检索结果-内蒙古大学图书馆

29th International Conference on Research in Computational Molecular Biology, RECOMB 2025

作者： Dokmai, Natnatee Zhu, Kaiyuan Sahinalp, S. Cenk Cho, Hyunghoon Department of Biomedical Informatics and Data Science Yale School of Medicine New HavenCT United States Department of Computer Science and Engineering UC San Diego La JollaCA United States Cancer Data Science Laboratory National Cancer Institute National Institutes of Health BethesdaMD United States Department of Computer Science Yale University New HavenCT United States

ISBN: (纸本)9783031902512

Genotype imputation servers enable researchers with limited resources to extract valuable insights from their data with enhanced accuracy and ease. However, the utility of these services is limited for those with sensitive study cohorts or those in restrictive regulatory environments due to data privacy concerns. Although privacy-preserving analysis tools have been developed to broaden access to these servers, none of the existing methods support haplotype phasing, a critical component of the imputation workflow. The complexity of phasing algorithms poses a significant challenge in maintaining practical performance under privacy constraints. Here, we introduce TX-Phase, a secure haplotype phasing method based on the framework of Trusted Execution Environments (TEEs). TX-Phase allows users’ private genomic data to be phased while ensuring data confidentiality and integrity of the computation. We introduce novel data-oblivious algorithmic techniques based on compressed reference panels and dynamic fixed-point arithmetic that comprehensively mitigate side-channel leakages in TEEs to provide robust protection of users’ genomic data throughout the analysis. Our experiments on a range of datasets from the UK Biobank and Haplotype Reference Consortium demonstrate the state-of-the-art phasing accuracy and practical runtimes of TX-Phase. Our work enables secure phasing of private genomes, opening access to large reference genomic datasets for a broader scientific community. Our open-source software is available at https://***/hcholab/txphase. The full manuscript is available at https://***/10.1101/2024.09.16.613301. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Head-wise Shareable Attention for Large Language Models

arXiv

引用

arXiv 2024年

作者： Cao, Zouying Yang, Yifei Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China

Large Language Models (LLMs) suffer from huge number of parameters, which restricts their deployment on edge devices. Weight sharing is one promising solution that encourages weight reuse, effectively reducing memory usage with less performance drop. However, current weight sharing techniques primarily focus on small-scale models like BERT and employ coarse-grained sharing rules, e.g., layer-wise. This becomes limiting given the prevalence of LLMs and sharing an entire layer or block obviously diminishes the flexibility of weight sharing. In this paper, we present a perspective on head-wise shareable attention for large language models. We further propose two memory-efficient methods that share parameters across attention heads, with a specific focus on LLMs. Both of them use the same dynamic strategy to select the shared weight matrices. The first method directly reuses the pre-trained weights without retraining, denoted as DirectShare. The second method first post-trains with constraint on weight matrix similarity and then shares, denoted as PostShare. Experimental results reveal our head-wise shared models still maintain satisfactory capabilities, demonstrating the feasibility of fine-grained weight sharing applied to LLMs1 Copyright © 2024, The Authors. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Resource Scheduling Method with Edge Channel Deployment for BPM 19

An Intelligent Resource Scheduling Method with Edge Channel ...

引用

2022 IEEE SmartWorld, 19th IEEE International Conference on Ubiquitous Intelligence and Computing, 2022 IEEE International Conference on Autonomous and Trusted Vehicles Conference, 22nd IEEE International Conference on Scalable Computing and Communications, 2022 IEEE International Conference on Digital Twin, 8th IEEE International Conference on Privacy Computing and 2022 IEEE International Conference on Metaverse, SmartWorld/UIC/ATC/ScalCom/DigitalTwin/PriComp/Metaverse 2022

作者： Liu, Bowen Dou, Wanchun Zhou, Xiaokang Zhang, Xuyun Qi, Lianyong Dai, Fei Chen, Chaochao Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Shiga University Faculty of Data Science Hikone Japan Macquarie University Department of Computing Sydney Australia College of Computer and Software Qingdao China Southwest Forestry University College of Big Data and Intelligent Engineering Kunming China Zhejiang University College of Computer Science and Technology Hangzhou China

