检索结果-内蒙古大学图书馆

Multimodal Fusion for Android Malware Detection Based on Large Pre-Trained Models

IEEE Transactions on Software engineering 2025年第5期51卷 1569-1590页

作者： Li, Xun Liu, Lei Liu, Yuzhou Zhao, Yu Zhang, Peng Liu, Huaxiao Jilin University College of Computer Science and Technology Changchun130012 China Northeast Electric Power University School of Computer Science Jilin132012 China Jilin University College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Changchun130012 China

Malware detection is a critical issue in software engineering as it directly threatens user information security. Existing approaches often focus on individual modality (either source code or binary code) for the detection, but it ignores to effectively exploit the complementary information between them. This limits the detection performance, especially in complex and evasive malware scenarios. In this paper, we take Android applications written in Java as objects, and provide a novel fine-grained multimodal fusion method with large pre-trained models to combine the features from source and binary codes for the malware detection. For the source code modality, we employ the graphical user interface (GUI) as a framework to segment the source code into snippets, and use a pre-trained programming language model to extract feature representations. For the binary code modality, we convert binary code into grayscale images and fine-tune a pre-trained vision model to extract features indirectly. We then implement cross-modal attention and devise a contrastive loss to align features across modalities, supplementing this with supervised classification loss to refine the multimodal fusion process specifically for malware detection. Our experiments, conducted using the data-MD and data-MC benchmarks, demonstrate that our approach achieves a precision of 0.977 and a recall of 0.984 in detecting malware. This underscores the advantages of using large pre-trained models for feature representation and the fusion of information across different modalities for effective malware detection. © 1976-2012 IEEE.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Recticoil for Efficient Compact Inductive Power Transfer

引用

IEEE Transactions on Power Electronics 2025年第7期40卷 10154-10164页

作者： Yi, Zixuan Qin, Yuanyuan Yang, Xue-Xia Shao, Yaoxia Zeng, Dan Li, Meiling Shanghai University School of Communication and Information Engineering Key Laboratory of Specialty Fiber Optics and Optical Access Networks Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai Institute for Advanced Communication and Data Science Shanghai200444 China Hangzhou City University School of Information and Electrical Engineering Hangzhou310015 China

The MHz inductive power transfer (IPT) system has broad application prospects due to its high safety, longer transmission distance, and better tolerance for misalignment. However, the increase in frequency will lead to an increased loss of lumped components, such as inductors and capacitors, in peripheral circuits, thereby reducing efficiency. This is currently the bottleneck problem encountered by MHz IPT. To address this key challenge, researchers have tried to remove the lumped components in the peripheral circuit while ensuring the functions of the IPT system. One successful and beneficial attempt is the self-resonant coil, which replaces traditional lumped resonant capacitors with distributed capacitors formed by coil turn-to-turn capacitance, ensuring compensation for leakage inductance and eliminating reactive power. This innovative integration makes efficiency and integration greatly improved. In this article, the novel coil named Recticoil, on which the rectification function is integrated further, is proposed for efficient compact IPT. Recticoil can directly output dc power without additional compensation and rectification circuits. By analyzing a toroidal coil where two separate conductors generate a voltage differential, and incorporating two diodes, resulting in a dc output. Subsequently, the self-resonant coil replaces the toroidal coil to form Recticoil, and the equivalent circuits of Recticoil are given and analyzed. In addition, the analysis and test method of rectification efficiency is given. The experimental results show that the Recticoil achieves a rectification efficiency as high as 97.25% at 6.78 MHz, outperforming both the bridge rectifier and the Class E rectifier. Additionally, the compact construction of Recticoil eliminates the volume of traditional rectifiers. All of these advantages of Recticoil render it a promising candidate for applications in wearables and miniaturized devices. © 1986-2012 IEEE.

