检索结果-内蒙古大学图书馆

A novel shilling attack on black-box recommendation systems for multiple targets

Neural Computing and Applications 2025年第5期37卷 3399-3417页

作者： Liu, Shuangyu Yu, Siyang Li, Huan Yang, Zhibang Duan, Mingxing Liao, Xiangke School of Information Science and Engineering Hunan University Hunan Changsha410082 China College of Information Technology and Management Hunan University of Finance and Economics Hunan Changsha410000 China Hunan Province Key Laboratory of Industrial Internet Technology and Security Changsha University Hunan Changsha410022 China Shenzhen Institute Hunan University Guangdong Shenzhen518063 China School of Computer Science National University of Defense Technology Hunan Changsha410073 China

In the digital era, e-platforms ubiquitously deploy recommendation systems, utilizing machine learning paradigms to tailor content according to user preferences and needs. Yet, the integrity of these systems is often compromised by shilling attacks, where malicious entities inject fake user profiles to skew product exposure and sales. This vulnerability has catalyzed research efforts to bolster the robustness and security of recommendation systems, primarily through controlled attacks and reinforcement training. This paper introduces an innovative approach to combat the inefficiency of traditional single-target shilling attacks. We propose a novel multi-target shilling strategy for black-box recommendation systems, capable of generating convincing and aggressive fake user profiles. Given the complexity of the recommendation system algorithms, we employ surrogate models to replicate and understand the target system’s behavior. The surrogate model is then subjected to attacks using our proposed methodology. An attack is deemed successful when it achieves an 80% or higher success rate against the surrogate, preluding an attack on the actual recommendation system. Our model, RWA-GAN, stands out by integrating two components: a generative adversarial network (GAN) for crafting realistic fake user profiles, and a mechanism to enhance attack success rates. This dual approach not only expedites the attack process but also ensures the generation of more authentic and well-distributed fake profiles, making the model easier to migrate. Additionally, the paper delineates several defense strategies against such attacks, contributing significantly to the discourse on enhancing the robustness of recommender systems. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

CASCAIN: Cascaded Attention Infused Networks for Named Entity Recognition in Code-Mixed Setting 6th

CASCAIN: Cascaded Attention Infused Networks for Named Entit...

引用

6th International Conference on Computational Intelligence in Communications and Business Analytics, CICBA 2024

作者： Kaoshik, Jay Vyas, Pranav Tripathy, B.K. Swarnalatha, P. Nagaraja, G. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore632014 India

ISBN: (纸本)9783031813351

Named Entity Recognition (NER), sometimes also referred to as Entity Extraction has been an integral part of Natural Language Understanding systems. To date, there have been continuous myriad efforts in linguistics and sequential modelling which have led to the development of reliable and highly efficient NER architectures. One frequent occurrence, however, is that most work done constitutes an inclination towards resource rich corpora. To bridge the grey space for real time code-mixed expressions, we present CASCAIN (Cascaded Attention Infused Network), which leverages attention for capturing sentence level context. We also experiment with multiple architectures involving varying number of recurrent units, attention types and stacking arrangements. To provide a comprehensive performance benchmark, we train and test our models on an extended set generated from two popular Hinglish datasets. Our best performing architecture incorporates Stacked Bi-Directional LSTM Units, each of which are paired with Attention Mechanisms for generating representations from Context Vector. CASCAIN achieves an accuracy of 94.31% on the Validation Set. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Topic-aware cosine graph convolutional neural network for short text classification

引用

Soft Computing 2024年第13-14期28卷 8119-8132页

作者： Min, Changrong Chu, Yonghe Lin, Hongfei Wang, Bolin Yang, Liang Xu, Bo Criminal Investigation Police University of China No.83 Tawan St Liaoning Shenyang China School of Computer Science and Technology Dalian University of Technology No. 2 Linggong Road Liaoning Dalian116024 China School of Information Science and Engineering Henan University of Technology No. 100 Lianhua Street Henan Zhengzhou450001 China

