检索结果-内蒙古大学图书馆

International Conference on software engineering (ICSE)

作者： Xin-Cheng Wen Yupan Chen Cuiyun Gao Hongyu Zhang Jie M. Zhang Qing Liao School of Computer Science and Technology Harbin Institute of Technology Shenzhen China Peng Cheng Laboratory and Guangdong Provincial Key Laboratory Novel Security Intelligence Technologies School of Big Data and Software Engineering Chongqing University China Department of Informatics King's College London UK Peng Cheng Laboratory

Prior studies have demonstrated the effectiveness of Deep Learning (DL) in automated software vulnerability detection. Graph Neural Networks (GNNs) have proven effective in learning the graph representations of source code and are commonly adopted by existing DL-based vulnerability detection methods. However, the existing methods are still limited by the fact that GNNs are essentially difficult to handle the connections between long-distance nodes in a code structure graph. Besides, they do not well exploit the multiple types of edges in a code structure graph (such as edges representing data flow and control flow). Consequently, despite achieving state-of-the-art performance, the existing GNN-based methods tend to fail to capture global information (i.e., long-range dependencies among nodes) of code graphs. To mitigate these issues, in this paper, we propose a novel vulnerability detection framework with grAph siMplification and enhanced graph rePresentation LEarning, named AMPLE. AMPLE mainly contains two parts: 1) graph simplification, which aims at reducing the distances between nodes by shrinking the node sizes of code structure graphs; 2) enhanced graph representation learning, which involves one edge-aware graph convolutional network module for fusing heterogeneous edge information into node representations and one kernel-scaled representation module for well capturing the relations between distant graph nodes. Experiments on three public benchmark datasets show that AMPLE outperforms the state-of-the-art methods by 0.39%-35.32% and 7.64%-199.81% with respect to the accuracy and F1 score metrics, respectively. The results demonstrate the effectiveness of AMPLE in learning global information of code graphs for vulnerability detection.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ECPC-IDS: A benchmark endometrial cancer PET/CT image dataset for evaluation of semantic segmentation and detection of hypermetabolic regions

引用

Computers in Biology and Medicine 2024年 171卷 108217-108217页

作者： Tang, Dechao Li, Chen Du, Tianmin Jiang, Huiyan Ma, Deguo Ma, Zhiyu Grzegorzek, Marcin Jiang, Tao Sun, Hongzan Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University China Software College Northeastern University Shenyang China Institute of Medical Informatics University of Luebeck Luebeck Germany Department of Knowledge Engineering University of Economics in Katowice Poland Chengdu University of Traditional Chinese Medicine Chengdu China International Joint Institute of Robotics and Intelligent Systems Chengdu University of Information Technology China Department of Radiology Shengjing Hospital China Medical University Shenyang China

Background: Endometrial cancer is one of the most common tumors in the female reproductive system and is the third most common gynecological malignancy that causes death after ovarian and cervical cancer. Early diagnosis can significantly improve the 5-year survival rate of patients. With the development of artificial intelligence, computer-assisted diagnosis plays an increasingly important role in improving the accuracy and objectivity of diagnosis and reducing the workload of doctors. However, the absence of publicly available image datasets restricts the application of computer-assisted diagnostic techniques. Methods: In this paper, a publicly available Endometrial Cancer PET/CT Image Dataset for Evaluation of Semantic Segmentation and Detection of Hypermetabolic Regions (ECPC-IDS) are published. Specifically, the segmentation section includes PET and CT images, with 7159 images in multiple formats totally. In order to prove the effectiveness of segmentation on ECPC-IDS, six deep learning semantic segmentation methods are selected to test the image segmentation task. The object detection section also includes PET and CT images, with 3579 images and XML files with annotation information totally. Eight deep learning methods are selected for experiments on the detection task. Results: This study is conduct using deep learning-based semantic segmentation and object detection methods to demonstrate the distinguishability on ECPC-IDS. From a separate perspective, the minimum and maximum values of Dice on PET images are 0.546 and 0.743, respectively. The minimum and maximum values of Dice on CT images are 0.012 and 0.510, respectively. The target detection section's maximum mAP values on PET and CT images are 0.993 and 0.986, respectively. Conclusion: As far as we know, this is the first publicly available dataset of endometrial cancer with a large number of multi-modality images. ECPC-IDS can assist researchers in exploring new algorithms to enhance computer-assisted d

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Architecture of Automated User Interface based Tests with Protocol-Oriented Programming paradigm

Architecture of Automated User Interface based Tests with Pr...

