检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qin, Zeqing Wu, Yiwei Han, Lansheng School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security China

Large Language Models (LLMs) have shown great promise in vulnerability identification. As C/C++ comprises half of the Open-Source Software (OSS) vulnerabilities over the past decade and updates in OSS mainly occur through commits, enhancing LLMs' ability to identify C/C++ Vulnerability-Contributing Commits (VCCs) is essential. However, current studies primarily focus on further pre-training LLMs on massive code datasets, which is resource-intensive and poses efficiency challenges. In this paper, we enhance the ability of BERT-based LLMs to identify C/C++ VCCs in a lightweight manner. We propose CodeLinguaNexus (CLNX) as a bridge facilitating communication between C/C++ programs and LLMs. Based on commits, CLNX efficiently converts the source code into a more natural representation while preserving key details. Specifically, CLNX first applies structure-level naturalization to decompose complex programs, followed by token-level naturalization to interpret complex symbols. We evaluate CLNX on public datasets of 25,872 C/C++ functions with their commits. The results show that CLNX significantly enhances the performance of LLMs on identifying C/C++ VCCs. Moreover, CLNX-equipped CodeBERT achieves new state-of-the-art and identifies 38 OSS vulnerabilities in the real *** Codes 68M25 Copyright © 2024, The Authors. All rights reserved.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

SLMP: A Scientific Literature Management Platform Based on Large Language Models

SLMP: A Scientific Literature Management Platform Based on L...

引用

IEEE International Conference on big knowledge (ICBK)

作者： Menghao Guo Jinling Jiang Fan Wu Shanxin Sun Chen Zhang Wenhui Li Zeyi Sun Guangyong Chen Xindong Wu Research Center for Life Sciences Computing Zhejiang Lab Hangzhou China Research Center for Data Hub and Security Zhejiang Lab Hangzhou China Research Center for High Efficiency Computing System Zhejiang Lab Hangzhou China Key Laboratory of Knowledge Engineering With Big Data Hefei University of Technology Hefei China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

This paper presents a Scientific Literature Management Platform (SLMP, demo link 1 ) based on large language models (LLMs). The platform consists of four modules: literature management, literature extraction, literature retrieval, and question answering. The core techniques used to support the four modules across the platform include a fine-tuned model PaperExtractGPT and a continual pre-training model ChatPaperGPT based on ChatGLM 2 using the data from scientific research literature, responsible for information extraction and communication, respectively. Due to their powerful capabilities in natural language understanding and generation, LLMs can understand complex scientific concepts based on the provided contexts, and thus generate high-quality texts and conduct in-depth information retrieval and question answering. Our platform can help researchers manage and utilize literature more effectively and efficiently for finding relevant literature, obtaining required information, and generating new knowledge.

关键词： Training Large language models knowledge graphs Information retrieval data models Question answering (information retrieval)

来源：评论

学校读者我要写书评

暂无评论

Owl: Differential-Based Side-Channel Leakage Detection for CUDA Applications

Owl: Differential-Based Side-Channel Leakage Detection for C...

引用

International Conference on Dependable Systems and Networks (DSN)

作者： Yu Zhao Wenjie Xue Weijie Chen Weizhong Qiang Deqing Zou Hai Jin National Engineering Research Center for Big Data Technology and System 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 Jinyinhu Laboratory Wuhan China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798350341058

ISBN: (纸本)9798350341065

Over the past decade, various methods for detecting side-channel leakage have been proposed and proven to be effective against CPU side-channel attacks. These methods are valuable in assisting developers to identify and patch side-channel vulnerabilities. Nevertheless, recent research has revealed the feasibility of exploiting side-channel vulnerabilities to steal sensitive information from GPU applications, which are beyond the reach of previous side-channel detection methods. Therefore, in this paper, we conduct an in-depth examination of various GPU features and present Owl, a novel side-channel detection tool targeting CUDA applications on NVIDIA GPUs. Owl is designed to detect and locate side-channel leakage in various types of CUDA applications. When tracking the execution of CUDA applications, we design a hierarchical tracing scheme and extend the A-DCFG (Attributed Dynamic Control Flow Graph) to address the massively parallel execution in CUDA, ensuring Owl's detection scalability. After completing the initial assessment and filtering, we conduct statistical tests on the differences in program traces to determine whether they are indeed caused by input variations, subsequently facilitating the positioning of side-channel leaks. We evaluate Owl's capability to detect side-channel leaks by testing it on Libgpucrypto, PyTorch, and nvJPEG. Meanwhile, we verify that our solution effectively handles a large number of threads. Owl has successfully identified hundreds of leaks within these applications. To the best of our knowledge, we are the first to implement side-channel leakage detection for general CUDA applications.