ISBN: (纸本)9798350346558

Edge computing is a novel computing paradigm that offers kinds of resources at the network edge. In edge computing, terminal users are connected to edge servers via the wireless network and there are various channels in each wireless link. These wireless channels are limited resource while different channel has different cost and service ability. The dynamic changes of users' status make it harder to find an appropriate method to satisfy the BPM requirements of channel deployment. With this observation, it is a tricky challenge to make a trade-off between the system cost(rental price) and the service ability(number of users). In view of this challenge, an intelligent resource scheduling method, named EdgeIRS, is proposed in this paper. In the technical sense, the EdgeIRS method can accommodate most users at the edge with a minimum cost of deploying channel resources in an online way. Its performance is analyzed theoretically and the experiments verify the superiority of the method. © 2022 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Kbpt: Knowledge-Based Prompt Tuning for Zero-Shot Relation Triplet Extraction

SSRN

引用

SSRN 2023年

作者： Guo, Qian Guo, Yi Zhao, Jin Department of Computer Science and Engineering East China University of Science and Technology Shanghai200237 China Business Intelligence and Visualization Research Center National Engineering Laboratory for Big Data Distribution and Exchange Technologies Shanghai200436 China Shanghai Engineering Research Center of Big Data & Internet Audience Shanghai200072 China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai200433 China

Knowledge representation is becoming an effective way of information extraction. However, considerable studies ignored its application scenarios in the zero-shot setting. In this paper, we propose a novel framework for prompt language models based on external ontology knowledge called Knowledge-Based Prompt Tuning for the Zero-shot Relation Triplet Extraction (KBPT), which encourages further investigation in low-resource regimes to address the data scarcity problem in Relation Triplet Extraction (RTE). The major task of relation triplet extraction in zero-shot learning is to extract multiple triplets that are consisted of head entities, tail entities, and relation labels from an input sentence where the extracted relation labels do not exist in the training set. The fundamental idea of prompt tuning is to construct a prompt template, then append it behind the input text as the pre-trained language models (PLMs) input, thus, transforming the classification task into a masked language model prediction. However, our proposed model does not involve the mask language model prediction but a well-designed prompt template in a structured text format to generate synthetic training data containing the unseen relation category. Concretely, we utilize the relation labels and incorporate virtual tokens sources from the relation semantics to construct a structured prompt template for generating synthetic training instances. Moreover, to further enrich and supplement prior knowledge, we draw on ontology schema based on external knowledge bases to enhance the capability of semantic representation in the prompt template. To address the problem of knowledge heterogeneity, we synergistically optimize these embedding representations by way of collective training. In addition, we carefully design a Multiple Triplets Decoding (MTD) algorithm to break through the limitation of extracting multiple relation triplets in a sentence, and our proposed model is model-agnostic and can be orthogon

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

APK Automated Analysis System Based on Machine Learning 14th

APK Automated Analysis System Based on Machine Learning

引用

14th International Conference on computer engineering and Networks, CENet 2024

作者： Tang, Keyan Liang, Guangjun Chen, Mengxuan Lu, You Zhang, Yang Xu, Zhongping Xu, Yiquan Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing China Engineering Research Center of Electronic Data Forensics Analysis Nanjing China Key Laboratory of Digital Forensics Department of Public Security of Jiangsu Province Nanjing China

ISBN: (纸本)9789819642441

This article first analyzes and compares the advantages and disadvantages of various traditional data mining methods and machine learning algorithms. Then, a new model for identifying Android malicious code was proposed: an Android malicious code detection model based on Java code analysis and deep learning algorithms. The model first extracts Java source code from Android software packages. Furthermore, based on the object-oriented features of the Java language, an inheritance and cross reference relationship graph between various classes is constructed, and the graph is mapped to a grayscale image through its adjacency matrix. Finally, a CNN model is used for classification training to identify malicious programs. By analyzing and comparing the advantages and disadvantages of various feature extraction and selection methods. Using data cleaning and principal component analysis to remove features unrelated to classification, thereby reducing data complexity and improving model prediction accuracy. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Java programming language

来源：评论

学校读者我要写书评

暂无评论

Design and Realization of Personal Password Management System Based on Domestic Cryptographic Algorithms 14th

Design and Realization of Personal Password Management Syste...

