems and propose a new loss function called Multi-label Contrastive Focal Loss (MCFL). This proposed MCFL emphasizes the hard and minority attributes by using a separated re-weighting mechanism for different positive and negative classes to alleviate the impact of the imbalance. MCFL is also able to enlarge the gaps between the intra-class of multi-label attributes, to force CNNs to extract more subtle discriminative features. We evaluate the proposed MCFL on three large public pedestrian datasets, including RAP, PA-100K, and PETA. The experimental results indicate that the proposed MCFL with the ResNet-50 backbone is able to outperform other state-of-the-art approaches in term of mean accuracy.

关键词： Training Visualization Force Complex networks Feature extraction Pattern recognition Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Backdoor Attacks and Countermeasures on Deep Learning: A Comprehensive Review

arXiv

引用

arXiv 2020年

作者： Gao, Yansong Doan, Bao Gia Zhang, Zhi Ma, Siqi Zhang, Jiliang Fu, Anmin Nepal, Surya Kim, Hyoungshick School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Data61 CSIRO Sydney Australia School of Computer Science University of Adelaide Adelaide Australia School of Information Technology and Electrical Engineering University of Queensland Brisbane Australia College of Computer Science and Electronic Engineering Hunan University Changsha China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China Department of Computer Science and Engineering College of Computing Sungkyunkwan University South Korea and Data61 CSIRO Sydney Australia

Backdoor attacks insert hidden associations or triggers to the deep learning models to override correct inference such as classification and make the system perform maliciously according to the attacker-chosen target while behaving normally in the absence of the trigger. As a new and rapidly evolving realistic attack, it could result in dire consequences, especially considering that the backdoor attack surfaces are broad. In 2019, the U.S. Army Research Office started soliciting countermeasures and launching TrojAI project, the National Institute of Standards and Technology has initialized a corresponding online competition accordingly. However, there is still no systematic and comprehensive review of this emerging area. Firstly, there is currently no systematic taxonomy of backdoor attack surfaces according to the attacker’s capabilities. In this context, attacks are diverse and not combed. Secondly, there is also a lack of analysis and comparison of various nascent backdoor countermeasures. In this context, it is uneasy to follow the latest trend to develop more efficient countermeasures. Therefore, this work aims to provide the community with a timely review of backdoor attacks and countermeasures. According to the attacker’s capability and affected stage of the machine learning pipeline, the attack surfaces are recognized to be wide and then formalized into six categorizations: code poisoning, outsourcing, pretrained, data collection, collaborative learning and post-deployment. Accordingly, attacks under each categorization are combed. The countermeasures are categorized into four general classes: blind backdoor removal, offline backdoor inspection, online backdoor inspection, and post backdoor removal. Accordingly, we review countermeasures and compare and analyze their advantages and disadvantages. We have also reviewed the flip side of backdoor attacks, which have been explored for i) protecting the intellectual property of deep learning models, ii) acting as

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging hardware-control imperfections for error mitigation via generalized quantum subspace

arXiv

引用

arXiv 2023年

作者： Ohkura, Yasuhiro Endo, Suguru Satoh, Takahiko Van Meter, Rodney Yoshioka, Nobuyuki Graduate School of Media and Governance Keio University SFC Kanagawa Fujisawa252-0882 Japan NTT Computer and Data Science Laboratories NTT Corporation Musashino180-8585 Japan Keio University Quantum Computing Center Kanagawa Yokohama223-8522 Japan Graduate School of Science and Technology Keio University Kanagawa Yokohama223-8522 Japan Faculty of Environment and Information Studies Keio University SFC Kanagawa Fujisawa252-0882 Japan Department of Applied Physics University of Tokyo 7-3-1 Hongo Bunkyo-ku Tokyo113-8656 Japan Wako-shi Saitama351-0198 Japan JST PRESTO 4-1-8 Honcho Kawaguchi Saitama332-0012 Japan

