检索结果-内蒙古大学图书馆

Security Analysis for a VANET Privacy Protection Scheme

Journal of Cyber Security 2022年第1期4卷 57-64页

作者： Yuzhen Liu Xiaoliang Wang Zhoulei Cao Frank Jiang School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411201China Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan411201China School of Engineering and IT University of New South WalesNSWAustralia

Vehicular ad hoc network(VANET)is a self-organizing wireless sensor network model,which is extensively used in the existing *** to the openness of wireless channel and the sensitivity of traffic information,data transmission process in VANET is vulnerable to leakage and *** of vehicle identitywhile protecting vehicle privacy information is an advantageous way to improve the security of *** propose a scheme based on fair blind signature and secret sharing *** this paper,we prove that the scheme is feasible through security analysis.

关键词： Vehicular ad hoc network anonymous authentication fair blind signature secret sharing algorithm security analysis BAN logic ideology

来源：评论

学校读者我要写书评

暂无评论

Image Data Augmentation for Deep Learning: A Survey

arXiv

引用

arXiv 2022年

作者： Yang, Suorong Xiao, Weikang Zhang, Mengchen Guo, Suhan Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Nanjing University China Department of Computer Science and Technology Nanjing University China School of Artificial Intelligence Nanjing University China School of Electronic Science and Engineering Nanjing University China

Deep learning has achieved remarkable results in many computer vision tasks. Deep neural networks typically rely on large amounts of training data to avoid overfitting. However, labeled data for real-world applications may be limited. By improving the quantity and diversity of training data, data augmentation has become an inevitable part of deep learning model training with image data. As an effective way to improve the sufficiency and diversity of training data, data augmentation has become a necessary part of successful application of deep learning models on image data. In this paper, we systematically review different image data augmentation methods. We propose a taxonomy of reviewed methods and present the strengths and limitations of these methods. We also conduct extensive experiments with various data augmentation methods on three typical computer vision tasks, including semantic segmentation, image classification and object detection. Finally, we discuss current challenges faced by data augmentation and future research directions to put forward some useful research guidance. © 2022, CC BY.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Sensitivity Pruner: Filter-Level Deep Neural Network Compression

SSRN

引用

SSRN 2022年

作者： Guo, Suhan Lai, Bilan Yang, Suorong Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Nanjing University China School of Artificial Intelligence Nanjing University China Department of Computer Science and Technology Nanjing University China School of Electronic Science and Engineering Nanjing University China

As neural networks get deeper to better higher performance, the demand for deployable models on resource-constrained devices also grows. In this work, we propose to achieve model compression using filter-level pruning, which eliminates less sensitive filters. The previous method evaluates neuron importance using the connection matrix gradient in a single shot, which is vulnerable to the sampling bias. Thus, we integrate this measure with the previously proposed "pruning while fine-tuning" framework. Besides classification errors, we introduce the difference between the learned pruning strategy and the single-shot strategy as the second loss component with a self-adjustive hyper-parameter that balances the training goal between improving accuracy and pruning more filters. Experimental results demonstrate the effectiveness of our Sensitivity Pruner (SP), which significantly reduces the computational cost and makes pruned models achieve comparable if not better performance on CIFAR10, CIFAR100, and ILSVRC-12 datasets. © 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

Learning Fair and Efficient Multiple Access Schemes with Decomposed MADDPG

Learning Fair and Efficient Multiple Access Schemes with Dec...

引用

Future Communications and Networks (FCN), International Conference on

作者： Zhaoyang Liu Haoxin Lin Xijun Wang Jie Gong Xiang Chen School of Electronics and Information Technology Sun Yat-sen University Guangzhou China Guangxi Key Laboratory of Wireless Wideband Communication and Signal Processing Guilin China State Key Lab of Novel Software Technology Nanjing University Nanjing China Guangdong Key Laboratory of Information Security Technology School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (数字)9798350396034

ISBN: (纸本)9798350396041

With the growing demand for wireless communication networks, achieving efficient and equitable channel access schemes has become paramount. In this paper, we delve into the realm of distributed channel access in homogeneous wireless networks, focusing on both fairness and efficiency. We introduce a media access control protocol, named Fair and Efficient Multiple Access (FEMA), by leveraging decomposed Multi-Agent Deep Deterministic Policy Gradient (MADDPG). FEMA decouples the dual objectives into self-oriented efficiency reward and team-oriented fairness reward. Correspondingly, local critic networks and global critic networks target self-oriented reward and team-oriented reward, respectively. Extensive simulations demonstrate FEMA’s superiority over conventional MAC protocols and other multiple access techniques based on deep reinforcement learning, showcasing its ability to simultaneously enhance fairness and efficiency.