关键词： Equivalent circuits

来源：评论

学校读者我要写书评

暂无评论

Novel Sm3+ and Eu3+ co-doped Sr2YNbO6 red-emitting phosphor for white LED applications

引用

Ceramics International 2025年第15期51卷 19901-19909页

作者： Zhang, Yuanfeng Shi, Youzhen Deng, Chaoyong Zhang, Min College of Big Data and Information Engineering Guizhou University Guiyang550025 China Key Laboratory of Electronic Functional Composite Materials of Guizhou Province Guiyang550025 China School of Science China University of Geosciences Beijing100083 China Guizhou Academy of Sciences Guiyang550001 China

A series Sm3+ and Eu3+ co-doped Sr2YNbO6 phosphors were prepared by high temperature solid state reaction method in this work. The photoluminescence properties and energy transfer process were studied, and the results revealed that the photoluminescence intensity was significantly enhanced by co-doped with Eu3+, with the optimal concentration of 0.15mol, and the energy transfer efficiency between Sm3+ and Eu3+ ions was as high as 94.25%. In addition, the diffuse reflectance spectrum results confirmed the excitation wavelength of the sample, and the optical band gap showed concentration dependence. Finally, the lower color temperature CCT=2502K and the higher color rendering index Ra=76.4 indicate that the material has potential application value in the fields of LED and anti-counterfeiting display. © 2025 Elsevier Ltd and Techna Group S.r.l.

关键词： Photoluminescence

来源：评论

学校读者我要写书评

暂无评论

Persistent luminescence encoding for rapid and accurate oral-derived bacteria identification

引用

Chinese Chemical Letters 2025年第1期36卷 459-463页

作者： Chaohui Zheng Jing Xi Shiyi Long Tianpei He Rui Zhao Xinyuan Luo Na Chen Quan Yuan The Second Affiliated Hospital of Fujian Medical University Quanzhou 362000China Renmin Hospital of Wuhan University College of Chemistry and Molecular SciencesInstitute of Molecular MedicineSchool of MicroelectronicsWuhan UniversityWuhan 430072China Molecular Science and Biomedicine Laboratory(MBL) State Key Laboratory of Chemo/Biosensing and Chemometrics College of Chemistry and Chemical EngineeringHunan UniversityChangsha 410082China

The dysbiosis of oral microbiota contributes to diseases such as periodontitis and certain cancers by triggering the host inflammatory *** methods for the immediate and sensitive identification of oral microorganism is crucial for the rapid diagnosis and early interventions of associated *** methods for microbial detection primarily include the plate culturing,polymerase chain reaction and enzyme-linked immunosorbent assay,which are either time-consuming or ***,we reported a persistent luminescence-encoded multiple-channel optical sensing array and achieved the rapid and accurate identification of oral-derived *** results demonstrate that electrostatic attractions and hydrophobic-hydrophobic interactions dominate the binding of the persistent luminescent nanoprobes to oral microorganisms and the microbial identification process can be finished within 30 ***,a total of 7 oral-derived microorganisms demonstrate their own response patterns and were differentiated by linear discriminant analysis(LDA)with the accuracy up to 100%both in the solution and artificial saliva ***,the persistent luminescence encoded array sensor could also discern the microorganism mixtures with the accuracy up to 100%.The proposed persistent luminescence encoding sensor arrays in this work might offer new ideas for rapid and accurate oralderived microorganism detection,and provide new ways for disease diagnosis associated with microbial metabolism.

关键词： Oral microorganisms Persistent luminescent nanoprobes Optical sensing array Fingerprint physicochemical properties Linear discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

Disentangled Noisy Correspondence Learning

引用

IEEE Transactions on Image Processing 2025年 34卷 2602-2615页

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong Xi’an Jiaotong University School of Computer Science and Technology Ministry of Education Key Laboratory of Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi’an710049 China SGIT AI Laboratory Xi’an710048 China State Grid Corporation of China State Grid Shaanxi Electric Power Company Ltd. Xi’an710048 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Abu Dhabi United Arab Emirates Baidu Inc. Beijing100085 China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of modality-invariant information (MII) and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal inputs for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL’s efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. © 1992-2012 IEEE.

