检索结果-内蒙古大学图书馆

4th Workshop on Human Evaluation of NLP systems, HumEval 2024

作者： Elaraby, Mohamed Xu, Huihui Gray, Morgan Ashley, Kevin Litman, Diane Department of Computer Science School of Computing and Information United States Learning Research and Development Center United States Intelligent Systems Program School of Computing Information University of Pittsburgh PittsburghPA United States

ISBN: (纸本)9782493814418

Human evaluation remains the gold standard for assessing abstractive summarization. However, current practices often prioritize constructing evaluation guidelines for fluency, coherence, and factual accuracy, overlooking other critical dimensions. In this paper, we investigate argument coverage in abstractive summarization by focusing on long legal opinions, where summaries must effectively encapsulate the document’s argumentative nature. We introduce a set of human-evaluation guidelines to evaluate generated summaries based on argumentative coverage. These guidelines enable us to assess three distinct summarization models, studying the influence of including argument roles in summarization. Furthermore, we utilize these evaluation scores to benchmark automatic summarization metrics against argument coverage, providing insights into the effectiveness of automated evaluation methods. © 2024 European Language Resources Association (ELRA).

关键词： Human Evaluation Legal Summarization Summarization

来源：评论

学校读者我要写书评

暂无评论

A graph-based method for identity resolution to assist police force investigative process

引用

Journal of Cyber Security Technology 2025年第2期9卷 127-150页

作者： Amirhosseini, Mohammad Hossein Kazemian, Hassan Phillips, Michael Department of Computer Science and Digital Technologies University of East London London United Kingdom Intelligent Systems Research Centre School of Computing and Digital Media London Metropolitan University London United Kingdom

The ability to prove an individual identity has become crucial in social, economic, and legal aspects of life. Identity resolution is the process of semantic reconciliation that determines whether a single identity is the same when being described differently. This paper introduces a novel graph-based methodology for identity resolution, designed to reconcile identities by analysing the similarity of attribute values associated with different identities within a policing dataset. The proposed methodology employs graph analysis techniques, including centrality measurement and community detection, to enhance the identity resolution process. This paper also presents a new identity model for identity resolution. SPIRIT policing dataset was used for testing the proposed methodology. This dataset is an anonymised dataset used in the SPIRIT project funded by EU Horizon. It contains 892 identity records and among these, two ’known’ identities utilize different names but actually represent the same individual. The presented method successfully recognised these two identities. Additionally, another experimental evaluation was conducted on a refined and extended version of the dataset and the false identities were successfully detected. This method can assist police forces in identifying criminals and fraudsters using fake identities and has applications across finance, marketing, and customer service. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

GRAMO:geometric resampling augmentation for monocular 3D object detection

引用

Frontiers of Computer Science 2024年第5期18卷 161-169页

作者： He GUAN Chunfeng SONG Zhaoxiang ZHANG School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent Perception and Computing State Key Laboratory of Multimodal Artificial Intelligence SystemsInstitute of Automation Chinese Academy of SciencesBeijing 100190China

Data augmentation is widely recognized as an effective means of bolstering model ***,when applied to monocular 3D object detection,non-geometric image augmentation neglects the critical link between the image and physical space,resulting in the semantic collapse of the extended *** address this issue,we propose two geometric-level data augmentation operators named Geometric-Copy-Paste(Geo-CP)and Geometric-Crop-Shrink(Geo-CS).Both operators introduce geometric consistency based on the principle of perspective projection,complementing the options available for data augmentation in monocular ***,Geo-CP replicates local patches by reordering object depths to mitigate perspective occlusion conflicts,and Geo-CS re-crops local patches for simultaneous scaling of distance and scale to unify appearance and *** operations ameliorate the problem of class imbalance in the monocular paradigm by increasing the quantity and distribution of geometrically consistent *** demonstrate that our geometric-level augmentation operators effectively improve robustness and performance in the KITTI and Waymo monocular 3D detection benchmarks.

关键词： 3D detection monocular augmentation geometry

来源：评论

学校读者我要写书评

暂无评论

Process Mining Benefits Model: A Preliminary Study 11

Process Mining Benefits Model: A Preliminary Study

引用

11th International Conference on Computer, Control, Informatics and its Applications, IC3INA 2024

作者： Darmayanti, Nungki Dian S. Cervantes, Abel Armas Kurnia, Sherah Nastiti, Arti Dian The School of Computing and Information Systems The University of Melbourne Australia Research Center for Artificial Intelligent and Cybersecurity National Research and Innovation Agency Indonesia

ISBN: (纸本)9798331542313

Process mining is a family of tools and techniques that analyzes business process data, collected by information systems, through a process lens. This technology can be used by organizations to discover valuable insights, identify bottlenecks, and improve business processes. However, despite the growing popularity of process mining in the industry, there is limited understanding of its benefits and success factors. This study aims to fill the gap by providing a set of guidelines to understand the benefits and success factors of process mining, as well as potential inhibitors that may hinder such benefits. As the study remains ongoing, this paper provides a preliminary assessment of the benefits and success factors of process mining through a literature review to identify the benefits, success factors, and inhibitors or process mining before we construct a PMBM framework. Our findings will help organizations making an informed decision when adopting process mining to maximize the success factors and remain conscious of the barriers that can hinder the benefits of this technology. © 2024 IEEE.