关键词： Target tracking Statistical analysis Filtering Scalability Graphics processing units Side-channel attacks Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Research on Liquidity Measurement and Influencing Factors of China Carbon Emission Allocation Trading Market

引用

Procedia Computer Science 2023年 221卷 1448-1457页

作者： Yong Shi Shuyang Peng Anqi Yu Kun Guo School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China

Considering multi-dimensional concepts of liquidity, we introduces two classical liquidity measures to quantify the liquidity of China carbon emission allowance(CCEA) trading markets, and analyze their trading activities. Then monthly unbalanced panel was constructed based on daily trading data to further study on the influencing factors of CCEA market. We find that: 1) No matter what method we take, the Hubei pilot is the most liquid in the context of overall running periods, and the national carbon market and Guangdong pilot are also well performed compared to the other markets. 2)The foundation of national generalized market could bring about noticeable changes on the liquidity of carbon market, and Guangdong market which is one of the 8 carbon market pilots become more developed and liquid, while no significant variation in the rest of 7 pilots. 3) The emission control enterprises of each pilot have no inborn incentive to trade proactively, therefore transactions are concentrated on the performance cycle. 4)Regression results show that the price at the end of each month, trading volumes aggregated in each month, trading frequency of each month are all positively correlated with the liquidity, and return volatility of each month, carbon market fragmentation are negatively related to the liquidity. Finally we put forward some suggestion and policy recommendation rested on the above qualitative and quantitative analysis.

关键词： CEA,Carbon market,Liquidity,Measurement,Influencing factors

来源：评论

学校读者我要写书评

暂无评论

A Multimodal knowledge Representation Method for Fake News Detection

A Multimodal Knowledge Representation Method for Fake News D...

引用

Computer, Control and Robotics (ICCCR), International Conference on

作者： Fanhao Zeng Jiaxin Yao Yijie Xu Yanhua Liu Fujian Key Laboratory of Network Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Engineering Research Center of Big Data Intelligence Ministry of Education (Fuzhou University) Fuzhou China

ISBN: (数字)9798350373141

ISBN: (纸本)9798350373158

To address the key challenge encountered in fake news detection, i.e., multimodal data is difficult to be effectively semantically represented due to its intrinsic heterogeneity, this paper proposes a multimodal knowledge representation method for fake news detection. First, visual feature extraction is performed for fake news image data, the relevant images are sliced into multiple blocks, and then visual modal features are obtained by linear projection layer mapping. This simplifies the feature extraction process and reduces the computational cost, which helps to improve the fake news recognition performance. Second, to meet the actual fake news detection needs, a long text representation method based on topic words is investigated for the text data in fake news. Finally, the multimodal representation of the same fake news data is optimized by establishing a connection between two different modalities, visual and text, and inputting it into a BiLSTM-Attention based network to achieve the fusion of multimodal features. The experiment selects the same fake news data of EANN model and uses four classical classification methods to verify the effect of knowledge representation and compare it with the fusion model ViLT which is not optimized for long text. The experiment proves that the accuracy rate of fake news detection using the multimodal representation proposed in this paper is improved by 7.4% compared to the EANN model, and by 9.3% compared to the ViLT representation.

关键词： Digital control Visualization Accuracy knowledge representation Machine learning Feature extraction data models

来源：评论

学校读者我要写书评

暂无评论

A Causal Graph for Learning Gender Debiased Word Embedding

A Causal Graph for Learning Gender Debiased Word Embedding

引用

International Conference on big data and Information Analytics (bigDIA)

作者： Yanxia Feng Yanghui Rao School of Computer Science and Engineering Guangdong Key Laboratory of Big Data Analysis and Processing Sun Yat-sen University Guangzhou China

Word embedding learning is a powerful technique to represent words’ rich semantics as low-dimensional vectors, but it may encode harmful social biases. Such biases can leave negative impacts on downstream applications that rely on word embeddings, e.g., text classification and sentiment analysis. In this work, we design a novel approach to debias word embeddings using a causal graph that separates gender and semantic information within words. Our method is theoretically interpretable and can effectively alleviate the issue of gender bias from words in real-world corpora without destructing their semantic meanings. We perform a comprehensive comparison for our proposed approach with existing state-of-the-art techniques using a range of evaluation metrics and tasks, and demonstrate that our method can not only mitigate bias mixed in word embeddings, but also improve their performance on downstream tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

UAV Flight data Anomaly Detection Based on Parameter Selection and Multiple Regression

UAV Flight Data Anomaly Detection Based on Parameter Selecti...

