检索结果-内蒙古大学图书馆

Companion Proceedings of the ACM on Web Conference 2025

作者： Xu Zhang Peng Wang Chen Wang Zhe Xu Xiaohua Nie Wei Wang Shanghai Key Laboratory of Data Science School of Computer Science and Technology Fudan University Shang Hai China Shanghai Key Laboratory of Data Science School of Computer Science and Technology Fudan University Shanghai China National Engineering Research Center for Big Data Software Tsinghua University Beijing China School of Software Tsinghua University Beijing China National Key Laboratory of Strength and Structural Integrity Aircraft Strength Research Institute of China Xi'an Shaanxi China

ISBN: (纸本)9798400713316

Strain Gauge Status (SGS) recognition is crucial in the field of intelligent manufacturing based on the Internet of Things, as accurate identification helps timely detection of failed mechanical components, avoiding accidents. The loading and unloading sequences generated by strain gauges can be identified through time series classification (TSC) algorithms. Recently, deep learning models, e.g., convolutional neural networks (CNNs) have shown remarkable success in the TSC task, as they can extract discriminative local features from the subsequences to identify the time series. However, we observe only the local features may not be sufficient for expressing the time series, especially when the local sub-sequences between different time series are very similar, e.g., SGS data of aircraft wings in static strength experiments. Nevertheless, CNNs suffer from the limitation in extracting global features due to the nature of convolution operations. For extracting global features to more comprehensively represent the SGS time series, we propose two insights: (i) Constructing global features through feature engineering. (ii) Learning high-order relationships between local features to capture global features. To realize and utilize them, we propose a hypergraph-based global feature learning and fusion framework, which learns and fuses global features for semantic consistency to enhance the representation of SGS time series, thereby improving recognition accuracy. Our method designs are validated on industrial SGS and public UCR datasets, showing better generalization for unseen data in SGS recognition.

关键词： deep learning models

来源：评论

学校读者我要写书评

暂无评论

Provenance Based Intrusion Detection via Measuring Provenance Sequence Similarity

Provenance Based Intrusion Detection via Measuring Provenanc...

引用

2022 International Conference on Blockchain Technology and Information Security, ICBCTIS 2022

作者： Wu, Lin Xie, Y.L. Wu, Yafeng Liang, Jinyuan Li, Xuan School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Engineering Research Center on Big Data Security Wuhan China Nsfocus Inc. A9-3/F Optical Valley Software Park Wuhan China

ISBN: (数字)9781665496919

ISBN: (纸本)9781665496919

Malicious intrusion presents normalization and diversification in the current environment. Attackers often evade detection by changing the execution order of programs or adding many confusing operations. Aiming at the problem that the existing methods cannot accurately detect abnormal variant sequences, we propose PSSID, an intrusion detection method based on provenance sequence similarity. Firstly, the system data is transformed into a provenance graph, and each path in the provenance graph is regarded as a provenance sequence. Then the provenance sequence and the rule database sequence are compared to find the maximum common sequence length. Finally, according to the distribution of sequence lengths, obtain the two sequences' similarity value to judge whether it is abnormal. © 2022 IEEE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. China Cluster and Grid Computing Lab. China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

A Parallelizable Counterfactual Generation Method Based on Gradient Optimization 29

A Parallelizable Counterfactual Generation Method Based on G...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Ding, Haorun Jiang, Xuesong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China State Key Laboratory of High-end Server and Storage Technology Jinan China

ISBN: (纸本)9798350330717

Post-hoc explanations are important for people to understand the predictions of explanation models. One class of methods in post-hoc explanation is the generation of counterfactuals, where a hypothetical example is obtained by perturbing the inputs to show how one could obtain a different prediction from the decision model. Counter-factual explanations should satisfy several properties: One is that counterfactuals generated under specific scenarios and constraints should be feasible for users, i.e., they should accommodate different causal constraints. The other is that it is more desirable for users to have a wider variety of viable examples, i.e., counterfactual diversity. To this end, we propose a parallelizable method based on gradient optimization. We partition the input feasible domains, perform counterfactual generation independently for each feasible domain, and then parallelize the counterfactual generation process for each feasible domain. Experimental results show that our approach effectively improves the diversity, sparsity, and proximity of the generated counterfactual instances on the public datasets Adult-Income, Lending-Club, German-Credit, and COMPAS compared to other models. © 2023 IEEE.

