检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Dingyi Zhou, Deyu School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University China

Persuasive dialogue plays a pivotal role in human communication, influencing various domains. Recent persuasive dialogue datasets often fail to align with real-world interpersonal interactions, leading to unfaithful representations. For instance, unrealistic scenarios may arise, such as when the persuadee explicitly instructs the persuader on which persuasion strategies to employ, with each of the persuadee’s questions corresponding to a specific strategy for the persuader to follow. This issue can be attributed to a violation of the "Double Blind" condition, where critical information is fully shared between participants. In actual human interactions, however, key information—such as the mental state of the persuadee and the persuasion strategies of the persuader—is not directly accessible. The persuader must infer the persuadee’s mental state using Theory of Mind capabilities and construct arguments that align with the persuadee’s motivations. To address this gap, we introduce ToMMA, a novel multi-agent framework for dialogue generation that is guided by causal Theory of Mind. This framework ensures that information remains undisclosed between agents, preserving "double-blind" conditions, while causal ToM directs the persuader’s reasoning, enhancing alignment with human-like persuasion dynamics. Consequently, we present CToMPersu, a multi-domain, multi-turn persuasive dialogue dataset that tackles both double-blind and logical coherence issues, demonstrating superior performance across multiple metrics and achieving better alignment with real human dialogues. Our dataset and prompts are available at https://***/DingyiZhang/ToMMA-CToMPersu. Copyright © 2025, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Fingerprint Revocable Template Protection of Variable Window-Based Random Permutation && Check Code 18th

Fingerprint Revocable Template Protection of Variable Windo...

引用

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Xu, Zilong Bian, Weixin Hu, Yao Luo, Feng School of Computer and Information Anhui Normal University Anhui Wuhu241002 China Anhui Provincial Key Laboratory of Network and Information Security Anhui Wuhu241002 China

ISBN: (纸本)9789819610679

The Uniformly Random Permutation Hashing (URP-IoM) algorithm demonstrates reliable performance and irreversibility in biometric template protection. However, URP-IoM, through random permutation and Hadamard product computation, fails to retain the local features of the original feature vector, which can negatively impact recognition rates and result in varying performance across different datasets. Addressing the impact of biometric template revocability on recognition rates and performance, this paper proposes a novel revocable template method for fingerprint biometrics, called Variable Window-Based Random Permutation IoM Hashing &&Check Code (VWP-IoM &&CC). This method first generates variable windows and check codes based on the Euclidean features of the user password and original feature vector, then records the maximum index of the Hadamard product under the variable window. Finally, it combines the maximum index value with the check code. Experimental results show that the VWP-IoM &&CC algorithm improves recognition rates and performance in FVC2002 and FVC2004 (DB1, DB2), and also meets the requirements of revocability and unlinkability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

MMH-FE:AMulti-Precision and Multi-Sourced Heterogeneous Privacy-Preserving Neural network Training Based on Functional Encryption

引用

computers, Materials & Continua 2025年第3期82卷 5387-5405页

作者： Hao Li Kuan Shao Xin Wang Mufeng Wang Zhenyong Zhang The State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science CenterQilu University of Technology(Shandong Academy of Sciences)Jinan250014China China Industrial Control Systems Cyber Emergency Response Team Beijing100040China

Due to the development of cloud computing and machine learning,users can upload their data to the cloud for machine learning model ***,dishonest clouds may infer user data,resulting in user data *** schemes have achieved secure outsourced computing,but they suffer from low computational accuracy,difficult-to-handle heterogeneous distribution of data from multiple sources,and high computational cost,which result in extremely poor user experience and expensive cloud computing *** address the above problems,we propose amulti-precision,multi-sourced,andmulti-key outsourcing neural network training ***,we design a multi-precision functional encryption computation based on Euclidean ***,we design the outsourcing model training algorithm based on a multi-precision functional encryption with multi-sourced ***,we conduct experiments on three *** results indicate that our framework achieves an accuracy improvement of 6%to 30%.Additionally,it offers a memory space optimization of 1.0×2^(24) times compared to the previous best approach.

关键词： Functional encryption multi-sourced heterogeneous data privacy preservation neural networks

来源：评论

学校读者我要写书评

暂无评论

MSCACodec: A Low-Rate Neural Speech Codec With Multi-scale Residual Channel Attention 21st

MSCACodec: A Low-Rate Neural Speech Codec With Multi-scale R...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Yu, Xingye Li, Ye Zhang, Peng Lin, Lingxia Cai, Tianyu Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (纸本)9789819601240

