检索结果-内蒙古大学图书馆

IEEE International Conference on Communications in China (ICCC)

作者： ZhangMengru Zhao Fan Wu Huaqing Wu Tong Liu Conghao Zhou Jun Ma Yongmin Zhang Feng Lyu School of Computer Science and Engineering Central South University Changsha China Department of Electrical and Software Engineering University of Calgary Calgary AB Canada Big Data Institute Central South University Changsha China Department of Electrical and Computer Engineering University of Waterloo Waterloo Ontario Canada Hunan Energy Big Data Intelligence Limited Changsha China

ISBN: (数字)9798350378412

ISBN: (纸本)9798350378429

Non-intrusive load monitoring (NILM) is a promising approach for recognizing various electrical equipment energy usage patterns from aggregate load data. In this paper, we investigate the development of an NILM model to achieve high recognition accuracy, ensure a small model size for lightweight implementation, and enhance its adaptability to a wide range of appliance types. Specifically, we propose a framework named DCML, which employs dilated convolution to precisely control the receptive field, allowing efficient adjustments in feature extraction granularity to meet the specific requirements of different appliances. In addition, multi-task learning techniques are incorporated to allow simultaneous recognition of multiple appliances from a single model, saving model space while ensuring high recognition accuracy. Compared to the benchmark, our model reduces the recognition mean absolute error (MAE) by $36.8 \%, 16.8 \%$, and $43.8 \%$ for fridges, microwaves, and washing machines, respectively. Furthermore, the proposed DCML can significantly save the storage space of convolutional layers when simultaneously recognizing multiple appliances.

关键词： Adaptation models Accuracy Convolution Multitasking data models Stability analysis Robustness

来源：评论

学校读者我要写书评

暂无评论

Research and Design of Remote Online Supervision System of Coal Mine Electromechanical Equipment 3

Research and Design of Remote Online Supervision System of C...

引用

2021 3rd International Conference on Computer, Communications and Mechatronics engineering, CCME 2021

作者： Chen, Yunqi Xu, Jin China Coal Technology Engineering Group Chongqing Research Institute No. 6 Kecheng Road Jiulongpo District Chongqing China School of Big Data and Software Enginecring Chongqing University Chongqing400000 China

Increasing the supervision of coal mine electromechanical equipment is an urgent need to ensure the safe production of coal mines. This paper designs and develops a coal mine electromechanical equipment supervision system, which includes four parts: mine-side monitoring subsystem, mine-side data acquisition and transmission module, local-side data analysis and storage module, and coal mine electromechanical equipment supervision platform. It realizes coal mine ventilator, drainage pump, air compressors, hoists and other major electromechanical equipment online monitoring and equipment failure analysis. The system satisfies the remote online inspection and management of equipment by multi-level departments, reduces the possibility of enterprise accidents, innovates the supervision mode, and improves the efficiency of supervision. © Published under licence by IOP Publishing Ltd.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Robust Network Optimization by Deep Generative Models and Stochastic Optimization

引用

IEEE Transactions on Wireless Communications 2025年

作者： Zhang, Shutao Xue, Ye Tang, Zhiwei Wang, Hao Shen, Chao Shi, Qingjiang Chang, Tsung-Hui The Chinese University of Hon g Kong School of Science and Engineering Shenzhen China Shenzhen Research Institute of Big Data Shenzhen China The Chinese University of Hon g Kong School of Data Science Shenzhen China Shenzhen Research Institute of Big Data Shenzhen International Center for Industrial and Applied Mathematics China Guangdong Provincial Engineering Technology Research Center for Intelligent Industrial Digital Twin and Optimization Shenzhen518172 China Tongji University School of Software Engineering Shanghai China

Wireless network optimization is essential for improving the network performance in mobile communications. However, due to the stochastic nature of wireless networks, existing schemes based on analytical models and deterministic optimization are less reliable. To this end, we design a framework for robust network optimization based on deep generative models and stochastic optimization. Inspired by the powerful diffusion process, we propose a deep generative simulator to capture the statistical distribution of the network performance. By sampling from the deep generative simulator, we can alleviate the inherent uncertainty related to the network performance and devise an innovative expectation-quantile-based stochastic objective function. The inner expectation is designed for the temporal statistics, while the outer quantile is developed for the spatial statistics. This designated two-tier objective function is capable of mitigating temporal fluctuations and ensuring satisfactory network performance across most geographical grids, thereby achieving robustness. To solve this stochastic optimization problem, a smooth zeroth-order approach is introduced by taking advantage of the unique structure of quantile functions. Through theoretical performance analysis and simulation experiments with real-world datasets, we demonstrate the superiority of our approach over other baseline schemes, highlighting its practical utility in robust network optimization. © 2002-2012 IEEE.

