检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Wu, Tianyi Xue, Zhiwei Liu, Yue Zhang, Jiaheng Hooi, Bryan Ng, See-Kiong Integrative Sciences and Engineering Programme NUS Graduate School National University of Singapore Singapore National University of Singapore Singapore Department of Computer Science School of Computing National University of Singapore Singapore

Jailbreak attacks, which aim to cause LLMs to perform unrestricted behaviors, have become a critical and challenging direction in AI safety. Despite achieving the promising attack success rate using dictionary-based evaluation, existing jailbreak attack methods fail to output detailed contents to satisfy the harmful request, leading to poor performance on GPT-based evaluation. To this end, we propose a black-box jailbreak attack termed GeneShift, by using a genetic algorithm to optimize the scenario shifts. Firstly, we observe that the malicious queries perform optimally under different scenario shifts. Based on it, we develop a genetic algorithm to evolve and select the hybrid of scenario shifts. It guides our method to elicit detailed and actionable harmful responses while keeping the seemingly benign facade, improving stealthiness. Extensive experiments demonstrate the superiority of GeneShift. Notably, GeneShift increases the jailbreak success rate from 0% to 60% when direct prompting alone would fail. We will open-source our code. © 2025, CC BY.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

A Survey on Cell Nuclei Instance Segmentation and Classification: Leveraging Context and Attention

arXiv

引用

arXiv 2024年

作者： Nunes, João D. Montezuma, Diana Oliveira, Domingos Pereira, Tania Cardoso, Jaime S. INESC TEC - Institute for Systems and Computer Engineering Technology and Science R. Dr. Roberto Frias Porto4200-465 Portugal University of Porto Faculty of Engineering R. Dr. Roberto Frias Porto4200-465 Portugal IMP Diagnostics Praça do Bom Sucesso Porto4150-146 Portugal R. Dr. António Bernardino de Almeida Porto4200-072 Portugal Doctoral Programme in Medical Sciences School of Medicine and Biomedical Sciences University of Porto ICBAS-UP Porto Portugal FCTUC - Faculty of Science and Technology University of Coimbra Coimbra3004-516 Portugal

Nuclear-derived morphological features and biomarkers provide relevant insights regarding the tumour microenvironment, while also allowing diagnosis and prognosis in specific cancer types. However, manually annotating nuclei from the gigapixel Haematoxylin and Eosin (H&E)-stained Whole Slide Images (WSIs) is a laborious and costly task, meaning automated algorithms for cell nuclei instance segmentation and classification could alleviate the workload of pathologists and clinical researchers and at the same time facilitate the automatic extraction of clinically interpretable features for artificial intelligence (AI) tools. But due to high intra- and inter-class variability of nuclei morphological and chromatic features, as well as H&E-stains susceptibility to artefacts, state-of-the-art algorithms cannot correctly detect and classify instances with the necessary performance. In this work, we hypothesise context and attention inductive biases in artificial neural networks (ANNs) could increase the performance and generalization of algorithms for cell nuclei instance segmentation and classification. To understand the advantages, use-cases, and limitations of context and attention-based mechanisms in instance segmentation and classification, we start by review works in computer vision and medical imaging. We then conduct a thorough survey on context and attention methods for cell nuclei instance segmentation and classification from H&E-stained microscopy imaging, while providing a comprehensive discussion of the challenges being tackled with context and attention. Besides, we illustrate some limitations of current approaches and present ideas for future research. As a case study, we extend both a general instance segmentation and classification method (Mask-RCNN) and a tailored cell nuclei instance segmentation and classification model (HoVer-Net) with context- and attention-based mechanisms, and do a comparative analysis on a multi-centre colon nuclei identification and

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Coastalwql for Stitching, Pre-Processing and Visualization of Push Broom Hyperspectral Imagery for Uav-Based Coastal Water Quality Monitoring