In the era of quantum computing without full fault-tolerance, it is essential to suppress noise effects via the quantum error mitigation techniques to enhance the computational power of the quantum devices. One of the most effective noise-agnostic error mitigation schemes is the generalized quantum subspace expansion (GSE) method, which unifies various mitigation algorithms under the framework of the quantum subspace expansion. Specifically, the fault-subspace method, a subclass of GSE method, constructs an error-mitigated quantum state with copies of quantum states with different noise levels. However, from the experimental aspect, it is nontrivial to determine how to reliably amplify the noise so that the error in the simulation result is efficiently suppressed. In this work, we explore the potential of the fault-subspace method by leveraging the hardware-oriented noise: intentional amplification of the decoherence, noise boost by insertion of identity, making use of crosstalk, and probabilistic implementation of noise channel. We demonstrate the validity of our proposals via both numerical simulations with the noise parameters reflecting those in quantum devices available via IBM Quantum, and also experiments performed therein. Copyright © 2023, The Authors. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Brain Age Estimation: A Systematic Review

arXiv

引用

arXiv 2022年

作者： Tanveer, M. Ganaie, M.A. Beheshti, Iman Goel, Tripti Ahmad, Nehal Lai, Kuan-Ting Huang, Kaizhu Zhang, Yu-Dong Ser, Javier Del Lin, Chin-Teng Department of Mathematics Indian Institute of Technology Indore Simrol Indore453552 India Department of Robotics University of Michigan Ann ArborMI48109 United States Department of Human Anatomy and Cell Science Rady Faculty of Health Sciences Max Rady College of Medicine University of Manitoba WinnipegMB Canada Biomedical Imaging Lab National Institute of Technology Assam Silchar788010 India Department of Electrical Engineering and Computer Science National Taipei University of Technology Taipei Taiwan Department of Electronic Engineering National Taipei University of Technology Taipei Taiwan Data Science Research Center Duke Kunshan University China School of Computing and Mathematical Sciences University of Leicester United Kingdom Derio48160 Spain Bilbao48013 Spain School of Computer Science Faculty of Engineering and Information Technology University of Technology Sydney Sydney Australia

Over the years, Machine Learning models have been successfully employed on neuroimaging data for accurately predicting brain age. Deviations from the healthy brain aging pattern are associated to the accelerated brain aging and brain abnormalities. Hence, efficient and accurate diagnosis techniques are required for eliciting accurate brain age estimations. Several contributions have been reported in the past for this purpose, resorting to different data-driven modeling methods. Recently, deep neural networks (also referred to as deep learning) have become prevalent in manifold neuroimaging studies, including brain age estimation. In this review we offer a comprehensive analysis of the literature related to the adoption of deep learning for brain age estimation with neuroimaging data. We detail and analyze different deep learning architectures used for this application, pausing at research works published to date quantitatively exploring their application. We also examine different brain age estimation frameworks, comparatively exposing their advantages and weaknesses. Finally, the review concludes with an outlook towards future directions that should be followed by prospective studies. The ultimate goal of this paper is to establish a common and informed reference for newcomers and experienced researchers willing to approach brain age estimation by using deep learning models. Copyright © 2022, 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