Graph Convolutional Network (GCN) has been extensively studied in the task of short text classification (STC), utilizing global graphs that incorporate texts at different levels of granularity to learn text embeddings. However, the GCN-based methods only focus on the alignment between ground-truth labels and predicted labels, overlooking the geometric structure implicitly encoded by the graph. To address this limitation, we propose a novel GCN-based method that is entitled Topic-aware Cosine GCN (ToCo-GCN) for the STC. The ToCo-GCN defines and captures underlying geometric structures of short texts from different categories in the cosine space. Specifically, the ToCo-GCN regards the within-class and between-class geometric structures as constraint, aiming to learn both representative and discriminative short text representations. Moreover, to mitigate the inherent sparsity problem of short texts, the ToCo-GCN augment the text graph with latent topics. Experimental results on 8 STC datasets demonstrate that the ToCo-GCN is superior to state-of-the-art baselines in terms of Accuracy and Macro-F1 score. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Secure Medical Data Management Based on Homomorphic Encryption and Secret Sharing

Secure Medical Data Management Based on Homomorphic Encrypti...

引用

8th IEEE International Conference on Smart Cloud, SmartCloud 2023

作者： Law, Po Ying Tsai, Chia-Cheng Fok, Tsz Wun Wang, Ching-Ting Chang, Chi-Hsien Chin, Tsung-Yu Liao, Yi-Chen Lee, Jen-Kuang Lin, Chung-Wei Department of Computer Science and Information Engineering Taiwan Department of Electrical Engineering Taiwan Department of Engineering Science and Ocean Engineering Taiwan School of Medicine National Taiwan University Taiwan

ISBN: (纸本)9798350313505

Medical data are highly sensitive and require secure storage systems to protect patients’ privacy. Centralized databases pose significant risks in the context of a breach, since all data are concentrated in a single location. Additionally, privacy concerns often prevent medical institutions from sharing data, hindering potential research breakthroughs. To address these challenges, we propose a novel cloud storage system that utilizes homomorphic encryption and secret sharing. Our approach enables secure cloud storage of medical data and allows for secure data sharing without compromising patients’ privacy. In addition to enhancing confidentiality, our proposed approach also improves data integrity and availability. We implement a proof-of-concept that demonstrates the feasibility of our storage system. ©2023 IEEE.

关键词： Cloud storage

来源：评论

学校读者我要写书评

暂无评论

Low-cost Granary Vehicles Positioning Using a Distributed LED Network 24

Low-cost Granary Vehicles Positioning Using a Distributed LE...

引用

24th IEEE International Conference on Communication Technology, ICCT 2024

作者： Liu, Jingya Ma, Pengtao Zhang, Lingmin Geng, Yu Yan, Lei Northeastern University School of Computer and Communication Engineering Qinhuangdao066004 China Hebei Normal University of Science and Technology Institute of Mathematics and Information Technology Qinhuangdao066004 China

ISBN: (纸本)9798350363760

To address the safety hazards and inefficiency of traditional manual grain depot management, the application of granary vehicles has emerged as a promising solution. However, the absence of GPS signals indoors and the cumulative errors inherent in inertial navigation system (INS) make it difficult for vehicles to achieve the required positioning accuracy for operations. To achieve accurate positioning in the grain depot work area, this paper proposes a distributed auxiliary positioning scheme based on a light emitting diode (LED) network, combined with a attitude angle-oriented variable state dimension (AAVSD)-Kalman filter to achieve low-cost and high-precision positioning. The scheme selects the positioning method according to the vehicle's attitude angle: LED network positioning is used when the attitude angle is within the certain threshold range. Simulation results show that the proposed scheme effectively solves the problem of INS cumulative error and significantly improves the positioning accuracy of granary vehicles without excessive budget. © 2024 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Radio Map Estimation via Latent-Domain Plug-and-Play Denoisers