SSRN

引用

SSRN 2023年

作者： Pak, Hui Ying Kieu, Hieu Trung Law, Adrian Wing-Keung Lin, Weisi Khoo, Eugene Environmental Process Modelling Centre Nanyang Environment and Water Research Institute Nanyang Technological University 1 CleanTech Loop 637141 Singapore Interdisciplinary Graduate Programme Graduate College Nanyang Technological University 61 Nanyang Drive 637335 Singapore School of Civil and Environmental Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue 639798 Singapore Engineering and Project Management Division Maritime and Port Authority of Singapore Singapore119963 Singapore

In recent years, Unmanned-Aerial Vehicles (UAVs) and hyperspectral sensors are emerging as popular alternatives for monitoring water quality on-demand. However, image stitching for largely featureless scenes such as open seas has shown to be challenging, and few studies have delved into this domain for push broom hyperspectral images. This study introduces CoastalWQL, with a proposed workflow that entails a GPS-based image stitching method with time delay correction, on top of essential pre-processing procedures to improve the quality of the image mosaic such as sun glint correction and object classification using either an XGBoost and U-net model. CoastalWQL also provides the flexibility for users to specify a trained Deep Neural Network (DNN) or XGBoost model to produce a prediction map for water quality monitoring applications, and a visualization platform to efficiently generate production-ready maps. The results of CoastalWQL have been validated with field surveys at the coastal region of Singapore. © 2023, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

E-Commerce Business Model Analysis and Success in Urban Areas Using AI-Distributed Machine Learning

E-Commerce Business Model Analysis and Success in Urban Area...

引用

Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering (RMKMATE), International Conference on

作者： Akey Sungheetha B Bharathi D. Ganesan T. Karthikeyan N. Bindu Madhavi Chairma Lakshmi K R Dept. of CSE Alliance College of Engineering and Design Alliance University Bangalore Karnataka India Department of Computer Science and Engineering R.M.K. Engineering College Kavaraipettai Tamilnadu India Department of Management Studies Sona College of Technology Salem Tamilnadu India Department of Information Technology University of Technology and Applied Sciences Salalah Sultanate of Oman KL Business School & Programme Coordinator (MBA) KL Centre for Distance & Online Education(CDOE) Koneru Lakshmaiah Education Foundation (Deemed to be University) Andhra Pradesh India Department of Electronics and Instrumentation Engineering R.M.K. Engineering College India

This study presents a comprehensive analysis of the e-commerce business model success in urban areas through the integration of AI distributed machine learning techniques. The rapid growth of e-commerce in urban settings has led to increased competition among businesses striving to capture market share. To achieve a competitive edge, companies are increasingly turning to AI and machine learning to enhance various aspects of their operations. This research examines the symbiotic relationship between e-commerce success and AI technologies, specifically focusing on distributed machine learning role in optimizing operations, personalizing user experiences, and predicting market trends. By leveraging real-world case studies and empirical data, this study sheds light on the mechanisms through which AI distributed machine learning contributes to the sustainable development of e-commerce enterprises in urban environments. The findings of this study provide valuable insights for e-commerce businesses, urban planners, and policymakers to formulate strategies that foster a conducive ecosystem for e-commerce success in urban areas.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Model Resistant to Transferable Adversarial Examples via Trigger Activation

arXiv

引用

arXiv 2025年

作者： Yu, Yi Xia, Song Lin, Xun Kong, Chenqi Yang, Wenhan Lu, Shijian Tan, Yap-Peng Kot, Alex C. Lab Interdisciplinary Graduate Programme Nanyang Technological University Singapore PengCheng Laboratory Shenzhen China School of Electrical and Electronic Engineering Nanyang Technological University Singapore School of Computer Science and Engineering Beihang University Beijing China College of Computing and Data Science Nanyang Technological University Singapore