引用

14th International Conference on computer engineering and Networks, CENet 2024

作者： Mo, Zixi Zhuge, Chengchen Ma, Zhuo Li, Xiang Zhang, Heyu Zhang, Xunrui Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing China Engineering Research Center of Electronic Data Forensics Analysis Nanjing China Department of Public Security of Jiangsu Province Key Laboratory of Digital Forensics Nanjing China

ISBN: (纸本)9789819642441

To address the problems of low password security and the use of the same password on multiple network platforms, we analyze the major techniques and shortcomings of the existing personal password manager, and a personal password management system based on domestic cryptographic algorithm is designed. This system mainly consists of four parts: identity authentication module, password management module, encryption and decryption module of domestic cryptographic algorithm, and visualization interaction module, which are responsible for user identity authentication, addition, deletion, modification and checking of passwords, encrypting and protecting passwords using SM2 in conjunction with SM4 algorithm, and displaying data on the front-end page through the interface and beautifying it, respectively. Compared with the traditional system, this system is easy to use, more secure in password preservation, more practical, and creatively uses the "SM2 + SM4" domestic cryptographic algorithms encryption combination instead of the traditional "RSA + AES" encryption combination, which is more reliable. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Human resource management

来源：评论

学校读者我要写书评

暂无评论

Metaverse Security and Forensics: VR Devices as an Example

Metaverse Security and Forensics: VR Devices as an Example

引用

14th International Conference on computer engineering and Networks, CENet 2024

作者： Su, Fu Liang, Guangjun Ni, Xueli Zhang, Qinrui Chen, Pu Liu, Jianning Li, Xiang Du, Hongtian Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing China Engineering Research Center of Electronic Data Forensics Analysis Nanjing China Department of Public Security of Jiangsu Province Key Laboratory of Digital Forensics Nanjing China

ISBN: (纸本)9789819642441

VR devices are a rapidly emerging type of sensory terminal device in the context of the metaverse, with its immersive use effects attracting a large number of users to experience. However, with the continuous development of virtual reality technology, an increasing number of criminal incidents in the virtual world have raised concerns. VR devices are developed based on the Android system but have their unique security mechanisms. Therefore, how to securely extract and preserve data from VR devices is a crucial concern for digital forensic practitioners. This paper first proposes a method for application data extraction and analysis in a non root environment within the VR ecosystem based on the Linux shared user id mechanism. This method utilizes Edge Developer Tools to debug Vuplex 3D Webview, enabling the extraction of internal storage data from embedded web pages within the application. Subsequently, a combination of decompilation and packet capture techniques is used to analyze the data transmission methods and data interaction logic of applications in the VR ecosystem. Finally, based on the experimental results, a comprehensive assessment of the security of VR devices is conducted in the paper. data extraction from VR devices is an indispensable part of digital forensics in the era of the metaverse. The research on methods for extracting and analyzing application data in the VR ecosystem in this paper provides valuable reference for future forensic work on VR devices. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： computer forensics

来源：评论

学校读者我要写书评

暂无评论

pFedGPA: Diffusion-based Generative Parameter Aggregation for Personalized Federated Learning 39

pFedGPA: Diffusion-based Generative Parameter Aggregation fo...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Lai, Jiahao Li, Jiaqi Xu, Jian Wu, Yanru Tang, Boshi Chen, Siqi Huang, Yongfeng Ding, Wenbo Li, Yang Tsinghua Shenzhen International Graduate School Tsinghua University China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong Shenzhen Key Laboratory of Ubiquitous Data Enabling Tsinghua University China

ISBN: (纸本)157735897X

Federated Learning (FL) offers a decentralized approach to model training, where data remains local and only model parameters are shared between the clients and the central server. Traditional methods, such as Federated Averaging (FedAvg), linearly aggregate these parameters which are usually trained on heterogeneous data distributions, potentially overlooking the complex, high-dimensional nature of the parameter space. This can result in degraded performance of the aggregated model. While personalized FL approaches can mitigate the heterogeneous data issue to some extent, the limitation of linear aggregation remains unresolved. To alleviate this issue, we investigate the generative approach of diffusion model and propose a novel generative parameter aggregation framework for personalized FL, pFedGPA. In this framework, we deploy a diffusion model on the server to integrate the diverse parameter distributions and propose a parameter inversion method to efficiently generate a set of personalized parameters for each client. This inversion method transforms the uploaded parameters into a latent code, which is then aggregated through denoising sampling to produce the final personalized parameters. By encoding the dependence of a client's model parameters on the specific data distribution using the high-capacity diffusion model, pFedGPA can effectively decouple the complexity of the overall distribution of all clients' model parameters from the complexity of each individual client's parameter distribution. Our experimental results consistently demonstrate the superior performance of the proposed method across multiple datasets, surpassing baseline approaches. Copyright © 2025, Association for the Advancement of Artificial Intelligence.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Intelligent AI-Based Security to Enhance the data Communication: An Empirical Review