Radio Map Estimation via Latent-Domain Plug-and-Play Denoise...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xu, Le Cheng, Lei Chen, Junting Pu, Wenqiang Fu, Xiao School of Electrical Engineering and Computer Science Oregon State University Corvallis United States College of Information Science and Electronic Engineering Zhejiang University Hangzhou China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China

ISBN: (纸本)9798350368741

Radio map estimation (RME) aims to construct a map of radio strength across multiple domains (e.g., space and frequency) from limited measurements. Data-driven deep neural model-based RME showed promising performance, yet requiring excessive training resources. This work puts forth an RME approach that can effectively incorporate learned information without training over radio map data. Our idea is to employ the plug-and-play (PnP) denoising scheme from computational imaging. The PnP framework allows incorporating denoisers trained over natural images to handle other types of data, e.g., ocean sound fields and medical images, due to the similarity of their denoising processes. Conventional PnP methods mostly use the learned denoisers in the data domain. Instead, the proposed approach applies PnP in the latent domain through a tailored algorithm design and spatial-spectral factorization of radio maps. This way, the proposed RME method exhibits enhanced scalability and noise robustness. Simulations are used to illustrate the effectiveness of the proposed approach. © 2025 IEEE.

关键词： plug-and-play algorithm design radio map estimation Spectrum cartography

来源：评论

学校读者我要写书评

暂无评论

Development of Fast Prediction System of User Action for a Fully Autonomous Smart Home System 4

Development of Fast Prediction System of User Action for a F...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Rajalakshmi, N.R. Sharmila, L. Prabu, S. Veeramakali, T. Arulkumaran, G. Chourasia, Pranshu Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu India School of Computing Srm Institute of Science and Technology Department of Computing Technologies Kattankulathur Chennai India School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Kattankulathur Chennai India School of Computing and Information Technology Reva University Karnataka Bangalore560064 India

ISBN: (纸本)9798331523923

The HVAC system, energy storage building, distributed power supply, and other equipment are integrated into the scheduling algorithm, which is aimed at reducing household electricity consumption. It is also assumed that users can provide energy to the grid according to their own conditions. Taking electricity cost and comfort level as optimization targets, a home energy optimization control model for the coordinated management of hybrid energy sources is built. A smart scheduling mechanism based on the improved adaptive particle swarm optimization approach is proposed in order to derive the best time intervals for electric appliances, necessary power for the control of the room temperature for every time frame, and power for charging and discharging of the storage battery at various moments. Simulation results show that through the incorporation of distributed photovoltaic power generation, backup storage by battery, and home energy optimization control, the system efficiently balances between user comfort and electricity consumption. This offers great technical support to the development of home energy management systems. By using time-of-use electricity price for energy acquisition and supply, the optimization control goal is minimizing both power use and cost as well as preserving comfort levels. The hybrid energy management's proposed home energy optimization control model uses an adaptive particle swarm optimization algorithm to find the optimal operation schedules of the electrical appliances, the required power for temperature control in a room, and the charge/discharge power level of the storage battery at each time interval. As per the optimization principle, the proposed dynamic programming algorithm converts the multi-stage problem into a sequence of single-stage problems and solves them separately. This method successfully resolves intricate problems that cannot be addressed through greedy algorithms or divide-and-conquer. In this research, management ac

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Improving Web Application Development Course 5

Improving Web Application Development Course

引用

5th National Conference of Saudi computers Colleges, NCCC 2022

作者： Gharaibeh, Natheer Khalif Taibah University College of Computer Science & Engineering at Yanbu Information Systems Department Yanbu Saudi Arabia