Adversarial examples, characterized by imperceptible perturbations, pose significant threats to deep neural networks by misleading their predictions. A critical aspect of these examples is their transferability, allowing them to deceive unseen models in black-box scenarios. Despite the widespread exploration of defense methods, including those on transferability, they show limitations: inefficient deployment, ineffective defense, and degraded performance on clean images. In this work, we introduce a novel training paradigm aimed at enhancing robustness against transferable adversarial examples (TAEs) in a more efficient and effective way. We propose a model that exhibits random guessing behavior when presented with clean data x as input, and generates accurate predictions when with triggered data x + τ. Importantly, the trigger τ remains constant for all data instances. We refer to these models as models with trigger activation. We are surprised to find that these models exhibit certain robustness against TAEs. Through the consideration of first-order gradients, we provide a theoretical analysis of this robustness. Moreover, through the joint optimization of the learnable trigger and the model, we achieve improved robustness to transferable attacks. Extensive experiments conducted across diverse datasets, evaluating a variety of attacking methods, underscore the effectiveness and superiority of our approach. Copyright © 2025, 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

Volatile organic compounds sensing based on Bennet doubler-inspired triboelectric nanogenerator and machine learning-assisted ion mobility analysis

引用

science Bulletin 2021年第12期66卷 1176-1185,M0003页

作者： Jianxiong Zhu Zhongda Sun Jikai Xu Rafal D.Walczak Jan ADziuban Chengkuo Lee School of Mechanical Engineering.Southeast University Nanjing 211189China Department of Electrical and Computer Engineering National University of SingaporeSingapore 117576Singapore Center for Intelligent Sensors and MEMS(CISM) National University of SingaporeSingapore 117576Singapore NUS Suzhou Research Institute(NUSRI) Suzhou 215123China Department of Mircroengineering and Photovoltaics Wroclaw University of Science and TechnologyWroclaw 50-370Poland Integrative Sciences and Engineering Programme(ISEP) National University of Singapore.Singapore 119077Singapore

Ion mobility analysis is a well-known analytical technique for identifying gas-phase compounds in fastresponse gas-monitoring ***,the conventional plasma discharge system is bulky,operates at a high temperature,and inappropriate for volatile organic compounds(VOCs)concentration ***,we report a machine learning(ML)-enhanced ion mobility analyzer with a triboelectric-based ionizer,which offers good ion mobility selectivity and VOC recognition ability with a small-sized device and non-strict operating *** on the charge accumulation mechanism,a multi-switched manipulation triboelectric nanogenerator(SM-TENG)can provide a direct current(DC)bias at the order of a few hundred,which can be further leveraged as the power source to obtain a unique and repeatable discharge characteristic of different VOCs,and their mixtures,with a special tip-plate electrode *** to tackle the grand challenge in the detection of multiple VOCs,the ML-enhanced ion mobility analysis method was successfully demonstrated by extracting specific features automatically from ion mobility spectrometry data with ML algorithms,which significantly enhance the detection ability of the SM-TENG based VOC analyzer,showing a portable real-time VOC monitoring solution with rapid response and low power consumption for future internet of things based environmental monitoring applications.

关键词： Machine learning Volatile organic compounds Ion mobility Triboelectric nanogenerator Plasma discharge

来源：评论

学校读者我要写书评

暂无评论

MoRe-Fi: Motion-robust and fine-grained respiration monitoring via deep-learning UWB radar

arXiv

引用

arXiv 2021年

作者： Zheng, Tianyue Chen, Zhe Zhang, Shujie Cai, Chao Luo, Jun School of Computer Science and Engineering Nanyang Technological University Singapore Energy Research Institute Interdisciplinary Graduate Programme Nanyang Technological University Singapore China-Singapore International Joint Research Institute Guangzhou China