引用

International IEEE Conference and Workshop: Óbuda on Electrical and Power engineering (CANDO-EPE)

作者： Jozsef Laszlo Basiszta Attila Kovari Jozsef Katona Department of Software Development and Application University of Dunaujvaros Dunaujvaros Hungary Institute of Engineering Alba Regia Technical Faculty Óbuda University Székesfehérvár Hungary Institute of Digital Technology Faculty of Informatics Eszterházy Károly Catholic University Eger Hungary Ágoston Trefort Engineering Education Center Institute of Electrophysics Kandó Kálmán Faculty of Electrical Engineering Óbuda University Budapest Hungary Department of Software Development and Application Informatics Institute University of Dunaujvaros Dunaujvaros Hungary

ISBN: (纸本)9798350346206

Nowadays, manual and automated tests, among other things, are used to achieve the best quality of a software product. There are several types of automated tests that try to meet the needs of today’s technology, but in addition to the advantages of these techniques, there are also disadvantages that are analysed in detail in this article. The aim of this article is to develop and present the possibilities of exploiting the potential of protocol orientation in a less common programming paradigm in user interface tests that do not suffer from the previously mentioned disadvantages. The manuscript meets the theory of user interface testing with protocol orientation, creating a test project that takes advantage of Swift’s unique language capabilities by transferring best practices from traditional testing procedures, resulting in easy-to-read, easy-tomaintain test codes.

关键词： software testing Protocols Codes Computer architecture Programming User interfaces Writing

来源：评论

学校读者我要写书评

暂无评论

State-based Sandbox Tool for Distributed Malware Detection with Avoid Techniques

State-based Sandbox Tool for Distributed Malware Detection w...

引用

IEEE International Conference on Dependable Systems, Services and Technologies (DESSERT)

作者： Pavlo Rehida George Markowsky Anatoliy Sachenko Oleg Savenko Department of Computer Engineering and Information Systems Khmelnytskyi National University Khmelnytskyi Ukraine Department of Software Engineering and Game Development Kennesaw State University Marietta USA Department of Informatics Kazimierz Pulaski University of Technology and Humanities Radom Poland Research Institute for Intelligent Computer Systems West Ukrainian National Unversity Ternopil Ukraine

This paper deals with the problem of detecting the malware by using emulation approach. Modern malware include various avoid techniques, to hide its anomaly actions. Advantages of using sandbox and emulation technologies are described. Various anti-emulation techniques that are used in modern malware considered. Obfuscation as one primary approach to hide malware malicious actions described and discussed. State of emulator is presented, and the advantages of its usage are covered. Distributed model for malware detection is considered. Basic emulator and its current capabilities presented. Prepared files that represent malware are described. Experimental results for developed files that differs with included avoid techniques are presented. Disadvantages of proposed approach is described. Future research and sandbox improvement are described.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Terahertz Image Reconstruction ⋆,⋆⋆

SSRN

引用

SSRN 2024年

作者： Su, Zhipeng Zhang, Yixiong Zhou, Jianyang Shi, Jianghong Qi, Feng Zhang, Xiao-Ping Ji, Chunlin School of Informatics Xiamen University National Demonstrative Software School Xiamen University China School of Electronic Science and Engineering National Model Microelectronics College Xiamen University China Shenyang Institute of Automation Chinese Academy of Sciences China Department of Electrical Computer & Biomedical Engineering Finance Department The Ted Rogers School of Management Toronto Metropolitan University Canada Kuang-Chi Institute of Advanced Technology State Key Laboratory of Meta-RF Electromagnetic Modulation Technology Shen Zhen China

This paper proposes a novel terahertz (THz) image recovery algorithm and a new THz image dataset is publicly available. Because of transmission noise, artificial errors and problems with diffraction phenomena are among the main problems that cause degradation of THz images. The point spread function (PSF) in real transmission is first obtained using a terahertz imaging system. Experiments can generate degraded images and clean image datasets for supervised training of neural networks via terahertz PSF. A Depthwise Dense Instantiation Normalization Block (DwDIN Block) has been proposed to recover the datasets. We constructed a powerful multi-stage network (DwDINet) at each scale by utilizing the DwDIN module. For input and output, the results of each stage of the network and the original images are taken as input into the next layer in order to enhance the background information. DwDINet achieves state-of-the-art (SOTA) results on the two main THz datasets. To verify the generality of the model, we performed experiments on various image recovery tasks. According to the experimental results, the proposed model is of great potential for the field of low-level image clarification. © 2024, The Authors. All rights reserved.