引用

Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Lei Yang Yizong Zhang Shaobo Li Ansi Zhang Zihao Liao Chuanjiang Li School of Mechanical Engineering Guizhou University Guiyang China State Key Laboratory of Public Big Data Guizhou University Guiyang China

Unmanned aerial vehicles (UAVs) are important in military and civilian applications. Flight data anomaly detection is an essential part of ensuring the safety and reliability of UAV s and has received extensive attention and research. The UAV system is complex and has many parameters. However, many unrelated parameters do not positively impact the model performance. In addition, since there are many anomaly types of UAV flight data, the adaptability of different anomaly types for anomaly detection methods remains a significant challenge. This paper proposes a data-driven method based on parameter selection and multiple regression for UAV flight data anomaly detection, which integrates correlation analysis and long short-term memory (CA-LSTM). First, a correlation-based analysis is performed to select parameters with correlation to reduce the model complexity. Second, an LSTM-based multiple regression model is designed to map flight parameters. Finally, the effectiveness of the proposed method is verified on real UAV flight data injected with two common anomaly types.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Production quality early warning method for firearms components based on cloud edge collaboration 4

Production quality early warning method for firearms compone...

引用

4th International Conference on Machine Learning and Computer Application, ICMLCA 2023

作者： Sun, Jiawei Hao, Jia Zhang, Xiaoning School of Mechanical Engineering Beijing Institute of Technology Beijing10081 China Yangtze Delta Region Academy of Beijing Institute of Technology Jiaxing314019 China Key Laboratory of Industry Knowledge and Data Fusion Technology and Application Ministry of Industry and Information Technology Beijing Institute of Technology Beijing10008 China Tianjin Key Laboratory of Space Environment Simulation Technology Tianjing300450 China

ISBN: (纸本)9798400709449

Digital transformation in manufacturing has become a trend with the continuous development of cloud computing and edge computing. The production process of firearms components is highly challenging and quality problems in the production process may directly affect the safety of people's lives and property. Thus, this paper proposes a production-quality early warning method for firearms components based on cloud-edge collaboration. Real-time early warning and rapid processing for abnormal conditions in the production process are realized based on cloud data analysis and edge intelligent prediction, thereby improving production efficiency and quality. The cloud edge collaboration framework is developed for cloud training of the long short-term memory models and real-time sample edge acquisition, enhancing the adaptability of quality early warning algorithms under specific conditions and the real-time quality of early warning for firearms components. © 2023 ACM.

关键词： big data

来源：评论

学校读者我要写书评

暂无评论

A Multi-Level FW-UAV Fault Diagnosis Solution Based on Multi-Task Learning Under Small Samples

A Multi-Level FW-UAV Fault Diagnosis Solution Based on Multi...

引用

Prognostics and System Health Management Conference (PHM-Qingdao)

作者： Yizong Zhang Lei Yang Xue An Shaobo Li Ansi Zhang Zihao Liao School of Mechanical Engineering Guizhou University Guiyang China State Key Laboratory of Public Big Data Guizhou University Guiyang China

Deep learning provides more advanced solutions for Unmanned Aerial Vehicle (UAV) fault diagnosis, but most existing deep learning methods are designed for a single fault diagnosis task. A UAV is a complex system with multiple coupled components, requiring the simultaneous execution of several different Faulty Component Diagnosis (FCD) level 1 tasks and Fault Level Detection (FLD) level 2 tasks. In addition, scarcity of fault samples is a recognized problem. Therefore, we propose a Multi-Level Fault Diagnosis (MLFD) method for Fixed-Wing UAV (FW-UAV) based on multi-task learning. MLFD jointly trains the FCD and FLD tasks by Cross-stitch units under small samples, adaptively sharing the public information of the two tasks, enriching the fault diagnosis knowledge, and at the same time improving the model's ability to handle the two tasks. Finally, we validate the effectiveness of the proposed method in real FW-UAV failure data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Visual Odometry Using Semantic Information in Complex Dynamic Scenes 5th

Robust Visual Odometry Using Semantic Information in Complex...

引用

5th International Conference on Cognitive Systems and Signal Processing, ICCSIP 2020

作者： Wang, Hao Wang, Le Fang, Baofu Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei Anhui230009 China Department of Computer Science and Technology Hefei University of Technology Hefei Anhui230009 China

ISBN: (纸本)9789811623356

Traditional vision-based simultaneous localization and mapping (SLAM) technology cannot obtain the semantic information of the surrounding environment, which will cause the robot to fail to complete intelligent grasping, human-computer interaction, and other advanced decision tasks. There are many challenges to solve this problem, such as obtaining less semantic information of the environment with low precision and being unable to deal with dynamic objects in a real environment quickly and effectively. In this paper, a robust visual odometry using semantic information in complex dynamic scenes was designed. Specifically, we present a refined instance segmentation method based on the contextual information of the frame to improve the accuracy of segmentation. On this basis, a feature detection and elimination algorithm for dynamic objects based on instance-level semantic information is proposed to improve the localization accuracy of camera pose. We extensively evaluate our system on the public TUM data set and compare it with ORB-SLAM2 and other methods. Experiments show that our methods greatly improve the localization accuracy of the camera pose and the robustness of the system, which verifies that our system is effective in complex dynamic scenes. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Cameras

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：