检索结果-内蒙古大学图书馆

Responding to News Sensitively in Stock Attention networks via Prompt-Adaptive Trimodal Model

IEEE Transactions on Neural networks and Learning Systems 2025年第6期36卷 10099-10113页

作者： Haotian Liu Bowen Hu Yadong Zhou Yuxun Zhou Ministry of Education Key Laboratory for Intelligent Networks and Network Security Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an Shaanxi China Department of Electrical Engineering and Computer Sciences University of California at Berkeley Berkeley CA USA

Modern quantitative finance and portfolio-based investment hinge on multimedia news and historical price trends for stock movement prediction. However, prior studies overlook the long tail effect in the feature distribution of stocks, inevitably leading to biased attention and thus degrading the efficiency of utilizing news. To this end, we propose a prompt-adaptive trimodal model (PA-TMM) to overcome the biased stock attention networks and tail feature scarcity problem. In this model, sentiments automatically extracted from trimodal information serve as prompts reflecting the market’s collective mood for other entities, and the interactions among stocks are dynamically inferred for integrating both news- and price-induced movements. By leveraging the movement prompt adaptation (MPA) strategy, our model proactively adapts to the feature-imbalanced phenomenon and converges toward being responsive to the news sensitively. Extensive experiments conducted on real-world datasets consistently demonstrate not only the superiority of the proposed framework over various state-of-the-art baselines, but also its effectiveness, profitability, and robustness in Fintech. The code is accessible at https://***/lauht/PA-TMM .

关键词： Adaptation models Peer-to-peer computing Investment Heavily-tailed distribution Tail Stock markets Feature extraction Correlation Attention mechanisms Time series analysis

来源：评论

学校读者我要写书评

暂无评论

Innovations in Machine Learning for Flight Delay Prediction: A Targeted Overview

Innovations in Machine Learning for Flight Delay Prediction:...

引用

computers and Artificial Intelligence Technologies (CAIT), International Conference on

作者： Wei Wei Chenchen Yu Zhao Yang Fu Bo School of Computer Science and Engineering and the Shaanxi Key Laboratory for Network Computing and Security Xi'an University Of Technology Xi’an China School of Computer Science and Engineering Xi'an University Of Technology Xi’an China

ISBN: (数字)9798331530891

ISBN: (纸本)9798331530907

Artificial intelligence technology is increasingly being applied to air traffic flow forecasting. Based on the core data of Web of Science, this study uses bibliometrics and content review methods to investigate the current situation, methodology evaluation and future research direction of flight delay prediction. Initially, a basic statistical analysis was performed on all the papers. This was followed by topic co-occurrence and keyword co-occurrence analysis, which revealed that most of the research focused on three main categories: machine learning methods, deep learning techniques, and algorithmic optimization strategies. Then reviewing the content in these categories, further content analysis showed that machine learning holds significant potential for handling large and diverse datasets.

关键词： Adaptation models Analytical models Computational modeling Machine learning Predictive models Prediction algorithms Data models Real-time systems Delays Optimization

来源：评论

学校读者我要写书评

暂无评论

Verifiable and Forward-Secure Multi-Keyword Query in Internet of Medical Things

引用

IEEE Internet of Things Journal 2025年

作者： Li, Hongjun He, Debiao Feng, Qi Luo, Min Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan China Wuhan University School of Cyber Science and Engineering Wuhan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China National Key Laboratory of Security Communication Chengdu China

The Internet of Medical Things (IoMT) plays a pivotal role in modern healthcare systems, enhancing patients' medical experiences and improving the efficiency of public medical services. However, concerns regarding security and privacy may hinder the widespread implementation and development of IoMT in practical applications. Dynamic Searchable Symmetric Encryption (DSSE) can maintain search capabilities on encrypted data, even when files are dynamically added or deleted. Earlier DSSE schemes typically support only single keyword query and provide forward security under the assumption of semi-honest servers, which significantly limits their applicability in real-world scenarios. To resolve these limitations, we propose a forward-secure and verifiable DSSE scheme that supports multi-keyword conjunctive query. Our scheme ensures forward security by utilizing a chain structure and guarantees correctness and completeness through RSA accumulator and Homomorphic Message Authentication Code (HMAC). Furthermore, we integrate the forward index and inverted index to enable efficient retrieval. Through comprehensive security and performance analysis, we demonstrate that our scheme effectively protects users' privacy while maintaining low computation and communication overheads. Finally, some experimental evaluations are conducted to verify both the correctness and efficiency of the proposed scheme. © 2014 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Visible Light Positioning Method for Indoor Line-of-Sight Scene Based on Time Series Coding 9

Visible Light Positioning Method for Indoor Line-of-Sight Sc...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Yu, Yonghao Guo, Yongde Zhao, Dawei Fu, Kexue Tang, Yongwei Wang, Qinyuan City University of Macau Faculty of Data Science China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong University School of Mechanical Engineering Key Laboratory of High Efficiency and Clean Mechanical Manufacture Ministry of Education Jinan China