ISBN: (纸本)9798350333688

Providing students with the expertise of scientific and practical skills in Web development requires good preparation and practical competencies, the formation of positive attitudes toward the given course and determining suitable learning outcomes is one of the most important trends and issues in instructional design and technology. One of the most important challenges in this paper is to develop the relatively old course plan to cope with the rapid developments in the world of web application development, this requires Curriculum mapping to identify and address academic gaps, and redundancies. For purposes of improving the overall coherence of the course, its relationship with the other prerequisite courses should be explained more, some learning outcomes may be achieved through more than one course, therefore this study traced other related courses to the problem statement, such as Object-Oriented-Programming (OOP), Software Modelling and Design and other courses. This interconnected set of courses was motivated by the idea of Crosscutting concepts (CCCs) in Web Application Development, such as design patterns, Model-View-Controller (MVC), Entity Framework, Object Relational Mapping, Application Programming Interface (API), and others. This paper proposed some best practices and guidelines to take students gradually from a simple to more complicated tasks in learning Web development. © 2022 IEEE.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Deep Semantic-consistent Penalizing Hashing for Cross-modal Retrieval

引用

IEEE Transactions on Multimedia 2025年

作者： Qin, Qibing Wu, Lei Zhang, Wenfeng Huang, Lei Nie, Jie Weifang University School of Computer Engineering Weifang China Qufu Normal University School of Computer Science Rizhao China Chongqing Normal University College of Computer and Information Science Chongqing China Ocean University of China Faculty of Information Science and Engineering Qingdao China

Benefiting from the advantages of low storage cost and high retrieval efficiency, hash learning could significantly speed up large-scale cross-modal retrieval. Based on the prior annotations, most of the available cross-modal hashing usually introduces the margin-based constraint to generate different boundaries for each class in the inference phase, optimizing the model. However, these obtained label-guided penalty boundaries may differ from the primitive semantic relationships between heterogeneous modalities, impairing retrieval performance. Besides, the margin-based constraint is too weak to penalize the classes with low intra-class variances or inter-class correlations, which struggle to learn high-quality embeddings. In this paper, we propose a novel Deep Semantic-consistent Penalizing Hashing framework (DScPH) to learn the consistent penalizing fields for all classes, achieving accurate and efficient cross-modal retrieval. Specifically, by exploring unbalanced intra-class and inter-class correlations, the consistent penalizing loss is introduced into cross-modal retrieval to learn the consistency decision boundaries across classes. During training, the dice-like optimization strategy is developed to balance the pulling penalizing elements and pushing penalizing elements, facilitating the model convergence. Besides, based on the invariance of similarity measures under orthogonal transformations, the alternative quantization is proposed to minimize the errors between the learned continuous embeddings and binary discretization, maintaining the consistency of semantic relationships after performing binary projection. Extensive experiments are conducted on three benchmark datasets, and the comprehensive results validate the efficacy of our proposed DScPH framework, which outperforms the current mainstream deep cross-modal hashing algorithms. The source code of our proposed DScPH framework has been released at https://***/QinLab-WFU/DScPH. © 1999-2012 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

From Data to Diagnosis: Investigating Approaches in Mental Illness Detection 2

From Data to Diagnosis: Investigating Approaches in Mental I...

引用

2nd International Conference of Intelligent Methods, systems and Applications, IMSA 2024

作者： Montasser, Reem Kadry Mazen, Sherif A. Helal, Iman M. A. October University for Modern Sciences and Arts Faculty of Computer Science Software Engineering Department Giza Egypt Cairo University Faculty of Computers and Artificial Intelligence Information Systems Department Giza Egypt

ISBN: (纸本)9798350362633

Mental illness is a considerable global public health problem, impacting both individual well-being and society's health. The growing popularity of social media and the increase of other data sources led to more research interest in detecting mental illness with a particular focus on utilizing and fusing emotional information. Artificial intelligence techniques like natural language processing and others, have shown encouraging improvements in recognizing complex relationships in a wide range of textual data, including clinical notes, social media posts, and interviews. In this paper, we assess the different branches of artificial intelligence based on previous research in mental illness detection, discussing methods, trends, challenges, and future research directions. © 2024 IEEE.

关键词： Adversarial machine 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：