In the development of modern communication technology, although wideband speech coding provides high-fidelity speech transmission, its high bandwidth requirement limits its application in resource-constrained environments. Thus, narrowband speech coding is still of great significance. Recently, end-to-end neural speech coding has made significant progress and demonstrated superior compression performance over traditional methods. However, existing methods are limited in reconstructing details, especially in low birate environments. To address this, we introduce MSCACodec, a narrowband-based neural speech codec that achieves advanced performance at low bitrates. MSCACodec adopts a multi-scale residual and channel attention feature fusion method to selectively focus on multi-scale information to enhance feature representation, solving the problem of inconsistent hierarchical information caused by multi-scale feature fusion. In addition, we also propose a Temporal Convolutional Gated Recurrent Unit (TCGRU) module, which combines temporal convolutional networks and gated recurrent units to enhance the reconstruction quality using global context and gating mechanisms. The experimental results show that, whether in subjective or objective evaluation, MSCACodec achieves higher quality reconstructed speech than Encodec and HiFiCodec at bitrates of 1.2 kbps and 2.4 kbps, and is even better than LyraV2 and Opus at 6 kbps. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

High-Capacity Image Hiding via Compressible Invertible Neural network 24th

High-Capacity Image Hiding via Compressible Invertible Neur...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Changguang Shi, Haoyi Li, Qingru Zhao, Dongmei Wang, Fangwei College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China Hebei Key Laboratory of Network and Information Security Shijiazhuang050024 China

ISBN: (纸本)9789819615278

Image steganography involves the concealment of confidential information within images, rendering it undetectable to unauthorized observers, and subsequently retrieving the hidden information following secure transmission. Numerous investigations into image steganography employ invertible neural networks. Nevertheless, the intricate architecture of these models poses significant challenges to both their training and inference processes. Consequently, this paper proposes a high-capacity image steganography scheme utilizing compressible modules. We propose a multi-scale attention module that compresses the model structure through structural reparameterization post-training, thereby enhancing inference speed. Additionally, we employ a pre-trained image autoencoder to extract deep features from large-scale images, facilitating high-capacity steganography within invertible neural networks by concealing key features. Experimental results indicate that our approach offers superior image quality and model inference speed, while significantly enhancing security relative to existing methodologies. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Adjacency Query Supporting Homoionym Search over Medical Graph Data in Cloud Computing 17th

Privacy Preserving Adjacency Query Supporting Homoionym Sear...

引用

17th International Conference on Cloud Computing, CLOUD 2024, Held as Part of the Services Conference Federation, SCF 2024

作者： Li, Hourong Tian, Yun Wu, Bin Shi, Jiaoli School of Computer and Big Data Science Jiujiang University Jiujiang332005 China Jiujiang Key Laboratory of Network and Information Security Jiujiang332005 China

ISBN: (纸本)9783031771521

Cloud computing is widely used in all walks of life today. Massive amounts of medical graph data are being outsourced to cloud servers to reduce overhead. The untrustworthiness of cloud servers puts the sensitive information of outsourced graph data at risk. To eliminate this security risk, it is an effective method to encrypt sensitive data. The adjacent queries are frequently used and highly valuable in graph data operations, and the adjacency query supporting homoionym search will enlarge the query effect and improve the query function. When the medical graph data is encrypted and stored on the cloud server, the operation of the data becomes extremely difficult. In this article, we propose a scheme to implement the adjacency query supporting homoionym search in cloud computing (AQHS), which maintains search contents privacy. We use a stem extraction algorithm and the searchable encryption mechanism to build secure index, and then achieve the adjacency query. The security of our proposed scheme is verified by formal analysis, and the effectiveness of the scheme is verified by experimental analysis. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

A Throughput and Priority Optimization Strategy for High Density Healthcare IoT

引用

Intelligent and Converged networks 2025年第1期6卷 41-52页

作者： Su, Zhenlang Ren, Junyu Huang, Yeheng Liao, Yang Qin, Tuanfa School of Computer Electronic and Information Guangxi University Nanning530004 China School of Physics and Electronic Information Guangxi Minzu University Nanning530006 China School of Computer Electronic and Information Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China

In the field of wireless body area networks (WBANs), for solving the complex interference problem of inter-WBANs, a density-based adaptive optimization strategy (DAOS) is proposed in this paper. Firstly, the complex interference problem among WBANs is converted into a distance-based graph coloring model, then time division multiple access and a two-level split clustering methods are adopted to allocate initial time slots for nodes. Secondly, the particle swarm optimization algorithm is used to optimize the time slot of each node for maximizing the throughput. We simulate the scenario on MATLAB simulator. Experimental results show that compared with the traditional scheme in high-density healthcare Internet of Things (IoT) scenarios, DAOS has obvious advantages compared with three comparison strategies of faster convergence rate of 48.94%, 60.76%, and 96.82%, and higher throughput of 5.60%, 8.08%, and 8.05% in traffic priorities 7 to 4. © 2020 Tsinghua University Press.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Task Offloading in Internet of Vehicles: A DRL-based Approach with Representation Learning for DAG Scheduling