关键词： Generative diffusion model quantile function robust approach wireless network optimization

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Multi-Keyword Fuzzy Adjacency Search Strategy for Encrypted Graph in Cloud Environment

引用

Computers, Materials & Continua 2024年第3期78卷 3177-3194页

作者： Bin Wu Xianyi Chen Jinzhou Huang Caicai Zhang Jing Wang Jing Yu Zhiqiang Zhao Zhuolin Mei School of Computer and Big Data Science Jiujiang UniversityJiujiang332005China Jiujiang Key Laboratory of Network and Information Security Jiujiang332005China School of Computer and Software Nanjing University of Information Science&TechnologyNanjing210044China School of Computer Engineering Hubei University of Arts and ScienceXiangyang441053China School of Modern Information Technology Zhejiang Institute of Mechanical and Electrical EngineeringHangzhou310053China Information Center Jiangxi Changjiang Chemical Co.Ltd.Jiujiang332005China School of Mathematics and Computer Science Ningxia Normal UniversityGuyuan756099China

In a cloud environment,outsourced graph data is widely used in companies,enterprises,medical institutions,and so *** owners and users can save costs and improve efficiency by storing large amounts of graph data on cloud *** on cloud platforms usually have some subjective or objective attacks,which make the outsourced graph data in an insecure *** issue of privacy data protection has become an important obstacle to data sharing and *** to query outsourcing graph data safely and effectively has become the focus of *** query is a basic and frequently used operation in graph,and it will effectively promote the query range and query ability if multi-keyword fuzzy search can be supported at the same *** work proposes to protect the privacy information of outsourcing graph data by encryption,mainly studies the problem of multi-keyword fuzzy adjacency query,and puts forward a *** our scheme,we use the Bloom filter and encryption mechanism to build a secure index and query token,and adjacency queries are implemented through indexes and query tokens on the cloud *** proposed scheme is proved by formal analysis,and the performance and effectiveness of the scheme are illustrated by experimental *** research results of this work will provide solid theoretical and technical support for the further popularization and application of encrypted graph data processing technology.

关键词： Privacy-preserving adjacency query multi-keyword fuzzy search encrypted graph

来源：评论

学校读者我要写书评

暂无评论

Evaluate-and-Purify: Fortifying Code Language Models Against Adversarial Attacks Using LLM-as-a-Judge

arXiv

引用

arXiv 2025年

作者： Mu, Wenhan Xu, Ling Pei, Shuren Mi, Le Zhou, Huichi School of Big Data and Software Engineering Chongqing University Chongqing China Imperial College London Exhibition Road LondonSW7 2AZ United Kingdom

The widespread adoption of code language models in software engineering tasks has exposed vulnerabilities to adversarial attacks, especially the identifier substitution attacks. Although existing identifier substitution attackers demonstrate high success rates, they often produce adversarial examples with unnatural code patterns. In this paper, we systematically assess the quality of adversarial examples using LLM-as-a-Judge. Our analysis reveals that over 80% of adversarial examples generated by state-of-the-art identifier substitution attackers (e.g., ALERT) are actually detectable. Based on this insight, we propose EP-Shield, a unified framework for evaluating and purifying identifier substitution attacks via naturalness-aware reasoning. Specifically, we first evaluate the naturalness of code and identify the perturbed adversarial code, then purify it so that the victim model can restore correct prediction. Extensive experiments demonstrate the superiority of EP-Shield over adversarial fine-tuning (up to 83.36% improvement) and its lightweight design (7B parameters) with GPT-4-level performance. © 2025, CC BY.