ISBN: (纸本)9798350391367

Existing indoor visible light positioning methods, such as those based on fingerprint database algorithms, are complex to construct and consume significant resources. In response to this issue, the text proposes an end-to-end indoor visible light positioning method that samples continuous signals at a small number of random coordinate positions in indoor environments. Through a deep learning method based on attention mechanism, a nonlinear mapping between the received signal and spatial position coordinates is constructed, and the time series properties in the received signal are encoded as a feature in the data. The method is further improved by combining residual networks to improve accuracy. Through simulation experiments, it has been verified that the deep learning based localization method described in this article can achieve sub meter level accuracy on small sample datasets, and it has been proven that time series features have a significant impact on localization accuracy in indoor visible light positioning algorithms based on deep learning. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server 2

A Web Attack Detection Method Based on DistilBERT and Featur...

引用

2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023

作者： Nige, Li Lu, Chen Lei, Zhao Zhenning, Teng Zhiqiang, Wang Yiyang, Shao Xiaolin, Gui State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co.Ltd. Nanjing China Xi'an Jiaotong University Faculty of Electronic and Information Engineering Shaanxi Province Key Laboratory of Computer Network Xi'an China

ISBN: (纸本)9798350322866

The widespread use of power micro-applications has significantly expanded the attack surface of their server side, thus increasing the risk of vulnerability attacks such as SQL injection, XSS, and CRLF injection. To ensure the security of power systems, these attacks must be detected precisely and timely. Therefore, this paper proposes a server-side web attack detection method based on DistilBERT and feature fusion for HTTP and HTTPS requests. The method treats HTTP and HTTPS requests as text data, specifically, extracts deep semantic features using DistilBERT, and fuses them with well-designed empirical features to comprehensively characterize and classify the request. Consequently, anomalous requests can be detected. The experimental results show that the accuracy, precision, recall, and F1 score of the method on HTTP CSIC 2010 and FWAF datasets are close to or higher than 99%. Compared with other methods as far as we known, this method has better performance and efficiency. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Petri Net Model of MITM Attack Based on NDP Protocol

Petri Net Model of MITM Attack Based on NDP Protocol

引用

2022 International Conference on networking and network Applications, NaNA 2022

作者： Zhang, Liumei Han, Yu Wang, Yichuan Quan, Ruiqin School of Computer Science Xi’an Shiyou University Xi’an China School of Computer Science and Engineering Xi’an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology Xi’an China Xinjiang Institute of Engineering China

ISBN: (数字)9781665461313

ISBN: (纸本)9781665461313

Neighbor Discovery Protocol (NDP) is one of the core protocols of IPv6 networks. Since NDP messages are an unauthenticated stateless protocol, they are vulnerable to various types of attacks, and Man-In-The-Middle (MITM) attacks are one of the most well-known attacks in the computer field. During NDP address resolution, attackers change their own IP-MAC mapping relationships by sniffing NA (Neighbor Advertisement) messages, thus spoofing the source host's neighbor cache table and compromising the confidentiality, integrity and availability of the IPv6 network. Therefore, this paper focuses on the MITM attack in the NDP address resolution process, and performs a fine-grained analysis and Petri Net modelling of the attack process. © 2022 IEEE.

关键词： Petri nets

来源：评论

学校读者我要写书评

暂无评论

MISP: An Efficient Quantum-resistant Misbehavior Preventing Scheme with Self-enforcement for Vehicle-to-Everything

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Chen, Ying He, Debiao Bao, Zijian Wang, Huaqun Luo, Min Wuhan University School of Cyber Science and Engineering Wuhan430072 China Key Laboratory of Computing Power Network & Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China Nanjing University of Posts and Telecommunications College of Computer Nanjing210023 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Industrial Network & Information System Security Jinan250014 China

In the Vehicle-to-Everything (V2X) communication system, the presence of ambiguous warnings significantly increases the risk of severe accidents, posing a substantial threat to the safety of autonomous driving. It is crucial to detect such confusing warnings to avoid danger. Existing solutions to address this issue heavily rely on trust entities or are constructed based on number theory assumptions, leading to low efficiency and vulnerability to quantum attacks. In this paper, we leverage the double authentication-preventing signature scheme (DAPS) to present a revocable identity-based double-authentication preventing signature scheme (RIDAPS) and provides an instantiation from lattice. Furthermore, we propose a post-quantum secure misbehavior preventing scheme (Misp) based on our RIDAPS scheme. We give a detailed proof in the random oracle model (ROM) to demonstrate that our contribution achieves security requirements. Additionally, the efficiency evaluation results demonstrate that our scheme is suitable to be applied in V2X. © 2004-2012 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Interactive Semantic Codec Training for IoT-Based Holographic Counterparts

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Xu, Jinpeng Chen, Liang Lin, Limei Wang, Xiaoding Huang, Yanze Xu, Li Piran, Md. Jalil Fujian Normal University College of Computer and Cyber Security Fujian Provincial Key Laboratory of Network Security and Cryptology Fujian Fuzhou350117 China Fujian University of Technology School of Computer Science and Mathematics Fujian Fuzhou350118 China Sejong University Department of Computer Science and Engineering Seoul05006 Korea Republic of

