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

Stackelberg Game-Based Pricing and Offloading for the DVFS-Enabled MEC Systems

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2502-2515页

作者： Mei, Jing Zeng, Cuibin Tong, Zhao Yang, Zhibang Li, Keqin Hunan Normal University College of Information Science and Engineering Changsha410081 China Changsha University Hunan Province Key Laboratory of Industrial Internet Technology and Security Hunan Changsha410022 China Hunan University College of Information Science and Engineering Changsha410012 China Ministry of Science and Technology PRC National Supercomputing Center Hunan Changsha410082 China State University of New York Department of Computer Science New YorkNY12561 United States

Due to the limited computing resources of both mobile devices (MDs) and the mobile edge computing (MEC) server, devising reasonable strategies for MD task offloading, MEC server resource pricing, and resource allocation is crucial. In this paper, a scenario is considered, comprising multiple MDs and a single MEC server. Each MD has a divisible task in each time slot, allowing for partial offloading and the option to discard parts of the task. The MEC server contains multiple computing units with the same computing power, and its computing resources can be dynamically adjusted through dynamic voltage and frequency scaling (DVFS) according to the size of tasks offloaded by MDs. At any given time slice, a Stackelberg game is formulated based on the strategies of the MDs and the strategy of the MEC server. An iterative evolution algorithm is employed to explore the optimal strategies for MDs and the MEC server. Simulation results demonstrate that both parties can reach an equilibrium state through the game, and these experiments confirm that the algorithm effectively enhances system efficiency. © 2004-2012 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

Facile and adjustable production of self-standing oxygen-doped graphene membranes for optimized oxygen evolution electrocatalysis

引用

Nano Materials science 2025年第2期7卷 231-239页

作者： Liang Chen Lanyun Yang Liying Hu Minghao Jin Chenxi Xu Binhong He Wei Wang Ying Liu Gangyong Li Zhaohui Hou Key Laboratory of Hunan Province for Advanced Carbon-based Functional Materials School of Chemistry and Chemical EngineeringHunan Institute of Science and TechnologyYueyang414006HunanChina College of Materials Science and Engineering Central South University of Forestry and TechnologyChangsha410004HunanChina

Owing to abundant resource and affordable price,metal-free carbon has been extensively studied in the field of oxygen reduction reaction,while the related studies on oxygen evolution reaction(OER)are quite *** this work,a facile and scalable knife coating coupled with annealing strategy is proposed to produce self-standing oxygen-doped graphene membranes(marked as O-GM-T,T represents the annealing temperature).Through systematic characterization and analysis,it is discovered the annealing treatment not only decreases the amount of oxygenic groups,but allows for controlled regulation of the oxygen configurations,leaving only C-OH/C-O-C and C=***,theoretical calculations indicate that the OER activity trend of different oxygen configurations is as follows:-COOH>C=O≈C-OH>*** the removal of highly active-COOH group through annealing treatment,the resulting O-GM-800 sample maintains good mechanical property and achieves a favorable balance on conductivity,hydrophilicity and catalytic ***,it displays significantly improved OER performance compared to the counterparts,making it highly promising for applications in overall water splitting ***,our work provides guidance for the rational design and controllable fabrication of self-standing carbon-based catalysts for energy-related reactions.

关键词： Self-standing Oxygen-doped graphene membrane Knife coating Oxygen evolution reaction Catalytic activity

来源：评论

学校读者我要写书评

暂无评论

Advances of Pipeline Model Parallelism for Deep Learning Training:An Overview

引用

Journal of computer science & technology 2024年第3期39卷 567-584页

作者：关磊李东升梁吉业王文剑葛可适卢锡城 College of Science National University of Defense TechnologyChangsha 410073China College of Computer National University of Defense TechnologyChangsha 410073China School of Computer and Information Technology Shanxi UniversityTaiyuan 030006China CCF IEEE

Deep learning has become the cornerstone of artificial intelligence,playing an increasingly important role in human production and ***,as the complexity of problem-solving increases,deep learning models become increasingly intricate,resulting in a proliferation of large language models with an astonishing number of *** model parallelism(PMP)has emerged as one of the mainstream approaches to addressing the significant challenge of training“big models”.This paper presents a comprehensive review of *** covers the basic concepts and main challenges of *** also comprehensively compares synchronous and asynchronous pipeline schedules for PMP approaches,and discusses the main techniques to achieve load balance for both intra-node and inter-node ***,the main techniques to optimize computation,storage,and communication are presented,with potential research directions being discussed.