关键词： Protocols Wireless networks Focusing Media Access Protocol Dynamic scheduling Deep reinforcement learning Resource management

来源：评论

学校读者我要写书评

暂无评论

Dts-Adapstnet: An Adaptive Spatiotemporal Neural Networks for Traffic Prediction with Mulit-Graph Fusion

SSRN

引用

SSRN 2023年

作者： Zhang, Jing Shi, Wenlong Ye, Xiucai Tsai, Peiwei School of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Computer Science University of Tsukuba Tsukuba Japan Department of Computer Science and Software Engineering Swinburne University of Technology Hawthorn Australia

Traffic prediction is of vital importance in intelligent transportation systems. It can realize efficient route planning, avoid traffic congestion and reduce travel time, etc. However, it is difficult to make accurate road traffic prediction, due to the complex spatiotemporal dependencies of the traffic network. The construction and learning of spatial dependencies play a pivotal role in road traffic prediction, laying the foundation for accurate traffic prediction. Regrettably, most of the existing methods for capturing spatial dependencies only consider a single spatial relationship, ignoring other potential temporal and spatial correlations in the traffic network. Moreover, the end-to-end training methods are difficult to control the training direction during graph learning. Additionally, the result of traffic forecasting lacks of fusing multiple traffic data information. All of these have adverse effects on road traffic prediction. In other to capture the spatiotemporal dependencies of the traffic network accurately, a novel traffic prediction framework, Adaptive Spatio-Temporal Graph Neural Network based on Multi-graph Fusion (DTS-adapSTNet), is proposed. First of all, in order to better extract the hidden spatial dependencies, a method of fusing multiple factors is designed, which includs the distance relationship, transfer relationship and same-road segment relationship of traffic data, etc. Secondly, an adaptive learning method is proposed, which can control the learning direction of parameters better by the adaptive matrix generation module and traffic prediction module. Thirdly, an improved loss function is designed for training processes and a multi-matrix fusion module is designed to perform weighted fusion of the learned matrices, updating the spatial adjacency matrix continuously, which fuses as much traffic information as possible for more accurate traffic prediction. Finally, based on the experiments by two large real-world datasets, the DTS-adapSTNe

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Evaluation of Large Language Models for Method Name Prediction

SSRN

引用

SSRN 2024年

作者： Qian, Hanwei Xu, Tingting Ding, Ziqi Liu, Wei Zhu, Shaomin Yin, Jie Feng, Xia Fang, Chunrong Zhao, Jianhua Sun, Weisong State Key Laboratory for Novel Software Technology Nanjing University Jiangsu Nanjing210093 China Jiangsu Police Institute China City University of Macau 999078 China Tongji University Shanghai200092 China School of Computer Science and Engineering Nanyang Technological University 639798 Singapore

High-quality method names are essential for understanding and maintaining programs. However, naming methods can be challenging, especially for new developers. To address this, deep-learning techniques have been developed to predict suitable names for method code bodies. Large Language Models (LLMs) have recently shown exceptional performance in Natural Language Processing (NLP), significantly impacting the software engineering (SE) field. LLMs have been applied to tasks like code summarization, indicating their considerable potential. Yet, there hasn't been a systematic study on adapting LLMs for method name prediction (MNP). This paper fills this gap with the first empirical study exploring LLMs' capabilities in MNP tasks. We evaluate LLMs’ comprehension and interaction patterns in MNP, finding they perform best with a 0 temperature and a few-shot prompt template. Comparing prompt-guided LLMs and fine-tuned PLMs, GPT-3.5 excels among LLMs while CodeT5 leads among PLMs, with minimal performance differences. SentenceBert with Cosine Similarity (SBCS) quantifies semantic differences between predicted and ground-truth names. Human evaluation surpasses the F1 metric for LLMs, identifying challenges like insufficient global information and dataset quality. Finally, we discuss applying LLMs to MNP tasks and suggest future research directions. © 2024, The Authors. All rights reserved.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding 39

HeGTa: Leveraging Heterogeneous Graph-enhanced Large Languag...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Jin, Rihui Li, Yu Qi, Guilin Hu, Nan Li, Yuan-Fang Chen, Jiaoyan Wang, Jianan Chen, Yongrui Min, Dehai Bi, Sheng School of Computer Science and Engineering Southeast University China Ministry of Education China Monash University Australia The University of Manchester United Kingdom Alibaba Group China Law and Innovation Lab Law School Southeast University China State Key Laboratory for Novel Software Technology Nanjing University China

ISBN: (纸本)157735897X

Table Understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures. To address these challenges, we propose HeGTa, a heterogeneous graph (HG)-enhanced large language model (LLM) designed for few-shot TU tasks. This framework aligns structural table semantics with the LLM's parametric knowledge through soft prompts and instruction tuning. It also addresses complex tables with a multi-task pre-training scheme by incorporating novel multi-granularity self-supervised HG pretext tasks. We empirically demonstrate the effectiveness of HeGTa, showing that it outperforms the SOTA for few-shot complex TU on several benchmarks. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing close relations between target artifacts for improving IR-based requirement traceability recovery

