检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liu, Tianhao Liu, Jiqiang Zhang, Tao Wang, Jian Wang, Jiacheng Kang, Jiawen Niyato, Dusit Mao, Shiwen School of Cyberspace Science and Technology Beijing Jiaotong University Beijing100044 China Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing Jiaotong University Beijing100045 China School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China Department of Electrical and Computer Engineering Auburn University AuburnAL36849-5201 United States

Ensuring end-to-end cross-layer communication security in military networks by selecting covert schemes between nodes is a key solution for military communication security. With the development of communication technology, covert communication has expanded from the physical layer to the network and application layers, utilizing methods such as artificial noise, private networks, and semantic coding to transmit secret messages. However, as adversaries continuously eavesdrop on specific communication channels, the accumulation of sufficient data may reveal underlying patterns that influence concealment, and establishing a cross-layer covert communication mechanism emerges as an effective strategy to mitigate these regulatory challenges. In this article, we first survey the communication security solution based on covert communication, specifically targeting three typical scenarios: device-to-device, private network communication, and public network communication, and analyze their application scopes. Furthermore, we propose an end-to-end cross-layer covert communication scheme driven by Generative Artificial Intelligence (GenAI), highlighting challenges and their solutions. Additionally, a case study is conducted using diffusion reinforcement learning to sovle cloud edge internet of things cross-layer secure communication. © 2025, CC BY.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Tuning Second Chern Number in a Four-Dimensional Topological Insulator by High-Frequency Time-Periodic Driving

引用

Chinese Physics Letters 2024年第4期41卷 77-89页

作者：刘峥嵘陈锐周斌 Department of Physics Hubei UniversityWuhan 430062China Key Laboratory of Intelligent Sensing System and Security of Ministry of Education Hubei UniversityWuhan 430062China

Floquet engineering has attracted considerable attention as a promising approach for tuning topological phase *** investigate the effects of high-frequency time-periodic driving in a four-dimensional(4D)topological insulator,focusing on topological phase transitions at the off-resonant quasienergy *** 4D topological insulator hosts gapless three-dimensional boundary states,characterized by the second Chern number C_(2).We demonstrate that the second Chern number of 4D topological insulators can be modulated by tuning the amplitude of time-periodic *** includes transitions from a topological phase with C_(2)=±3 to another topological phase with C_(2)=±1,or to a topological phase with an even second Chern number C_(2)=±2,which is absent in the 4D static ***,the approximation theory in the high-frequency limit further confirms the numerical conclusions.

关键词： topological transitions Periodic

来源：评论

学校读者我要写书评

暂无评论

Higher-order topological Anderson insulator on the Sierpiński lattice

引用

Chinese Physics B 2024年第1期33卷 218-222页

作者：陈焕刘峥嵘陈锐周斌 Department of Physics Hubei UniversityWuhan 430062China Key Laboratory of Intelligent Sensing System and Security of Ministry of Education Hubei UniversityWuhan 430062China

Disorder effects on topological materials in integer dimensions have been extensively explored in recent years. However, its influence on topological systems in fractional dimensions remains unclear. Here, we investigate the disorder effects on a fractal system constructed on the Sierpiński lattice in fractional dimensions. The system supports the second-order topological insulator phase characterized by a quantized quadrupole moment and the normal insulator phase. We find that the second-order topological insulator phase on the Sierpiński lattice is robust against weak disorder but suppressed by strong disorder. Most interestingly, we find that disorder can transform the normal insulator phase to the second-order topological insulator phase with an emergent quantized quadrupole moment. Finally, the disorder-induced phase is further confirmed by calculating the energy spectrum and the corresponding probability distributions.

关键词： fractal system topological insulator

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. 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

Noise-enhanced graph contrastive learning for multimodal recommendation systems

引用

Knowledge-Based systems 2025年 324卷

作者： Ke Shi Yan Zhang Miao Zhang Kui Xiao Xiaoju Hou Zhifei Li School of Computer Science Hubei University Wuhan 430062 China Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan 430062 China Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University) Wuhan 430062 China Institute of Vocational Education Guangdong Industry Polytechnic University Guangzhou 510300 China