A Novel Intelligent AI-Based Security to Enhance the Data Co...

引用

International Conference on Intelligent Systems and Sustainable Computing, ICISSC 2022

作者： Shaik, Amjan Hung, Bui Thanh Chakrabarti, Prasun Siva Shankar, S. Parveen, Nikhat Department of Computer Science and Engineering Dean R&D St. Peter’s Engineering College Maisammaguda Telangana Hyderabad India Data Science Laboratory Faculty of Information Technology Industrial University of Ho Chi Minh Ho Chi Minh Viet Nam Department of Computer Science and Engineering Sir Padampat Singhania University Rajasthan Udaipur India Adjunct Distinguished Professor ITM SLS Baroda University Gujarat Vadodara India CSE K G Reddy College of Engineering and Technology Moinabad India CSE Koneru Lakshmaiah Education Foundation AP Guntur Vaddeswaram India

ISBN: (纸本)9789819947164

The transmission of digital data between two devices is termed data communication. As the world nowadays relies on digital communication, the transferring of data among various devices is vitally important, and hence, the security of the data is a concern. Several works are carried out to secure the data transmission between the devices in various applications like mobile communication, wireless communication, vehicular communication, and more. Incorporated with security, the data classification is also performed to ignore the unwanted or hackers’ data. In this work, we have discussed several secure data communication-related papers from various applications. Works including machine learning-based approaches such as decision tree, linear regression, logistic regression, KNN, K-means, and deep learning-based approaches such as a convolutional neural network, recurrent neural network, and long short-term memory approaches were discussed and listed with their limitations along with merits. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Online Location Planning for AI-Defined Vehicles: Optimizing Joint Tasks of Order Serving and Spatio-Temporal Heterogeneous Model Fine-Tuning

arXiv

引用

arXiv 2025年

作者： Zheng, Bokeng Rao, Bo Zhu, Tianxiang Tan, Chee Wei Duan, Jingpu Zhou, Zhi Chen, Xu Zhang, Xiaoxi School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China College of Computing and Data Science Nanyang Technological University Singapore Department of Communications Peng Cheng Laboratory Shenzhen518066 China

Advances in artificial intelligence (AI) including foundation models (FMs), are increasingly transforming human society, with smart city driving the evolution of urban living. Meanwhile, vehicle crowdsensing (VCS) has emerged as a key enabler, leveraging vehicles’ mobility and sensor-equipped capabilities. In particular, ride-hailing vehicles can effectively facilitate flexible data collection and contribute towards urban intelligence, despite resource limitations. Therefore, this work explores a promising scenario, where edge-assisted vehicles perform joint tasks of order serving and the emerging foundation model fine-tuning using various urban data. However, integrating the VCS AI task with the conventional order serving task is challenging, due to their inconsistent spatio-temporal characteristics: (i) The distributions of ride orders and data point-of-interests (PoIs) may not coincide in geography, both following a priori unknown patterns;(ii) they have distinct forms of temporal effects, i.e., prolonged waiting makes orders become instantly invalid while data with increased staleness gradually reduces its utility for model fine-tuning. To overcome these obstacles, we propose an online framework based on multi-agent reinforcement learning (MARL) with careful augmentation. A new quality-of-service (QoS) metric is designed to characterize and balance the utility of the two joint tasks, under the effects of varying data volumes and staleness. We also integrate graph neural networks (GNNs) with MARL to enhance state representations, capturing graph-structured, time-varying dependencies among vehicles and across locations. Extensive experiments on our testbed simulator, utilizing various real-world foundation model fine-tuning tasks and the New York City Taxi ride order dataset, demonstrate the advantage of our proposed method. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

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：