关键词： Optical transfer function

来源：评论

学校读者我要写书评

暂无评论

Towards Lightweight Super-Resolution with Dual Regression Learning

arXiv

引用

arXiv 2022年

作者： Guo, Yong Tan, Mingkui Deng, Zeshuai Wang, Jingdong Chen, Qi Cao, Jiezhang Xu, Yanwu Chen, Jian The School of Software Engineering South China University of Technology China The Max Planck Institute for Informatics Germany The Pazhou Laboratory Guangzhou China The Baidu Inc China The Faculty of Engineering The University of Adelaide Australia ETH Zürich Switzerland The School of Future Technology South China University of Technology China

Deep neural networks have exhibited remarkable performance in image super-resolution (SR) tasks by learning a mapping from low-resolution (LR) images to high-resolution (HR) images. However, the SR problem is typically an ill-posed problem and existing methods would come with several limitations. First, the possible mapping space of SR can be extremely large since there may exist many different HR images that can be super-resolved from the same LR image. As a result, it is hard to directly learn a promising SR mapping from such a large space. Second, it is often inevitable to develop very large models with extremely high computational cost to yield promising SR performance. In practice, one can use model compression techniques to obtain compact models by reducing model redundancy. Nevertheless, it is hard for existing model compression methods to accurately identify the redundant components due to the extremely large SR mapping space. To alleviate the first challenge, we propose a dual regression learning scheme to reduce the space of possible SR mappings. Specifically, in addition to the mapping from LR to HR images, we learn an additional dual regression mapping to estimate the downsampling kernel and reconstruct LR images. In this way, the dual mapping acts as a constraint to reduce the space of possible mappings. To address the second challenge, we propose a dual regression compression (DRC) method to reduce model redundancy in both layer-level and channel-level based on channel pruning. Specifically, we first develop a channel number search method that minimizes the dual regression loss to determine the redundancy of each layer. Given the searched channel numbers, we further exploit the dual regression manner to evaluate the importance of channels and prune the redundant ones. Extensive experiments show the effectiveness of our method in obtaining accurate and efficient SR models. Copyright © 2022, The Authors. All rights reserved.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Leveraging Big Data for Effective Healthcare Management with Artificial Intelligence

Leveraging Big Data for Effective Healthcare Management with...

引用

Artificial Intelligence for Innovations in Healthcare Industries (ICAIIHI), International Conference on

作者： Krati Dubey Chaitali B. Kasar Guravaiah Thulluri Anuradha Yesugad Mehaboob Karishma Dipanjali Padhi Department of Information technology Manipal University Jaipur Jaipur India Department of Electronics and Telecommunication Engineering Dr. D. Y. Patil Institute of Technology Pune Embedded Senior Software Developer SAK informatics Hyderabad Institute of Management & Entrepreneurship Development Bharati Vidyapeeth (Deemed to be University) Pune Department of Computer Application Sir C R R College Eluru Department of Electronics & Telecommunication Engineering Dhole Patil college of Engineering Pune

To improve clinical judgment, resource allocation, and patient outcomes, this study investigates the integration of big data with artificial intelligence (AI) for medical management. Utilizing a descriptive design with an emphasis on secondary data collecting, the study adopts an interpretive perspective and a deductive approach. Data collection, AI algorithm implementation, integration into the system, and infrastructure issues are all included in the technical setup. Accuracy, sensitivity, quickness of processing, and scalability are examples of performance measures, and the influence on patients and healthcare providers is highlighted by user viewpoints and experiences. Informed permission, data security, and legal compliance are all included in the ethical considerations. The results highlight the potential advantages of data-driven medical services, but they also highlight how crucial ethical precautions and user acceptance are. Upcoming studies ought to concentrate on improving algorithms, protecting privacy, and evaluating long-term effects

关键词：

来源：评论

学校读者我要写书评

暂无评论

TAD-Bench: A Comprehensive Benchmark for Embedding-Based Text Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Cao, Yang Yang, Sikun Li, Chen Xiang, Haolong Qi, Lianyong Liu, Bo Li, Rongsheng Liu, Ming School of Computing and Information Technology Great Bay University China Great Bay Institute for Advanced Study Great Bay University China Graduate School of Informatics Nagoya University Japan School of Software Nanjing University of Information Science and Technology China College of Computer Science and Technology China University of Petroleum [East China China College of Cyberspace Security Zhengzhou University China School of Computer Harbin Engineering University China School of IT Deakin University Australia