引用

IEEE Transactions on Mobile Computing 2025年第06期24卷 5045-5060页

作者： Deng, Xiaoheng Yang, Haoyu Zhang, Jingjing Gui, Jinsong Lin, Siyu Wang, Xin Min, Geyong Central South University School of Electronic Information Changsha410075 China Central South University Shenzhen Research Institute China Beijing Jiaotong University School of Electronic and Information Engineering The State Key Laboratory of Rail Traffic Control and Safety Beijing100044 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250014 China University of Exeter Department of Computer Science ExeterEX4 4QF United Kingdom

The rapid evolution of the Internet-of-Vehicles (IoV) has amplified the need for mobile computing resources, driving the shift toward offloading tasks to edge servers or vehicles with idle resources to optimize computational efficiency. To this end, an approach based on Deep Reinforcement Learning (DRL) is presented in this paper, termed DVTP, which integrates Variational Graph Attention networks (VGAT) and Transformer models to optimize Directed Acyclic Graph (DAG) task scheduling in vehicular networks. DVTP effectively captures both the spatiotemporal information and task dependencies, enabling more accurate and efficient task offloading decisions. Extensive simulation experiments demonstrate that DVTP outperforms traditional methods in reducing task completion times across various multi-vehicle and multi-edge server scenarios, showcasing its potential for real-world IoV applications. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Distributed Stochastic Gradient Descent with Staleness: A Stochastic Delay Differential Equation Based Framework

引用

IEEE Transactions on Signal Processing 2025年 73卷 1708-1726页

作者： Yu, Siyuan Chen, Wei Poor, H. Vincent Department of Electronic Engineering State Key Laboratory of Space Network and Communications and Beijing National Research Center for Information Science and Technology (BNRist) Tsinghua University Beijing China Department of Electrical and Computer Engineering Princeton University Princeton NJ USA

Distributed stochastic gradient descent (SGD) has attracted considerable recent attention due to its potential for scaling computational resources, reducing training time, and helping protect user privacy in machine learning. However, stragglers and limited bandwidth may induce random computational/ communication delays, thereby severely hindering the learning process. Therefore, how to accelerate asynchronous SGD (ASGD) by efficiently scheduling multiple workers is an important issue. In this paper, a unified framework is presented to analyze and optimize the convergence of ASGD based on stochastic delay differential equations (SDDEs) and the Poisson approximation of aggregated gradient arrivals. In particular, we present the run time and staleness of distributed SGD without a memorylessness assumption on the computation times. Given the learning rate, we reveal the relevant SDDE's damping coefficient and its delay statistics, as functions of the number of activated clients, staleness threshold, the eigenvalues of the Hessian matrix of the objective function, and the overall computational/ communication delay. The formulated SDDE allows us to present both the distributed SGD's convergence condition and speed by calculating its characteristic roots, thereby optimizing the scheduling policies for asynchronous/event-triggered SGD. It is interestingly shown that increasing the number of activated workers does not necessarily accelerate distributed SGD due to staleness. Moreover, a small degree of staleness does not necessarily slow down the convergence, while a large degree of staleness will result in the divergence of distributed SGD. Numerical results demonstrate the potential of our SDDE framework, even in complex learning tasks with non-convex objective functions. © 2025 IEEE.

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Chain-of-Specificity: Enhancing Task-Specific Constraint Adherence in Large Language Models 31

Chain-of-Specificity: Enhancing Task-Specific Constraint Adh...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wei, Kaiwen Zhong, Jiang Zhang, Hongzhi Zhang, Di Jin, Li Yu, Yue Zhang, Jingyuan College of Computer Science Chongqing University China Kuaishou Inc. China Key Laboratory of Network Information System Technology Aerospace Information Research Institute Chinese Academy of Sciences China

ISBN: (纸本)9798891761964

Large Language Models (LLMs) exhibit remarkable generative capabilities, enabling the generation of valuable information. Despite these advancements, previous research found that LLMs sometimes struggle with adhering to specific constraints (e.g., in specific place or at specific time), at times even overlooking them, which leads to responses that are either too generic or not fully satisfactory. Existing approaches attempted to address this issue by decomposing, rewriting input instructions, or reflecting on prior failings, yet they fall short in adequately emphasizing specific constraints and in unlocking the underlying knowledge (e.g., programming within the context of software development). In response, this paper proposes a simple yet effective method Chain-of-Specificity (CoS). Specifically, CoS iteratively emphasizes the specific constraints in the input instructions, unlocks knowledge within LLMs, and refines responses. Experiments conducted on publicly available and self-build complex datasets demonstrate that CoS outperforms existing methods in enhancing generated content especially for the specificity. Besides, as the number of specific constraints increase, other baselines falter, while CoS still performs well. Moreover, we show that distilling responses generated by CoS effectively enhances the ability of smaller models to follow the constrained instructions. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

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：