关键词： counterfactual explanation machine learning parallel computing

来源：评论

学校读者我要写书评

暂无评论

Exploration and Practice of Civic Teaching in Cybersecurity Technology Specialized Courses under the Background of big data

引用

Applied Mathematics and Nonlinear sciences 2024年第1期9卷

作者： Yu, Kun School of Computer Engineering Jingchu University of Technology Hubei Jingmen448000 China Jingmen Cryptometry Application Technology Research Center Hubei Jingmen448000 China Big Data Research Center Jingchu University of Technology Hubei Jingmen448000 China

In recent years, curriculum Civics has begun to be widely used in higher education programs, providing new ideas and inspiration for the development and reform of higher education. The study integrates Civic Politics elements into the professional course of network security technology to teach Civic Politics in the curriculum. The improved TOPSIS method is used to construct a teaching evaluation model for the Civic Politics of Network Security Technology course, build an evaluation index system for the Civic Politics teaching effect of the Network Security Technology course, and determine the weights of the indexes at all levels. Factor analysis, difference analysis, and correlation analysis are carried out to analyze the situation of the network security technology course Civics. And explore the teaching effects of the network security technology course Civics. The highest score among the 15 factors of cyber course civics is cyber cultivation (8.89), while the lowest score is tenacity (7.77). There are significant differences in the factors of cultural confidence, dialectical thinking, aesthetic awareness, security awareness, and fairness and justice among students of different grades, and the factors of aesthetic awareness and fairness and justice among students of different disciplines become significantly different. There is a significant positive correlation between all the factors, among which the dialectical thinking factor has the strongest correlation with the total score of cybersecurity technology course civics. The total score of the teaching effect of the Civics of Cybersecurity Technology Course is 0.85, which is good. © 2024 Kun Yu, published by Sciendo.

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

DivLog: Log Parsing with Prompt Enhanced In-Context Learning

引用

International Conference on Software engineering (ICSE)

作者： Junjielong Xu Ruichun Yang Yintong Huo Chengyu Zhang Pinjia He School of Data Science The Chinese University of Hong Kong Shenzhen China Dept. of Computer Science & Engineering The Chinese University of Hong Kong China ETH Zurich Switzerland Shenzhen Research Institute of Big Data China

ISBN: (数字)9798400702174

ISBN: (纸本)9798350382143

Log parsing, which involves log template extraction from semi-structured logs to produce structured logs, is the first and the most critical step in automated log analysis. However, current log parsers suffer from limited effectiveness for two reasons. First, traditional data-driven log parsers solely rely on heuristics or handcrafted features designed by domain experts, which may not consistently perform well on logs from diverse systems. Second, existing super-vised log parsers require model tuning, which is often limited to fixed training samples and causes sub-optimal performance across the entire log source. To address this limitation, we propose Di-vLog, an effective log parsing framework based on the in-context learning (ICL) ability of large language models (LLMs). Specifically, before log parsing, DivLog samples a small amount of offline logs as candidates by maximizing their diversity. Then, during log parsing, DivLog selects five appropriate labeled candidates as examples for each target log and constructs them into a prompt. By mining the semantics of examples in the prompt, DivLog generates a target log template in a training-free manner. In addition, we design a straightforward yet effective prompt format to extract the output and enhance the quality of the generated log templates. We conducted experiments on 16 widely-used public datasets. The results show that DivLog achieves (1) 98.1% Parsing Accuracy, (2) 92.1% Precision Template Accuracy, and (3) 92.9% Recall Template Accuracy on average, exhibiting state-of-the-art performance.