Text anomaly detection is crucial for identifying spam, misinformation, and offensive language in natural language processing tasks. Despite the growing adoption of embedding-based methods, their effectiveness and generalizability across diverse application scenarios remain under-explored. To address this, we present TAD-Bench, a comprehensive benchmark designed to systematically evaluate embedding-based approaches for text anomaly detection. TAD-Bench integrates multiple datasets spanning different domains, combining state-of-the-art embeddings from large language models with a variety of anomaly detection algorithms. Through extensive experiments, we analyze the interplay between embeddings and detection methods, uncovering their strengths, weaknesses, and applicability to different tasks. These findings offer new perspectives on building more robust, efficient, and generalizable anomaly detection systems for real-world applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

WcDT: World-centric Diffusion Transformer for Traffic Scene Generation

arXiv

引用

arXiv 2024年

作者： Yang, Chen He, Yangfan Tian, Aaron Xuxiang Chen, Dong Wang, Jianhui Shi, Tianyu Heydarian, Arsalan Liu, Pei Department of Computer Science and Informatics Cardiff University United Kingdom College of Libera Arts University of Minnesota - Twin Cities United States United States Agricultural & Biological Engineering Mississippi State University United States Information and Software Engineering University of Electronic Science and Technology of China China Transportation Research Institute University of Toronto Canada Link Lab & Civil and Environmental Engineering University of Virginia United States Intelligent Transportation Thrust The Hong Kong University of Science and Technology Guangzhou China

In this paper, we introduce a novel approach for autonomous driving trajectory generation by harnessing the complementary strengths of diffusion probabilistic models (a.k.a., diffusion models) and transformers. Our proposed framework, termed the "World-centric Diffusion Transformer"(WcDT), optimizes the entire trajectory generation process, from feature extraction to model inference. To enhance the scene diversity and stochasticity, the historical trajectory data is first preprocessed into "Agent Move Statement" and encoded into latent space using Denoising Diffusion Probabilistic Models (DDPM) enhanced with Diffusion with Transformer (DiT) blocks. Then, the latent features, historical trajectories, HD map features, and historical traffic signal information are fused with various transformer-based encoders that is used to enhance the interaction of agents with other elements in the traffic scene. The encoded traffic scenes are then decoded by a trajectory decoder to generate multimodal future trajectories. Comprehensive experimental results show that the proposed approach exhibits superior performance in generating both realistic and diverse trajectories, showing its potential for integration into automatic driving simulation systems. Our code is available at https://***/yangchen1997/WcDT. © 2024, CC BY.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Multi-sector Risk Management Framework for Analysis Cybersecurity Challenges and Opportunities 1

引用

11th International Conference on Multimedia Communications, Services and Security, MCSS 2022

作者： Niemiec, Marcin Pappalardo, Salvatore Marco Bozhilova, Maya Stoianov, Nikolai Dziech, Andrzej Stiller, Burkhard AGH University of Science and Technology Mickiewicza 30 Krakow30-059 Poland CIRM Viale Ortles 22 Milan Italy Software Engineering Italia S.r.l. Piazza Abramo Lincoln 7 Catania Italy Bulgarian Defence Institute Sofia Bulgaria Communication Systems Group CSG Department of Informatics IfI University of Zurich UZH Binzmühlestrasse 14 Zürich8050 Switzerland

ISBN: (数字)9783031202155

ISBN: (纸本)9783031202148

This paper describes an approach to analyse transversal and inter-sectoral cybersecurity challenges and opportunities: dedicated risk assessment and management framework, which can be used to develop cybersecurity technology roadmaps. This multi-sector assessment framework is able to prioritise and evaluate cybersecurity risks in trans-sectoral and inter-sectoral contexts as well as supports proper resource allocations and mitigation actions. To achieve this goal, the analysis of known risk management and risk assessment frameworks was performed, and results are presented in this paper. Also, an overview on transversal, inter-sectoral and multi-sectoral technological challenges and opportunities is provided. The result of this analysis is an architecture of the ECHO Multi-sector Assessment Framework, which was described in detail, including identified and analysed transversal aspects, multi-sector dependencies, and technological challenges and opportunities determine the input data for the framework. This solution is applicable in many sectors, such as energy, healthcare, maritime transportation, or defence, however it can also be extended to others. The architecture of the framework proposed supports the design of cybersecurity technology roadmap and the definition of governance models. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Risk assessment

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：