Multimodal recommendation systems enhance recommendation accuracy through the fusion of different types of information. Graph Contrastive Learning (GCL) has recently been widely applied in recommendation systems. However, the application of GCL mainly focuses on general user–item interactions, and few models apply it to multimodal information learning. This limitation may hinder the full potential of GCL in more complex multimodal scenarios. To address this issue, we propose a N oise- E nhanced G raph C ontrastive L earning for Multimodal Recommendation systems (NEGCL). As different data augmentation strategies yield distinct outcomes in GCL, we have examined their relative strengths and weaknesses. Introducing innovative contrastive learning into the multimodal information extraction process helps address the limitations of this method in multimodal recommendation, supplemented by an improved transformer for learning in general interactions. A longitudinal comparison of contrastive learning across different methods reveals that noise-based contrastive learning substantially reduces the additional overhead potentially introduced by data augmentation. Furthermore, the introduction of appropriate noise allows contrastive learning to develop more robust nodes. Extensive experiments on three public datasets reveal that NEGCL surpasses previous benchmark models, achieving performance improvements ranging from 8.46% to 11.62% on the Clothing dataset. The source code is publicly available at https://***/HubuKG/NEGCL .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Poisoning as a Post-Protection: Mitigating Membership Privacy Leakage From Gradient and Prediction of Federated Models

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Liu, Gaoyang Xu, Tianlong Yang, Yang Abdelmoniem, Ahmed M. Wang, Chen Liu, Jiangchuan Huazhong University of Science and Technology Hubei Key Laboratory of Internet of Intelligence School of Electronic Information and Communications Wuhan430074 China Simon Fraser University School of Computing Science BurnabyBCV5A 1S6 Canada Ministry of Education Key Laboratory of Intelligent Sensing System and Security China Hubei University School of Artificial Intelligence Wuhan430062 China Queen Mary University of London School of Electronic Engineering and Computer Science United Kingdom

Federated learning (FL) is a distributed learning paradigm that enables multiple clients to train a unified model without sharing their private data. However, recent works demonstrate that FL models are vulnerable to membership inference attacks (MIAs), which can infer whether a data sample was used to train a given FL model. Existing countermeasures either require far-reaching modifications of FL training process or enforce extra processing in prediction phase, yielding them unlikely to be applied well in practice. In this paper, we design a post-protection mechanism, dubbed P2-Protection, which degrades the inference performance of MIAs by simultaneously poisoning the prediction and gradient of the target FL model to reduce the privacy leakage of training data while keeping the model prediction accuracy. P2-Protection only involves one additional training round to embed the poisoned prediction and gradient into the target FL model, without requiring model retraining or training process modification. We evaluate P2-Protection and compare it with two state-of-the-art defenses against three MIAs on five realistic datasets. Experimental results show that P2-Protection outperforms the existing defenses by offering limited implement overhead and improved utility-privacy trade-off. © 2004-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dual topology and versatile Rashba-split surface state configurations in 2M−WS2 and 2M−WSe2

引用

Physical Review B 2025年第11期111卷 115151-115151页

作者： Lixuan Xu Yuqiang Fang Fuqiang Huang Shihao Zhang Shiheng Liang Yulin Chen Lexian Yang Zhongkai Liu Nan Xu Department of Physics Hubei University Wuhan 430062 China Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan 430062 China School of Materials Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Physics and Electronics Hunan University Changsha 410082 China School of Physical Science and Technology ShanghaiTech University Shanghai 201210 China ShanghaiTech Laboratory for Topological Physics Shanghai 201210 China Department of Physics University of Oxford Oxford OX1 3PU United Kingdom State Key Laboratory of Low Dimensional Quantum Physics Department of Physics Tsinghua University Beijing 100084 China Institute for Advanced Studies (IAS) Wuhan University Wuhan 430072 China Wuhan Institute of Quantum Technology Wuhan 430206 China

The 2M-phase transition metal dichalcogenides have recently attracted intensive research interest due to their rich topological and superconducting phase diagrams. Apart from the topological surface states of 2M−WS2 near Γ that originated from the strong topological order, using angle-resolved photoemission spectroscopy, we discover additional Rashba-split states on the surfaces of both 2M−WS2 and 2M−WSe2, which extend in large momentum-energy regions. First-principles calculations well reproduce these states and attribute them to the weak topological orders. The calculations further indicate that the surface state connecting configurations are tunable under moderate pressure, suggesting that 2M−WS2 and WSe2 are promising platforms to study topological phase transition and explore topological superconductivity.