关键词： Information theory

来源：评论

学校读者我要写书评

暂无评论

Constructing a Biomass-data Center Nexus for Circular Economy-Based Energy Systems Integration

IEEE Open Access Journal of Power and Energy

引用

IEEE Open Access Journal of Power and Energy 2025年 12卷 270-283页

作者： Wang, Pengya Pan, Li He, Guannan Li, Gengyin Song, Jie Zhou, Ming Wang, Jianxiao State Grid Dezhou Power Supply Company Shandong Dezhou253000 China The Chinese University of Hon g Kong School of Science and Engineering Guangdong Shenzhen518000 China Peking University College of Engineering Department of Industrial Engineering and Management Beijing100871 China North China Electric Power University State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources Beijing102206 China Peking University National Engineering Laboratory for Big Data Analysis and Applications Beijing100871 China

The dual challenges of energy crises and waste management have spurred interest in a circular economy, where biomass, valued for its carbon neutrality, is crucial. Remote areas, rich in biomass, are also becoming hubs for data center (DC) construction. Despite DCs’ low energy efficiency and production of low-grade waste heat, recovering this heat offers a promising path toward a circular economy. There are few systematic studies on the relationships among DC energy supply, waste heat generation, and renewable energy resources. In this study, we formulate day-ahead, real-time optimal scheduling strategies to provide electricity, heat, and gas using a complementary photovoltaic-biomass system. The biogas production process requires heat to promote the anaerobic reaction, and the adaptation temperature of anaerobic bacteria matches the low-quality waste heat generated from of the DC. We realize a circular economy by coupling a DC and a renewable energy system by directly using the waste heat from the DC and by using the queuing theory of the DC’s delay tolerance workload for partial load response. Moreover, the nonlinearity in the process is linearized by the least squares method. Actual data calculations show that the introduction of biogas can result in a fully renewable energy supply. Based on specific configurations—including a 350 kW PV system, 450 kWh BSS, 250 kW CHP unit, and an AD operating at 20°C to 45°C—the system is tested under 0% and 50% carbon emission scenarios. The DC workload combines delay-tolerant and delay-sensitive tasks, enabling flexible scheduling for energy and heat optimization, the power usage effectiveness (PUE) of the DC decreases from 1.73 to 1.24, operating expenses decrease by 36.06%, and system energy consumption decreases by 44.6%. © 2020 IEEE.

关键词： Waste heat utilization

来源：评论

学校读者我要写书评

暂无评论

Network intrusion detection based on feature fusion of attack dimension

引用

Journal of Supercomputing 2025年第6期81卷 1-33页

作者： Sun, Xiaolong Gu, Zhengyao Zhang, Hao Gu, Jason Liu, Yanhua Dong, Chen Ye, Junwei College of Computer and Data Science Fuzhou University Fuzhou350116 China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou350116 China Engineering Research Center of Big Data Intelligence Chinese Ministry of Education Fuzhou350116 China Department of Electrical and Computer Engineering Dalhousie University HalifaxNSB3J 1Z1 Canada

Network traffic anomaly detection involves the rapid identification of intrusions within a network through the detection, analysis, and classification of network traffic data. The variety of cyberattacks encompasses diverse attack principles. Employing an indiscriminate feature selection strategy may lead to the neglect of key features highly correlated with specific attack types. This oversight could diminish the recognition rate for that category, thereby impacting the overall performance of the detection model. To address this issue, this paper proposes a network traffic anomaly detection model based on the fusion of attack-dimensional features. Firstly, construct binary classification datasets independently for each attack class and perform individual feature selection to extract positively correlated features for each class. The features are then fused by employing a combination methods. Subsequently, based on the fused sub-datasets, base classifiers are trained. Finally, an ensemble learning approach is introduced to integrate the predictions of individual classifiers, enhancing the robustness of the model. The proposed approach, validated on NSL-KDD and UNSW-NB15 benchmark datasets, outperforms the latest methods in the field by achieving a 2% and 7% increase in precision on weighted averages. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Personalized Hierarchical Federated Learning towards Heterogeneous Internet of Vehicles

引用

IEEE Internet of Things Journal 2025年第11期12卷 16349-16362页

作者： Zhang, Puning Shao, Shuman Wu, Chao Yang, Zhigang Zhang, Ruoying Chongqing University of Posts and Telecommunications School of Communications and Information Engineering Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China Chongqing400065 China Chongqing Innovation Center of Industrial Big-Data Co. Ltd National Engineering Laboratory for Industrial Big-data Application Technology Chongqing400707 China China Merchants Testing Vehicle Technology Research Institute Co. Ltd Chongqing404100 China Chongqing University of Posts and Telecommunications School of Cyber Security and Information Law Chongqing400065 China Chongqing Key Laboratory of Ubiquitous Sensing and Networking Advanced Network and Intelligent Connection Technology Key Laboratory of Chongqing Education Commission of China China China Academy of Information and Communications Beijing100083 China