关键词： software quality

来源：评论

学校读者我要写书评

暂无评论

Optimization of a Deep Learning Algorithm for Security Protection of big data from Video Images

引用

Computational Intelligence and Neuroscience 2022年第0期2022卷 3394475页

作者： Geng, Qiang Yan, Huifeng Lu, Xingru School of Big Data and Software Engineering Chongqing College of Mobile Communication Chongqing401520 China Chongqing Key Laboratory of Public Big Data Security Technology Chongqing401420 China School of Software Engineering Chongqing University of Posts and Telecommunications Chongqing400065 China

With the rapid development of communication technology, digital technology has been widely used in all walks of life. Nevertheless, with the wide dissemination of digital information, there are many security problems. Aiming at preventing privacy disclosure and ensuring the safe storage and sharing of image and video data in the cloud platform, the present work proposes an encryption algorithm against neural cryptography based on deep learning. Primarily, the image saliency detection algorithm is used to identify the significant target of the video image. According to the significant target, the important region and nonimportant region are divided adaptively, and the encrypted two regions are reorganized to obtain the final encrypted image. Then, after demonstrating how attackers conduct attacks to the network under the ciphertext attack mode, an improved encryption algorithm based on selective ciphertext attack is proposed to improve the existing encryption algorithm of the neural network. Besides, a secure encryption algorithm is obtained through detailed analysis and comparison of the security ability of the algorithm. The experimental results show that Bob's decryption error rate will decrease over time. The average classification error rate of Eve increases over time, but when Bob and Alice learn a secure encryption network structure, Eve's classification accuracy is not superior to random prediction. Chosen ciphertext attack-advantageous neural cryptography (CCA-ANC) has an encryption time of 14s and an average speed of 69mb/s, which has obvious advantages over other encryption algorithms. The self-learning secure encryption algorithm proposed here significantly improves the security of the password and ensures data security in the video image. © 2022 Qiang Geng et al.

关键词： Cryptography

来源：评论

学校读者我要写书评

暂无评论

Reentrancy Vulnerability Detection and Localization: A Deep Learning Based Two-phase Approach 22

Reentrancy Vulnerability Detection and Localization: A Deep ...

引用

Proceedings of the 37th IEEE/ACM International Conference on Automated software engineering

作者： Zhuo Zhang Yan Lei Meng Yan Yue Yu Jiachi Chen Shangwen Wang Xiaoguang Mao School of Big Data & Software Chongqing University China College of Computer National University of Defense Technology China School of Software Engineering Sun Yat-sen University China

ISBN: (纸本)9781450394758

Smart contracts have been widely and rapidly used to automate financial and business transactions together with blockchains, helping people make agreements while minimizing trusts. With millions of smart contracts deployed on blockchain, various bugs and vulnerabilities in smart contracts have emerged. Following the rapid development of deep learning, many recent studies have used deep learning for vulnerability detection to conduct security checks before deploying smart contracts. These approaches show effective results on detecting whether a smart contract is vulnerable or not whereas their results on locating suspicious statements responsible for the detected vulnerability are still unsatisfactory. To address this problem, we propose a deep learning based two-phase smart contract debugger for reentrancy vulnerability, one of the most severe vulnerabilities, named as ReVulDL: Reentrancy Vulnerability Detection and Localization. ReVulDL integrates the vulnerability detection and localization into a unified debugging pipeline. For the detection phase, given a smart contract, ReVulDL uses a graph-based pre-training model to learn the complex relationships in propagation chains for detecting whether the smart contract contains a reentrancy vulnerability. For the localization phase, if a reentrancy vulnerability is detected, ReVulDL utilizes interpretable machine learning to locate the suspicious statements in smart contract to provide interpretations of the detected vulnerability. Our large-scale empirical study on 47,398 smart contracts shows that ReVulDL achieves promising results in detecting reentrancy vulnerabilities (e.g., outperforming 16 state-of-the-art vulnerability detection approaches) and locating vulnerable statements (e.g., 70.38% of the vulnerable statements are ranked within Top-10).

关键词： Smart contract fault localization reentrancy vulnerability vulnerability detection

来源：评论

学校读者我要写书评

暂无评论

PFME: A Modular Approach for Fine-grained Hallucination Detection and Editing of Large Language Models

arXiv

引用

arXiv 2024年

作者： Deng, Kunquan Huang, Zeyu Li, Chen Lin, Chenghua Gao, Min Rong, Wenge SCSE Beihang University China ILCC The University of Edinburgh United Kingdom DCS University of Manchester United Kingdom School of Big Data and Software Engineering Chongqing University China