Towards deployment-centric multimodal AI beyond vision and language

arXiv

引用

arXiv 2025年

作者： Liu, Xianyuan Zhang, Jiayang Zhou, Shuo van der Plas, Thijs L. Vijayaraghavan, Avish Grishina, Anastasiia Zhuang, Mengdie Schofield, Daniel Tomlinson, Christopher Wang, Yuhan Li, Ruizhe van Zeeland, Louisa Tabakhi, Sina Demeocq, Cyndie Li, Xiang Das, Arunav Timmerman, Orlando Baldwin-McDonald, Thomas Wu, Jinge Bai, Peizhen Al Sahili, Zahraa Alwazzan, Omnia Do, Thao N. Suvon, Mohammod N.I. Wang, Angeline Cipolina-Kun, Lucia Moretti, Luigi A. Farndale, Lucas Jain, Nitisha Efremova, Natalia Ge, Yan Varela, Marta Lam, Hak-Keung Celiktutan, Oya Evans, Ben R. Coca-Castro, Alejandro Wu, Honghan Abdallah, Zahraa S. Chen, Chen Danchev, Valentin Tkachenko, Nataliya Lu, Lei Zhu, Tingting Slabaugh, Gregory G. Moore, Roger K. Cheung, William K. Charlton, Peter H. Lu, Haiping Centre for Machine Intelligence University of Sheffield Sheffield United Kingdom School of Computer Science University of Sheffield Sheffield United Kingdom The Alan Turing Institute London United Kingdom Department of Metabolism Digestion and Reproduction Imperial College London London United Kingdom Department of Applied AI Simula Research Laboratory Oslo Norway Information School University of Sheffield Sheffield United Kingdom NHS England Leeds United Kingdom Institute of Health Informatics University College London London United Kingdom Department of Engineering King’s College London London United Kingdom Department of Computing Science University of Aberdeen Aberdeen United Kingdom School of Informatics University of Edinburgh Edinburgh United Kingdom School of Engineering Mathematics and Technology University of Bristol Bristol United Kingdom Department of Informatics King’s College London London United Kingdom Department of Earth Sciences University of Cambridge Cambridge United Kingdom Department of Computer Science University of Manchester Manchester United Kingdom Department of Computer Science Queen Mary University of London London United Kingdom Digital Environment Research Institute Queen Mary University of London London United Kingdom Department of Computer Science University of Bath Bath United Kingdom Department of Classics King’s College London London United Kingdom School of Electrical Electronic and Mechanical Engineering University of Bristol Bristol United Kingdom School of Engineering University of the West of England Bristol United Kingdom Cancer Research UK Scotland Institute Glasgow United Kingdom School of Business and Management Queen Mary University of London London United Kingdom City St George’s University of London London United Kingdom British Antarctic Survey Cambridge United Kingdom School of Health and Wellbeing University of Glasgow Glasgow United Kingdom Chief Data & AI Office Lloyds Banking Group Lo

Multimodal artificial intelligence (AI) integrates diverse types of data via machine learning to improve understanding, prediction, and decision-making across disciplines such as healthcare, science, and engineering. However, most multimodal AI advances focus on models for vision and language data, while their deployability remains a key challenge. We advocate a deployment-centric workflow that incorporates deployment constraints early to reduce the likelihood of undeployable solutions, complementing data-centric and model-centric approaches. We also emphasise deeper integration across multiple levels of multimodality and multidisciplinary collaboration to significantly broaden the research scope beyond vision and language. To facilitate this approach, we identify common multimodal-AI-specific challenges shared across disciplines and examine three real-world use cases: pandemic response, self-driving car design, and climate change adaptation, drawing expertise from healthcare, social science, engineering, science, sustainability, and finance. By fostering multidisciplinary dialogue and open research practices, our community can accelerate deployment-centric development for broad societal impact. © 2025, CC BY.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Governing AI-Driven Health Research: Are IRBs Up to the Task?