Crucial for healthcare and biomedical applications, respiration monitoring often employs wearable sensors in practice, causing inconvenience due to their direct contact with human bodies. Therefore, researchers have been constantly searching for contact-free alternatives. Nonetheless, existing contact-free designs mostly require human subjects to remain static, largely confining their adoptions in everyday environments where body movements are inevitable. Fortunately, radio-frequency (RF) enabled contact-free sensing, though suffering motion interference inseparable by conventional filtering, may offer a potential to distill respiratory waveform with the help of deep learning. To realize this potential, we introduce MoRe-Fi to conduct fine-grained respiration monitoring under body movements. MoRe-Fi leverages an IR-UWB radar to achieve contact-free sensing, and it fully exploits the complex radar signal for data augmentation. The core of MoRe-Fi is a novel variational encoder-decoder network;it aims to single out the respiratory waveforms that are modulated by body movements in a non-linear manner. Our experiments with 12 subjects and 66-hour data demonstrate that MoRe-Fi accurately recovers respiratory waveform despite the interference caused by body movements. We also discuss potential applications of MoRe-Fi for pulmonary disease diagnoses. Copyright © 2021, The Authors. All rights reserved.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

SYNAPSE: An international roadmap to large brain imaging

引用

Physics Reports 2023年第1期999卷 1-60页

作者： Stampfl, Anton P.J. Liu, Zhongdong Hu, Jun Sawada, Kei Takano, H. Kohmura, Yoshiki Ishikawa, Tetsuya Lim, Jae-Hong Je, Jung-Ho Low, Chian-Ming Teo, Alvin Tok, Eng Soon Tan, Tin Wee Ban, Kenneth Libedinsky, Camilo Tan, Francis Chee Kuan Chen, Kuan-Peng Yang, An-Cheng Chuang, Chao-Chun Chen, Nan-Yow Shih, Chi-Tin Lee, Ting-Kuo Yang, De-Nian Lai, Hsu-Chao Shuai, Hong-Han Cheng, Chang-Chieh Ching, Yu-Tai Li, Chia-Wei Charng, Ching-Che Lo, Chung-Chuan Chiang, Ann-Shyn Recur, Benoit Petibois, Cyril Cheng, Chia-Liang Chen, Hsiang-Hsin Yang, Shun-Min Hwu, Yeukuang Rojviriya, Catleya Rugmai, Supagorn Rujirawat, Saroj Margaritondo, Giorgio Australian Nuclear Science and Technology Organization Lucas Heights 2234 NSW Australia Henan university of Technology Zhengzhou China Shanghai Institute of Applied Physics Chinese Academy of Science Shanghai China RIKEN SPring-8 Center Hyogo 679-5148 Japan Pohang Accelerator Laboratory Pohang University of Science and Technology Pohang Gyeongbuk 37673 South Korea Department of Materials Science and Engineering Pohang University of Science and Technology Gyeongbuk Pohang 37673 South Korea Department of Pharmacology Department of Anaesthesia and Healthy Longevity Research Programme Yong Loo Lin School of Medicine National University of Singapore Singapore School of Chemical and Life Sciences Nanyang Polytechnic Singapore eMaGIC-Lab Department of Physics National University of Singapore Singapore National Supercomputing Center Singapore Department of Psychology The N1 Institute for Health National University of Singapore Singapore Institute of Molecular and Cell Biology A*STAR Singapore Department of Anaesthesia National University Hospital National University Health System Singapore National Center for High-Performance Computing Hsinchu Taiwan Department of Physics Tunghai University Taichung Taiwan Department of Physics National Tsing Hua University Hsinchu Taiwan Institute of Information Science Academia Sinica Taipei Taiwan Department of Computer Science National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Information Technology Service Center National Yang Ming Chiao Tung University Hsinchu Taiwan National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Life Science National Tsing Hua University Hsinchu Taiwan Institute of Systems Neuroscience and Brain Research Center National Tsing Hua University Hsinchu Taiwan Institute of Physics Academia Sinica Taipei Taiwan Department of Physics National Dong Hwa University