关键词： deep learning pipeline schedule load balance multi-GPU system pipeline model parallelism(PMP)

来源：评论

学校读者我要写书评

暂无评论

LSTM-Based Model Compression for CAN Security in Intelligent Vehicles

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 6457-6471页

作者： Feng, Yuan Lai, Yingxu Chen, Ye Zhang, Zhaoyi Wei, Jingwen Beijing University of Technology College of Computer Science Beijing100124 China

The rapid deployment and low-cost inference of controller area network (CAN) bus anomaly detection models on intelligent vehicles can drive the development of the Green Internet of Vehicles. Anomaly detection on intelligent vehicles often utilizes recurrent neural network models, but computational resources for these models are limited on small platforms. Model compression is essential to ensure CAN bus security with restricted computing resources while improving model computation efficiency. However, the existence of shared cyclic units significantly constrains the compression of recurrent neural networks. In this study, we propose a structured pruning method for long short-term memory (LSTM) based on the contribution values of shared vectors. By analyzing the contribution value of each dimension of shared vectors, the weight matrix of the model is structurally pruned, and the output value of the LSTM layer is supplemented to maintain the information integrity between adjacent network layers. We further propose an approximate matrix multiplication calculation module that runs in the whole process of model calculation and is deployed in parallel with the pruning module. Evaluated on a realistic public CAN bus dataset, our method effectively achieves highly structured pruning, improves model computing efficiency, and maintains performance stability compared to other compression methods. © 2024 IEEE.

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Discrete-time double-integral zeroing neural dynamics for time-varying equality-constrained quadratic programming with application to manipulators

引用

Neural Computing and Applications 2024年第4期37卷 1905-1918页

作者： Xiang, Qiuhong Gong, Hongfang College of Mathematics and Statistics Changsha University of Science and Technology Hunan Changsha410114 China

Neural dynamics remains a crucial field of interest for researchers, owing to its extensive applicability in addressing time-varying challenges across diverse domains. This study innovatively integrates discrete-time processing with neural dynamics principles, introducing a discrete-time double-integral zeroing neural dynamics (DTDIZND) method to address real-time-varying equality-constrained quadratic programming (ECQP) problems in diverse noisy environments. The DTDIZND model offers a robust solution. Theoretical analyses reveal that the DTDIZND model excels in real-time calculations with remarkable precision, effectively managing multiple noise sources. For comparative analysis, the existing discrete-time zeroing neural dynamics models are evaluated, addressing the same time-varying problems. Relative numerical experiments have been undertaken, further strengthening the evidence of the DTDIZND model’s efficiency and preponderance in managing diverse noise scenarios. In addition, the DTDIZND method is applied to robot manipulator motion planning, particularly in scenarios where diverse noise sources pose challenges. It is a promising tool for addressing time-varying challenges in various domains given its ability to handle real-time calculations with precision, coupled with its resilience against noise. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Manipulators

来源：评论

学校读者我要写书评

暂无评论

Dynamic Cloth Folding Using Curriculum Learning

引用

Journal of Shanghai Jiaotong university (science) 2024年 1-10页

作者： Li, Mingyang Bao, Hujun Huang, Jin College of Computer Science and Technology Zhejiang University Hangzhou310058 China

This paper presents a novel algorithm for training robotic arms to manipulate cloth, by leveraging reinforcement learning and curriculum learning approaches. Traditional cloth manipulation algorithms rely heavily on predefined action primitives and assumptions about cloth dynamics, introducing significant prior knowledge. To circumvent this limitation, we utilize reinforcement learning to train our cloth folding agent. To fully utilize the advantage of reinforcement learning, we propose a semi-sparse reward function incorporating folding accuracy and a curriculum scheme to accelerate training and improve policy stability. We validate the proposed method by implementing it in the StableBaselines3 framework and training the agent using the soft actor critic algorithm in our virtual environment based on physical-based cloth simulator. Our results demonstrate the benefits of the curriculum learning scheme which increases sample efficiency and accelerates training process compared with previous reinforcement learning cloth manipulation method. © Shanghai Jiao Tong university 2024.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

StyleFlow: Disentangle Latent Representations via Normalizing Flow for Unsupervised Text Style Transfer 30