引用

Frontiers of Information technology & Electronic Engineering 2021年第7期22卷 957-968页

作者： Haijuan WANG Guohua SHEN Zhiqiu HUANG Yaoshen YU Kai CHEN College of Computer Science and Technology Nanjing University of Aeronautics and AstronauticsNanjing 211106China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing 211106China Key Laboratory of Safety-Critical Software Ministry of Industry and Information TechnologyNanjing 211106China

Requirement traceability is an important and costly task that creates trace links from requirements to different software *** trace links can help engineers reduce the time and complexity of software *** information retrieval(IR)technique has been widely used in requirement *** uses the textual similarity between software artifacts to create ***,if two artifacts do not share or share only a small number of words,the performance of the IR can be very *** methods have been developed to enhance the IR by considering relations between target artifacts,but they have been limited to code rather than to other types of target *** overcome this limitation,we propose an automatic method that combines the IR method with the close relations between target ***,we leverage close relations between target artifacts rather than just text matching from requirements to target ***,the method is not limited to the type of target artifacts when considering the relations between target *** conduct experiments on five public datasets and take account of trace links between requirements and different types of software *** show that under the same recall,the precisions on the five datasets improve by 40%,8%,20%,4%,and6%,respectively,compared with the baseline *** precision on the five datasets improves by an average of15.6%,showing that our method outperforms the baseline method when working under the same conditions.

关键词： Requirement traceability Information retrieval Close relations Target artifacts

来源：评论

学校读者我要写书评

暂无评论

HeGTa: Leveraging Heterogeneous Graph-enhanced Large Language Models for Few-shot Complex Table Understanding

arXiv

引用

arXiv 2024年

作者： Jin, Rihui Li, Yu Qi, Guilin Hu, Nan Li, Yuan-Fang Chen, Jiaoyan Wang, Jianan Chen, Yongrui Min, Dehai Bi, Sheng School of Computer Science and Engineering Southeast University China Key Laboratory of New Generation Artificial Intelligence Technology and its Interdisciplinary Applications Southeast University Ministry of Education China Monash University Australia The University of Manchester United Kingdom Alibaba Group China Law and Innovation Lab Law School Southeast University China State Key Laboratory for Novel Software Technology Nanjing University China

Table Understanding (TU) has achieved promising advancements, but it faces the challenges of the scarcity of manually labeled tables and the presence of complex table structures. To address these challenges, we propose HeGTa, a heterogeneous graph (HG)-enhanced large language model (LLM) designed for few-shot TU tasks. This framework aligns structural table semantics with the LLM’s parametric knowledge through soft prompts and instruction tuning. It also addresses complex tables with a multi-task pre-training scheme by incorporating novel multi-granularity self-supervised HG pretext tasks. We empirically demonstrate the effectiveness of HeGTa, showing that it outperforms the SOTA for few-shot complex TU on several benchmarks. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Preventing the Popular Item Embedding Based Attack in Federated Recommendations

Preventing the Popular Item Embedding Based Attack in Federa...

引用

International Conference on Data Engineering

作者： Jun Zhang Huan Li Dazhong Rong Yan Zhao Ke Chen Lidan Shou The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China Department of Computer Science Aalborg University Aalborg Denmark

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Privacy concerns have led to the rise of federated recommender systems (FRS), which can create personalized models across distributed clients. However, FRS is vulnerable to poisoning attacks, where malicious users manipulate gradients to promote their target items intentionally. Existing attacks against FRS have limitations, as they depend on specific models and prior knowledge, restricting their real-world applicability. In our exploration of practical FRS vulnerabilities, we devise a model-agnostic and prior-knowledge-free attack, named PIECK (Popular Item Embedding based Attack). The core module of PIECK is popular item mining, which leverages embedding changes during FRS training to effectively identify the popular items. Built upon the core module, PIECK branches into two diverse solutions: The PIECKIPE solution employs an item popularity enhancement module, which aligns the embeddings of targeted items with the mined popular items to increase item exposure. The PIECKUEA further enhances the robustness of the attack by using a user embedding approximation module, which approximates private user embeddings using mined popular items. Upon identifying PIECK, we evaluate existing federated defense methods and find them ineffective against PIECK, as poisonous gradients inevitably overwhelm the cold target items. We then propose a novel defense method by introducing two regularization terms during user training, which constrain item popularity enhancement and user embedding approximation while preserving FRS performance. We evaluate PIECK and its defense across two base models, three real datasets, four top-tier attacks, and six general defense methods, affirming the efficacy of both PIECK and its defense.

关键词： Training Privacy Data engineering Robustness Recommender systems

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：