Since 2020, synchrotron radiation facilities in several Asia-Pacific countries have been collaborating in a major project called “SYNAPSE” (Synchrotrons for Neuroscience: an Asia-Pacific Scientific Enterprise). They use x-ray imaging to attack in a coordinated fashion one of the major issues in modern science: the structure of animal and human brains, including neurons and connections. The objective is to develop Google-like maps also including detailed structural and functional information for selected regions of interest. The sheer mass of data needed for the objective poses huge problems for the acquisition, processing, storage and use of images. In order to complete the task within a reasonable time, the key element of the SYNAPSE strategy is the parallel and coordinated work of several facilities on the same specimens. This article reviews different aspects of the enterprise, including the foundations of synchrotron radiation, coherence and of its role in advanced imaging, electron accelerators, x-ray optics and detectors. This will provide the foundation for an extensive presentation of the different components of SYNAPSE, with an overview of results already obtained within the consortium. © 2022

关键词： Brain mapping Phase contrast Radiology Supercomputing Synchrotron X-rays

来源：评论

学校读者我要写书评

暂无评论

An Energy-Efficient Convolution Unit for Depthwise Separable Convolutional Neural Networks

An Energy-Efficient Convolution Unit for Depthwise Separable...

引用

IEEE International Symposium on Circuits and Systems

作者： Yi Sheng Chong Wang Ling Goh Yew Soon Ong Vishnu P. Nambiar Anh Tuan Do School of Electrical and Electronic Engineering Nanyang Technological University (NTU) Singapore Energy Research Institute Interdisciplinary Graduate Programme NTU Singapore Nanyang Technological University Singapore Singapore School of Computer Science and Engineering NTU Singapore Institute of Microelectronics A*STAR Singapore

High performance but computationally expensive Convolutional Neural Networks (CNNs) require both algorithmic and custom hardware improvement to reduce model size and to improve energy efficiency for edge computing applications. Recent CNN architectures employ depthwise separable convolution to reduce the total number of weights and MAC operations. However, depthwise separable convolution workload does not run efficiently in existing CNN accelerators. This paper proposes an energy-efficient CONV unit for pointwise and depthwise operation. The CONV unit utilizes weight stationary to enable high efficiency. The row partial sum reduction is engaged to increase parallelism in pointwise convolution thereby lightening the memory requirements on output partial sums. Our design achieves a maximum efficiency of 3.17 TOPS/W at 0.85V/40nm CMOS which is well-suited for energy constrained edge computing applications.

关键词： Convolution Memory management Prototypes Parallel processing Energy efficiency Convolutional neural networks Edge computing

来源：评论

学校读者我要写书评

暂无评论

Validation free and replication robust volume-based data valuation 21

Validation free and replication robust volume-based data val...

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Xinyi Xu Zhaoxuan Wu Chuan Sheng Foo Bryan Kian Hsiang Low Dept. of Computer Science National University of Singapore Republic of Singapore and Institute for Infocomm Research A*STAR Republic of Singapore Institute of Data Science National University of Singapore Republic of Singapore and Integrative Sciences and Engineering Programme NUSGS Republic of Singapore Institute for Infocomm Research A*STAR Republic of Singapore Dept. of Computer Science National University of Singapore Republic of Singapore

ISBN: (纸本)9781713845393

Data valuation arises as a non-trivial challenge in real-world use cases such as collaborative machine learning, federated learning, trusted data sharing, data marketplaces. The value of data is often associated with the learning performance (e.g., validation accuracy) of a model trained on the data, which introduces a close coupling between data valuation and validation. However, a validation set may not be available in practice and it can be challenging for the data providers to reach an agreement on the choice of the validation set. Another practical issue is that of data replication: Given the value of some data points, a dishonest data provider may replicate these data points to exploit the valuation for a larger reward/payment. We observe that the diversity of the data points is an inherent property of a dataset that is independent of validation. We formalize diversity via the volume of the data matrix (i.e., determinant of its left Gram), which allows us to establish a formal connection between the diversity of data and learning performance without requiring validation. Furthermore, we propose a robust volume measure with a theoretical guarantee on the replication robustness by following the intuition that copying the same data points does not increase the diversity of data. We perform extensive experiments to demonstrate its consistency in valuation and practical advantages over existing baselines and show that our method is model- and task-agnostic and can be flexibly adapted to handle various neural networks.

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：