StyleFlow: Disentangle Latent Representations via Normalizin...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Zhu, Kangchen Tian, Zhiliang Wei, Jingyu Luo, Ruifeng Song, Yiping Mao, Xiaoguang College of Computer National University of Defense Technology Hunan China College of Science National University of Defense Technology Hunan China

ISBN: (纸本)9782493814104

Unsupervised text style transfer aims to modify the style of a sentence while preserving its content without parallel corpora. Existing approaches attempt to separate content from style, but some words contain both content and style information. It makes them difficult to disentangle, where unsatisfactory disentanglement results in the loss of the content information or the target style. To address this issue, researchers adopted a "cycle reconstruction" mechanism to maintain content information, but it is still hard to achieve satisfactory content preservation due to incomplete disentanglement. In this paper, we propose a new disentanglement-based method, StyleFlow, which effectively avoids the loss of contents through a better cycle reconstruction via a reversible encoder. The reversible encoder is a normalizing flow that can not only produce output given input but also infer the exact input given the output reversely. We design a stack of attention-aware coupling layers, where each layer is reversible and adopts the attention mechanism to improve the content-style disentanglement. Moreover, we propose a data augmentation method based on normalizing flow to enhance the training data. Our experiments on sentiment transfer and formality transfer tasks show that StyleFlow outperforms strong baselines on both content preservation and style transfer. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Hybrid compression for LSTM-based encrypted traffic classification model

引用

International Journal of Wireless and Mobile Computing 2024年第1期26卷 61-73页

作者： Mu, Qiaoxu Zhang, Meng College of Computer Science and Technology Jilin University Jilin Changchun China

Traditional techniques for network traffic classification are no longer effective in handling the complexities of dynamic network environments. Moreover, deep learning methods, while powerful, demand substantial spatial and computational resources, resulting in increased latency and instability. In this paper, we propose an innovative approach to network traffic classification utilising an LSTM structure. This approach incorporates network pruning, knowledge refinement, and Generative Adversarial Networks (GAN) to reduce model size, accelerate training speed without compromising accuracy, and address challenges associated with unbalanced datasets in classification problems. Our methodology involves the pruning of unimportant filters from the teacher model, followed by retraining and knowledge distillation to generate the student model. Experimental show that the size of the pruned teacher model is only 25.69% of the original, resulting in a noteworthy 28.16% improvement in training speed. Additionally, the classification performance of various unbalanced traffic categories, such as VoIP and streaming, shows significant enhancement. © 2024 Inderscience Publishers. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Molecular Design Through Learning Latent Pareto Set 39

Multi-Objective Molecular Design Through Learning Latent Par...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liu, Yiping Yang, Jiahao Ren, Xuanbai Zhang, Xinyi Liu, Yuansheng Song, Bosheng Zeng, Xiangxiang Ishibuchi, Hisao College of Computer Science and Electronic Engineering Hunan University China Department of Computer Science and Engineering Southern University of Science and Technology China

ISBN: (纸本)157735897X

Molecular design inherently involves the optimization of multiple conflicting objectives, such as enhancing bio-activity and ensuring synthesizability. Evaluating these objectives often requires resource-intensive computations or physical experiments. Current molecular design methodologies typically approximate the Pareto set using a limited number of molecules. In this paper, we present an innovative approach, called Multi-Objective Molecular design through Learning Latent Pareto Set (MLPS). MLPS initially utilizes an encoder-decoder model to seamlessly transform the discrete chemical space into a continuous latent space. We then employ local Bayesian optimization models to efficiently search for local optimal solutions (i.e., molecules) within predefined trust regions. Using surrogate objective values derived from these local models, we train a global Pareto set learning model to understand the mapping between direction vectors (called "preferences") in the objective space and the entire Pareto set in the continuous latent space. Both the global Pareto set learning model and local Bayesian optimization models collaborate to discover high-quality solutions and adapt the trust regions dynamically. Our work is an effective endeavor towards learning the Pareto set for multi-objective molecular design, providing decision-makers with the capability to fine-tune their preferences and thoroughly explore the Pareto set. Experimental results demonstrate that MLPS achieves state-of-the-art performance across various multi-objective scenarios, encompassing diverse objective types and varying numbers of objectives. The effectiveness of MLPS was further validated through real-world challenges in discovering antifungal peptides with low toxicity and high activity. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Set theory

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：