High mobility and non-independent and identically distributed (non-iid) data in the Internet of Vehicles (IoV) pose challenges for the convergence speed and accuracy of federated learning model training. Traditional federated learning approaches fail to account for the unique characteristics of local vehicle data, limiting the model performances. To address this, we propose a personalized hierarchical federated learning method tailored for heterogeneous IoV. Our approach customizes models for each vehicle, enhancing their performance on local data. We introduce a network-aware client selection method that dynamically chooses vehicle clients based on their spatiotemporal distribution and changing channel conditions. Additionally, our fine-grained personalized learning method leverages frequency domain analysis to extract and retain both fundamental and personalized knowledge from local model parameters. This allows us to build highly accurate personalized models suited to each vehicle's data characteristics. Experimental results show that our method improves model accuracy by up to 10.31% and reduces training time by up to 24.93% compared to the latest personalized federated learning algorithms. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Secure Multi-way Join Query and Its Bench-Marking with Trusted Execution Environments 2nd

Secure Multi-way Join Query and Its Bench-Marking with Tru...

引用

2nd International Conference on data Security and Privacy Protection, DSPP 2024

作者： Zhao, Yi Zhao, Sen Lv, Siyi School of Cyber Engineering Xidian University Xi’an China State Key Laboratory of Integrated Service Networks Xidian University Xi’an China Key Laboratory of Data and Intelligent System Security Ministry of Education Nankai University Tianjin China

ISBN: (纸本)9789819785452

Because of server-untrustable model in outsourcing encrypted database system, it’s fatal for data owners to keep their data confidential under complex query operations performed by database servers. Trusted Execution Environments (TEEs) provide a secure space for privacy computation via hardware-based methods to increase the efficiency of database system, and it ensures the availability of computing directly on sensitive data in untrusted outsourcing database servers. However, while various query schemes are designed under the combination of encrypted database and TEEs, designing an available and secure scheme for join queries on multiple data tables with TEEs remains an open problem. Besides, previous works also devote less to bench-marking multi-way joins on TEEs. In our work, we extend binary join query scheme into multi-way forms in encrypted database system based on TEEs. It combines various join algorithms based on hash functions (hash-based, radix-based, etc.) with parallelized optimizing mechanism. Besides, we do bench-marking with TEEBench framework on those multi-way join schemes in three-way forms using both cache-fit and cache-exceed datasets and do different evaluation on two TEEs hardware platforms (Intel SGX and AMD SEV) to show its availability. After that, we also propose a multi-way join scheme with access pattern protection through the combination between our previous scheme and oblivious I/O methods. With the evaluation of its efficiency and memory leakage, we can also verify the feasibility of our access-pattern-protected multi-way join scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Outsourcing

来源：评论

学校读者我要写书评

暂无评论

LoRS: Efficient Low-Rank Adaptation for Sparse Large Language Model

arXiv

引用

arXiv 2025年

作者： Hu, Yuxuan Zhang, Jing Chen, Xiaodong Zhao, Zhe Li, Cuiping Chen, Hong School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering Beijing China Engineering Research Center of Database and Business Intelligence Beijing China Tencent AI Lab Beijing China

Existing low-rank adaptation (LoRA) methods face challenges on sparse large language models (LLMs) due to the inability to maintain sparsity. Recent works introduced methods that maintain sparsity by augmenting LoRA techniques with additional masking mechanisms. Despite these successes, such approaches suffer from an increased memory and computation overhead, which affects efficiency of LoRA methods. In response to this limitation, we introduce LoRS, an innovative method designed to achieve both memory and computation efficiency when fine-tuning sparse LLMs. To mitigate the substantial memory and computation demands associated with preserving sparsity, our approach incorporates strategies of weight recompute and computational graph rearrangement. In addition, we also improve the effectiveness of LoRS through better adapter initialization. These innovations lead to a notable reduction in memory and computation consumption during the fine-tuning phase, all while achieving performance levels that outperform existing LoRA approaches. © 2025, CC BY.

关键词： Problem oriented languages

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：