The use of IoT-based semantic codecs to process complex contextual semantic information in holographic counterparts introduces significant privacy risks, as it may expose sensitive data, thereby increasing the likelihood of privacy disclosures. The diverse and dynamic nature of holographic counterparts in IoT environments exacerbates these challenges, making it more difficult for semantic codecs to effectively safeguard data privacy. This complexity further intensifies the need for privacy-preserving computation methods, as ensuring the confidentiality and security of the data processed by these codecs becomes a critical concern. However, current privacy protection strategy for multi-party training of semantic codecs relies heavily on the central server for gradient calculation, which may lead to gradient leakage issue. To address this issue, we propose PIMSeC (Privacy-Preserving Interactive Multi-Party Semantic Codec Training for IoT-Based Holographic Counterparts), a novel encryption-based technique that facilitates secure and efficient multi-party interactive training without the dependence on the central server, which enhances both data security and privacy resilience. PIMSeC not only proposes a full interactive secure multi-party deep learning model to protect data privacy during multi-party interactive training, but also, within the above deep learning model, establishes an encrypted additive gradient noise mechanism to ensure post-training semantic codec data privacy. Our theoretical analysis and experimental results demonstrate that PIMSeC promotes semantic codecs privacy protection effectively by interactive secure multi-party training. Compared to the state-of-art methods, PIMSeC achieves a 3% to 15% improvement in terms of accuracy, precision, F1-score, and recall at lower compression rates. © 1975-2011 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Key Management and Authentication Scheme Forward Trusted Pervasive Container Computing

Key Management and Authentication Scheme Forward Trusted Per...

引用

Big Data and Privacy Computing (BDPC), International Conference on

作者： XinHong Hei YuZhan Xue YiChuan Wang YiFan Liu Chen Peng Xiang Sun School of computer science and engineering Xi'an University of Technology Xi’an China Shaanxi Key Laboratory for Network Computing and Security Technology School of computer science and engineering Xi'an University of Technology Xi’an China

ISBN: (数字)9798350307597

ISBN: (纸本)9798350307603

Cloud computing technology is an internet-based computing model that provides high reliability and security measures, including data backup, secure access control, etc. As Docker containers play a increasingly important role in traditional cloud computing architectures, the communication needs between containers become prominent. However, existing container to container communication mainly relies on network protocols for file transfer, making it difficult to achieve the expected results in cloud cluster security. Therefore, this paper primarily focuses on container based keys and proposes a container identity trusted key management method based on Pervasive container computing architecture. The experimental results demonstrate that the container identity trusted key management method not only meets the security transmission characteristics required in the container cloud architecture, but also adopts a strategy combined with trusted hardware, providing security guarantees. In addition, the method proposed in this article that combines trusted hardware for signature verification can defend against multiple network attacks compared to traditional container architectures without using security policies.

关键词： computers Cloud computing Handwriting recognition Data privacy Protocols computer architecture Containers

来源：评论

学校读者我要写书评

暂无评论

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on Adaptive Perturbation on Federated Graph Learning 25

NI-GDBA: Non-Intrusive Distributed Backdoor Attack Based on ...

引用

34th ACM Web Conference, WWW 2025

作者： Li, Ken Shi, Bin Wei, Jiazhe Dong, Bo School of Computer Science and Technology Xi’an Jiaotong University Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi’an China School of Computer Science and Technology Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China School of Distance Education Xi’an Jiaotong University Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi’an China

ISBN: (纸本)9798400712746

Federated Graph Learning (FedGL) is an emerging Federated Learning (FL) framework that learns the graph data from various clients to train better Graph Neural networks(GNNs) model. Owing to concerns regarding the security of such framework, numerous studies have attempted to execute backdoor attacks on FedGL, with a particular focus on distributed backdoor attacks. However, all existing methods posting distributed backdoor attack on FedGL only focus on injecting distributed backdoor triggers into the training data of each malicious client, which will cause model performance degradation on original task and is not always effective when confronted with robust federated learning defense algorithms, leading to low success rate of attack. What’s more, the backdoor signals introduced by the malicious clients may be smoothed out by other clean signals from the honest clients, which potentially undermining the performance of the attack. To address the above significant shortcomings, we propose a non-intrusive graph distributed backdoor attack(NI-GDBA) that does not require backdoor triggers to be injected in the training data. Our attack trains an adaptive perturbation trigger generator model for each malicious client to learn the natural backdoor from the GNN model downloading from the server with the malicious client’s local data. In contrast to traditional distributed backdoor attacks on FedGL via trigger injection in training data, our attack on different datasets such as Molecules and Bioinformatics have higher attack success rate, stronger persistence and stealth, and has no negative impact on the performance of the global GNN model. We also explore the robustness of NI-GDBA under different defense strategies, and based on our extensive experimental studies, we show that our attack method is robust to current federated learning defense methods, thus it is necessary to consider non-intrusive distributed backdoor attacks on FedGL as a novel threat that requires custom d

关键词： Federated learning

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：