Ethics & human research

引用

Ethics & human research 2021年第2期43卷 35-42页

作者： Friesen, Phoebe Douglas-Jones, Rachel Marks, Mason Pierce, Robin Fletcher, Katherine Mishra, Abhishek Lorimer, Jessica Véliz, Carissa Hallowell, Nina Graham, Mackenzie Chan, Mei Sum Davies, Huw Sallamuddin, Taj Assistant professor in the Biomedical Ethics Unit and the Department of Social Studies of Medicine at McGill University Associate professor of anthropological approaches to data and infrastructure head of the Technologies in Practice research group the codirector of the ETHOS Lab at the IT University of Copenhagen Assistant professor of law at Gonzaga University and the Edmond J. Safra/Petrie-Flom Centers Joint Fellow-in-Residence at Harvard University Technology and Society at the Tilburg Law School at Tilburg University Coordinator of Cyber Security Oxford and the founding administrator of the Computer Science Department Research Ethics Committee in the Department of Computer Science at the University of Oxford DPhil candidate at the Uehiro Centre for Practical Ethics at the University of Oxford DPhil candidate on the NEUROSEC team in the Department of Psychiatry at the University of Oxford Associate professor in the Faculty of Philosophy at the Institute for Ethics in AI as well as a tutorial fellow at Hertford College at the University of Oxford Codirector of the EPSRC Centre for Doctoral Training in Health Data Science and a professor at the Ethox Centre and Wellcome Centre for Ethics and Humanities at the University of Oxford Senior research fellow in data ethics at the Wellcome Centre for Ethics and Humanities in the Nuffield Department of Population Health at the University of Oxford DPhil student in the Nuffield Department of Population Health at the University of Oxford and a research fellow in the Department of Applied Health Research at University College London Lecturer in education at the School of Education and Sport at the University of Edinburgh Data protection and information lawyer

Many are calling for concrete mechanisms of oversight for health research involving artificial intelligence (AI). In response, institutional review boards (IRBs) are being turned to as a familiar model of governance. Here, we examine the IRB model as a form of ethics oversight for health research that uses AI. We consider the model's origins, analyze the challenges IRBs are facing in the contexts of both industry and academia, and offer concrete recommendations for how these committees might be adapted in order to provide an effective mechanism of oversight for health-related AI research. © 2021 by The Hastings Center. All rights reserved.

关键词： AI research oversight artificial intelligence ethics committees health-related AI research institutional review boards research ethics

来源：评论

学校读者我要写书评

暂无评论

Crosslink-net: Double-branch encoder segmentation network via fusing vertical and horizontal convolutions

arXiv

引用

arXiv 2021年

作者： Yu, Qian Qi, Lei Zhou, Luping Wang, Lei Yin, Yilong Shi, Yinghuan Wang, Wuzhang Gao, Yang School of Data and Computer Science Shandong Women's University Jinan250300 China The State Key Laboratory for Novel Software Technology Nanjing University Nanjing210023 China School of Computer Science and Engineering Southeast University Nanjing211189 China The School of Electrical and Information Engineering University of Sydney NSW2006 Australia The School of Computing and Information Technology University of Wollongong WollongongNSW2522 Australia The School of Soft Shandong University Jinan250100 China Department of Respiratory and Critical Care Medicine Shandong Chest Hospital Jinan250013 China

Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://***/Qianyu1226/*** Codes 68T07 Copyright © 2021, The Authors. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

A Fragile Watermarking Algorithm for Speech Authentication by Modifying Least Significant Digits

A Fragile Watermarking Algorithm for Speech Authentication b...

引用

International Conference on computers, Communications, and Systems (ICCCS)

作者： Qing Qian Yunhe Cui School of Information International Joint Research Center for Data Science and High-Performance Computing Guizhou University of Finance and Economics Guiyang China School of Computer Science and Technology Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China

ISBN: (数字)9781728161365

ISBN: (纸本)9781728161372

Speech content is often faced with malicious forgery and tampering in transit. Therefore, we introduce a novel fragile watermarking algorithm by modifying the least significant digits for speech content authentication and tampering recovery. In this letter, the proposed authentication scheme consists of two processes: the first one is watermark generation and embedding, the second one is content authentication and recovery. In the former process, the compressed speech signal, frame number and check information are generated based on speech content to form a watermark. Subsequently, the generated watermark is embedded into the least significant digits of speech sampling points using the proposed watermarking algorithm. In the latter process, the embedded watermark is utilized to locate the tampered area and recover that tampered content synchronously. Experimental results show that the proposed watermarking algorithm is fragile to common signal processing. Additionally, it has favorable inaudibility, accurate location ability and high recovery quality.

关键词： Watermarking Authentication Speech coding Signal to noise ratio Speech processing

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：