关键词： Photoacoustic spectroscopy

来源：评论

学校读者我要写书评

暂无评论

FedPHE: A Secure and Efficient Federated Learning via Packed Homomorphic Encryption

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Li, Yuqing Yan, Nan Chen, Jing Wang, Xiong Hong, Jianan He, Kun Wang, Wei Li, Bo Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Wuhan University RiZhao Information Technology Institute Rizhao276800 China Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China Shanghai Jiao Tong University School of Cyber Science and Engineering Shanghai200240 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads, packed HE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE assumes all clients share a single private key, making the system vulnerable to security threats of ciphertexts being intercepted and decrypted by honest-but-curious clients. Also, it does not consider the heterogeneity among different clients, resulting in undermined training efficiency with slow convergence and stragglers. To address these challenges, we propose FedPHE, a secure and efficient FL framework with PHE by jointly exploiting contribution-aware secure aggregation and straggler-resistant client selection. Using CKKS with sparsification and blinding, FedPHE achieves efficient secure aggregation that allows clients to only provide obscured encrypted updates while the server can perform aggregation by accounting for contributions of local updates. To mitigate the straggler effect, we devise a perturbed sketch-based selection to cherry-pick representative clients with heterogeneous models and computing capabilities in a communication-efficient and privacy-preserving manner. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients' privacy, achieve 2.45-6.56× training speedup, cut the communication overhead by 1.32-24.85×, and reduce straggler effects by 1.89-2.78×. © 2004-2012 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

Adaptive Perception for Unified Visual Multi-modal Object Tracking

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Hu, Xiantao Zhong, Bineng Liang, Qihua Shi, Liangtao Mo, Zhiyi Tai, Ying Yang, Jian Guangxi Normal University Guangxi Key Lab of Multi-Source Information Mining Guilin541004 China Guangxi Normal University Security Guilin541004 China Guangxi Normal University Intelligent Technology Guilin541004 China Guangxi Normal University Ministry of Education Guilin541004 China Wuzhou University School of Data Science Wuzhou543002 China Wuzhou University Software Engineering Wuzhou543002 China Nanjing University State Key Laboratory for Novel Software Technology Suzhou215163 China Nanjing University of Science and Technology School of Computer Science Nanjing210094 China Nanjing University of Science and Technology Engineering Nanjing210094 China

Recently, many multi-modal trackers prioritize RGB as the dominant modality, treating other modalities as auxiliary, and fine-tuning separately various multi-modal tasks. This imbalance in modality dependence limits the ability of methods to dynamically utilize complementary information from each modality in complex scenarios, making it challenging to fully perceive the advantages of multi-modal. As a result, a unified parameter model often underperforms in various multi-modal tracking tasks. To address this issue, we propose APTrack, a novel unified tracker designed for multi-modal adaptive perception. Unlike previous methods, APTrack explores a unified representation through an equal modeling strategy. This strategy allows the model to dynamically adapt to various modalities and tasks without requiring additional fine-tuning between different tasks. Moreover, our tracker integrates an adaptive modality interaction (AMI) module that efficiently bridges cross-modality interactions by generating learnable tokens. Experiments conducted on five diverse multi-modal datasets (RGBT234, LasHeR, VisEvent, DepthTrack, and VOT-RGBD2022) demonstrate that APTrack not only surpasses existing state-of-the-art unified multi-modal trackers but also outperforms trackers designed for specific multi-modal tasks. © 2020 IEEE.

关键词： Multicarrier modulation

来源：评论

学校读者我要写书评

暂无评论

Link prediction for attribute and structure learning based on attention mechanism

引用

Applied Soft Computing 2025年 179卷

作者： Renjuan Nie Guoyin Wang Qun Liu Chengxin Peng Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing 400065 China Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing 400065 China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing 401331 China

The link prediction problem within complex network analysis focus on accurately inferring future relationships between unconnected node pairs in networks. In real-world scenarios, many relationships can find effective expression through network representation learning, making link prediction pivotal in solving various practical problems. However, existing link prediction methods often exhibit an over-reliance on network structure information or struggle to effectively integrate network structure with node attribute information. Moreover, the current limitations of GPU memory pose challenges for deploying graph neural network (GNN) methods at scale. To address these challenges, this paper introduces attribute and structure learning based on attention mechanism(ASLAM), a novel link prediction framework that amalgamates graph neural networks with attention mechanisms. ASLAM adeptly extracts and integrates both node attribute and structural information, constructing semantic and structural node representations through attention mechanisms and facilitating predictions via adaptive merging. Additionally, to mitigate GPU memory consumption, ASLAM innovatively incorporates the subgraph history embedding method, ensuring stable performance with either constant or linear increases in memory consumption. Experimental results show ASLAM’s superiority over baseline methods across nine real datasets in link prediction tasks. The AUC and AP metrics witness enhancements ranging from 0.11% to 3.03% and 0.15% to 3.32%, respectively, underscoring its promise and applicability.

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：