Large Language Models (LLMs) excel in fluency but risk producing inaccurate content, called "hallucinations." This paper outlines a standardized process for categorizing fine-grained hallucination types (Mishra et al., 2024) and proposes an innovative framework—the Progressive Fine-grained Model Editor (PFME)—specifically designed to detect and correct fine-grained hallucinations in LLMs. PFME consists of two collaborative modules: the Real-time Fact Retrieval Module and the Fine-grained Hallucination Detection and Editing Module. The former identifies key entities in the document and retrieves the latest factual evidence from credible sources. The latter further segments the document into sentence-level text and, based on relevant evidence and previously edited context, identifies, locates, and edits each sentence’s hallucination type. Experimental results on FavaBench and FActScore demonstrate that PFME outperforms existing methods in fine-grained hallucination detection tasks. Particularly, when using the Llama3-8B-Instruct model, PFME’s performance in fine-grained hallucination detection with external knowledge assistance improves by 8.7 percentage points (pp) compared to ChatGPT. In editing tasks, PFME further enhances the FActScore of FActScore-Alpaca13B and FActScore-ChatGPT datasets, increasing by 16.2pp and 4.6pp, respectively. © 2024, CC BY.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

BIM: Improving Graph Neural Networks with Balanced Influence Maximization 40

BIM: Improving Graph Neural Networks with Balanced Influence...

引用

40th IEEE International Conference on data engineering, ICDE 2024

作者： Zhang, Wentao Gao, Xinyi Yang, Ling Cao, Meng Huang, Ping Shan, Jiulong Yin, Hongzhi Cui, Bin Peking University Center for Machine Learning Research China Institute of Advanced Algorithms Research Shanghai China National Engineering Labratory for Big Data Analytics and Applications The University of Queensland Australia Peking University Key Lab of High Confidence Software Technologies China Apple Inc. Institute of Computational Social Science Peking University Qingdao China

ISBN: (纸本)9798350317152

The imbalanced data classification problem has aroused lots of concerns from both academia and industry since data imbalance is a widespread phenomenon in many real-world scenarios. Although this problem has been well researched from the view of imbalanced class samples, we further argue that graph neural networks (GNNs) expose a unique source of imbalance from the influenced nodes of different classes of labeled nodes, i.e., labeled nodes are imbalanced in terms of the number of nodes they influenced during the influence propagation in GNNs. To tackle this previously unexplored influence-imbalance issue, we connect social influence maximization with the imbalanced node classification problem and propose balanced influence maximization (BIM). Specifically, BIM greedily assigns the pseudo label to the node which can maximize the number of influenced nodes in GNN training while making the influence of each class more balance. Experimental results on five public datasets demonstrate the effectiveness of our method in relieving the influence-imbalance issue. For example, when training a GCN with an imbalance ratio of 0.1, BIM significantly outperforms the most competitive baseline by 0.6% -9.8% in five public datasets in terms of the F1 score. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Why not Just Look for Answers? Using a More Direct Way for API Recommendation

Why not Just Look for Answers? Using a More Direct Way for A...

引用

Asia-Pacific Conference on software engineering

作者： Changxin Liu Ling Xu Wenhan Mu Rui Qin Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China

ISBN: (数字)9798331534011

ISBN: (纸本)9798331534028

Automated API recommendation technology can help developers quickly find target APIs that meet their require-ments. Some retrieval-based API recommendation approaches, such as BIKER and CLEAR, adopt an indirect API recommen-dation strategy. Although these approaches have shown good performance, we observed two limitations in these approaches: (1) These approaches heavily relies on the coverage of the collected question titles proposed by developers; (2) These approaches ignore the API source code information. To overcome the two limitations, we propose an approach named AnsAPIRec (Answer- directed API Recommendation), which leverages a pre-trained model and joint-attention mechanism in this paper. In addition to the fully qualified name of the API, AnsAPIRec extracts the corresponding source code from the JDK as an additional feature. AnsAPIRec adopts a direct API recommendation strategy, which directly calculates the similarity between user queries and API features, i.e., API fully qualified name and API source code, to find the target API, alleviating the reliance on question titles. To further enhance AnsAPIRec's ability to understand the semantics of the inputs, we propose a joint-attention mechanism to learn the interdependent representations between the queries and API features. This deep semantic fusion mechanism enables AnsAPIRec to perform well in understanding user intent and API functionality. We reused the APIBench-Q dataset, containing 5885 queries for training and 653 queries for testing. The experimental result shows that AnsAPIRec achieved an MRR of 0.473, significantly outperforming the baseline approaches, BIKER and CLEAR.

关键词： Training Source coding Semantics Feature extraction Testing software engineering

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：