关键词： Training Measurement Analytical models Semantics Feature extraction Tuning Software engineering

来源：评论

学校读者我要写书评

暂无评论

Mining User–Item Interactions via Knowledge Graph for Recommendation

引用

ACM Transactions on Recommender Systems 2025年第3期3卷 1-19页

作者： Shenghao Liu Lingyun Lu Bang Wang Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Smart Internet Technology School of Electronic Information and Communications Huazhong University of Science and Technology (HUST) Wuhan China

Introducing a Knowledge Graph (KG) to facilitate a recommender system has become a tendency in recent years. Many existing methods leverage KGs to obtain side information of items to promote item representation learning for enhancing recommendation performance. However, they ignore that KGs also may contribute to better user representation learning. To solve this issue, we propose a novel algorithm, the KIGR (Knowledge-aware Interaction Graph for Recommendation), to mine user–item interactions via KGs for assisting user representation learning. Specifically, a user–item interaction is encoded by attentively summing up the relation embedding about the item in the KG. Then, an unsupervised learning method is used to group the user–item interactions into different latent types. Further, a user–item interaction graph is divided into several subgraphs, which is referred to as a Knowledge-aware Interaction Graph, making each subgraph only contain one latent type of interaction. Finally, user representation is the fusion of user interest embedding, which is learned on the knowledge-aware interaction graph, whereas item representation is learned on the KG. Experimental results on MovieLens, LastFM and Amazon-Book validate that the proposed KIGR has a superior performance compared with the state-of-the-art algorithms.

关键词： Recommendation system knowledge graph graph neural network

来源：评论

学校读者我要写书评

暂无评论

Personalized Local Differential Privacy for Multi-dimensional Range Queries over Mobile User data

引用

IEEE Transactions on Mobile Computing 2025年

作者： He, Yuanyuan Wang, Meiqi Deng, Xianjun Yang, Peng Xue, Qiao Yang, Laurence T. Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Huazhong University of Science and Technology School of Electronic Information and Communications Wuhan430074 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210000 China

Multi-dimensional range queries performed on the mobile user data records become increasingly important and popular in the fields of e-commerce, social media, transportation logistics, etc. Meanwhile, mobile users usually have different privacy requirements for different attributes of the records. A straightforward and effective approach is to first get low-dimensional range query outcomes by using existing LDP mechanisms at different privacy levels, and then derive high-dimensional range query results at each level, and finally aggregate the results from all levels. However, it incurs low utility of the query results, since the non-fixed privacy budgets and the correlation between dimensions (attributes) detrimentally impact the utility of LDP methods, ultimately rendering them ineffective in practice. In this paper, we propose a new Personalized LDP approach for Multi-dimensional Range queries (PLDP-MR) over mobile user data, consisting of the user grouping, data perturbing, data re-perturbing, and range query results aggregating steps. First, PLDP-MR offers flexible dual grouping based on user-selected privacy levels and relevant attributes to obtain the corresponding one-dimensional and two-dimensional grids. PLDP-MR optimizes the grid granularity to minimize errors from perturbing users' attribute data with different LDP noises at non-fixed privacy levels. Furthermore, PLDP-MR carefully re-perturbs the LDP-noisy data from mobile users at lower privacy levels (i.e., having the higher utility) to achieve LDP with higher privacy levels and supplement the data volume of the corresponding groups. Thus, the data utility is effectively improved without additional privacy losses. Finally, PLDP-MR aggregates the frequencies in all the one-dimensional and two-dimensional grids related to the multi-dimensional range query at all query intervals and all privacy levels to derive the final query result with considering the correlation between attributes. The aggregations use

关键词： data privacy

来源：评论

学校读者我要写书评

暂无评论

research of mask wearing detection method using Improved YOLO network

Research of mask wearing detection method using Improved YOL...

引用

Chinese Control and Decision Conference, CCDC

作者： Fei Xiao Zixi Liu Shengbin Zhao Shuai Yuan School of Computer Science and Engineering Shenyang Jianzhu University Shenyang China Daqing Oilfield Limited Company DaQing China School of Computer Science and Engineering Shenyang Jianzhu University Liaoning Province Big Data Management and Analysis Laboratory of Urban Construction Shenyang Branch of National Special Computer Engineering Technology Research Center Shenyang China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

Mask wearing detection technology is a practical and research-oriented area within object detection. Due to the complexity of mask wearing detection scenarios, issues such as small target detection and low image clarity often result in missed detections and false alarms. The YOLO algorithm, known for its fast detection speed, is commonly used in mask wearing detection. However, the original YOLO algorithm struggles to achieve satisfactory results in dense crowd scenarios. Therefore, this paper proposes an improved YOLOv5 algorithm based on the BiFPN structure and incorporating attention mechanisms to enhance the accuracy of mask wearing detection while maintaining real-time performance. The proposed approach firstly introduces the Bidirectional Feature Pyramid (BiFPN) structure into the backbone network to enhance the feature extraction capability. Additionally, attention mechanisms are incorporated to filter out irrelevant information, conserve computational resources, and improve the detection performance for small targets. Experimental results on a custom dataset demonstrate that the YOLOv5_BiFPN algorithm achieves a 4% improvement in accuracy and an 11.7% increase in mAP50 compared to the original YOLOv5. Moreover, the inclusion of attention mechanisms further boosts the accuracy by an additional 1.6%. These findings confirm that the improved YOLOv5s model exhibits superior performance in the task of mask wearing detection.

关键词： YOLO Attention mechanisms Accuracy Filtering algorithms Feature extraction Information filters Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Passenger Waiting Time Prediction Based on Density Spatiotemporal Clustering and Time Series Feature Processing 6

Passenger Waiting Time Prediction Based on Density Spatiotem...

引用

6th International Conference on Electronic engineering and Informatics, EEI 2024

作者： Huang, Ruixi Xia, Dawen Geng, Jian Zhang, Wenyong Hu, Yang Li, Yantao Li, Huaqing College of Data Science and Information Engineering Guizhou Minzu University Guiyang550025 China Engineering Research Center of Micro-nano and Intelligent Manufacturing Ministry of Education Kaili University Kaili556011 China College of Big Data Engineering College of Microelectronics and Artificial Intelligence Kaili University Kaili556011 China Party School of the Anshun Municipal Committee of C.P.C Anshun561000 China Guizhou Traffic Technician and Transportation College Department of Automotive Engineering Guiyang550008 China College of Computer Science Chongqing University Chongqing400044 China College of Electronic and Information Engineering Southwest University Chongqing400715 China

ISBN: (纸本)9798350353594

Accurate passenger waiting time prediction addresses the taxi supply-demand imbalance in Intelligent Transport Systems (ITS). To capture the dependencies of passenger waiting time on urban taxi distribution, we propose a Density Spatiotemporal Clustering and Time Series Feature Processing (DSC-TSFP) method that discovers potential feature relationships of taxi GPS trajectory data. Specifically, a Multilevel Spatiotemporal Density-Based Spatial Clustering of Applications with Noise (MST-DBSCAN) is proposed to cluster taxi GPS trajectory data to obtain waiting time series with spatiotemporal correlations. Furthermore, a time series processing module based on the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise Normalization (CEEMDANN) is designed to enhance prediction accuracy by handling non-stationarity and numerical discrepancy, which solves the residual white noise problem in Intrinsic Modal Functions (IMFs) of EEMD and CEEMD. Next, a waiting time prediction module oriented to a Convolutional Long Short-Term Memory Network (ConvLSTM) is incorporated to compensate for the defects of spatially localized dependencies that LSTM cannot capture. Finally, a CEEMDANN-ConvLSTM model is constructed to predict the passenger waiting time by combining the time series processing and waiting time prediction module. Based on real-world taxi GPS trajectory data, experimental results demonstrate that DSC-TSFP outperforms comparable methods regarding prediction accuracy. © 2024 IEEE.

关键词： Global positioning system

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：