关键词： Mining industry

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security: Evaluating RFID Card Access Control systems using SHA-256

Enhancing Security: Evaluating RFID Card Access Control Syst...

引用

2024 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2024

作者： Yang, You Zhi Ramly, Athirah Mohd Sharif, Mhd Saeed Department of Computing and Information Systems Sunway University Selangor Malaysia School of Architecture Computing and Engineering UEL London United Kingdom Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom

ISBN: (纸本)9798331533137

This paper focuses on enhancing the security of a chosen system by implementing multiple layers of protection, including concealing sensitive data on the Liquid Crystal Display (LCD), utilizing hashed Unique Identifiers (UIDs), and deploying biometric dual-factor authentication via fingerprint recognition. The system is considered secure as it prevents unauthorized access attempts, even if the tag appears legitimate. The paper covers various stages, from component procurement to vulnerability assessment, exploitation, and solution development. While this paper significantly improves system security, further investigation remains crucial. Therefore, this paper not only addresses immediate security implementations but also paves the way for ongoing analysis and improvements aimed at defending the system against malicious threats while optimizing its performance. ©2024 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Intelligence to Secure Wireless Network: Exploring Threats, Existing Approaches, and Proposed Mitigation Strategies

Leveraging Artificial Intelligence to Secure Wireless Networ...

引用

2024 International Conference on Innovation and Intelligence for Informatics, computing, and Technologies, 3ICT 2024

作者： Nan Xin, Alice Lee Ramly, Athirah Mohd Behjati, Mehran Sharif, Mhd Saeed Department of Computing and Information Systems Sunway University Selangor Malaysia School of Architecture Computing and Engineering UEL London United Kingdom Intelligent Technologies Research Group School of Architecture Computing and Engineering UEL London United Kingdom

ISBN: (纸本)9798331533137

The exponential growth of network has introduced new Internet-of-Things (IoT) use cases that has enabling us convenience and comfort. The surge of IoT devices due to the capabilities brought by fifth generation (5G) have given rise to security threats and attacks, particularly malware attacks IoT botnets have been an alarming issue, where smart devices can be manipulated by malicious actors to commence subsequent attacks such as Denial of Service (DoS). Traditional and complex security techniques may not be a viable solution towards these resource-constrained devices with limited processing power. Machine Learning techniques (ML) are the rising trend, and it is often used in Intrusion Detection systems and Network Anomaly Detection. This paper emphasizes on analyzing and comparing various ML models on the IoT-23 dataset. It aims to predict anomalies and conclude the model with optimal performance and least computational time cost that can be used for network anomaly detection systems with real-time data in future works. The ML models used in this paper are Decision Trees (DT), K-nearest neighbours (KNN), Random Forest (RF), Naïve Bayes (NB) and Histogram Gradient Boosting (HGB). DT displayed the best performance with an accuracy score of 73% and F1 score of 0.49 with a time cost of 28.22 seconds. ©2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Of Rodents and Primates: Time-Variant Gain in Drift–Diffusion Decision Models

引用

Computational Brain and Behavior 2024年第2期7卷 195-206页

作者： Asadpour, Abdoreza Tan, Hui Lenfesty, Brendan Wong-Lin, KongFatt Intelligent Systems Research Centre School of Computing Engineering and Intelligent Systems Ulster University Magee Campus Northern Ireland Derry~Londonderry United Kingdom Département Electronique et Technologies Numériques Polytech Nantes Nantes Université Nantes France

Sequential sampling models of decision-making involve evidence accumulation over time and have been successful in capturing choice behaviour. A popular model is the drift–diffusion model (DDM). To capture the finer aspects of choice reaction times (RTs), time-variant gain features representing urgency signals have been implemented in DDM that can exhibit slower error RTs than correct RTs. However, time-variant gain is often implemented on both DDM’s signal and noise features, with the assumption that increasing gain on the drift rate (due to urgency) is similar to DDM with collapsing decision bounds. Hence, it is unclear whether gain effects on just the signal or noise feature can lead to a different choice behaviour. This work presents an alternative DDM variant, focusing on the implications of time-variant gain mechanisms, constrained by model parsimony. Specifically, using computational modelling of choice behaviour of rats, monkeys, and humans, we systematically showed that time-variant gain only on the DDM’s noise was sufficient to produce slower error RTs, as in monkeys, while time-variant gain only on drift rate leads to faster error RTs, as in rodents. We also found minimal effects of time-variant gain in humans. By highlighting these patterns, this study underscores the utility of group-level modelling in capturing general trends and effects consistent across species. Thus, time-variant gain on DDM’s different components can lead to different choice behaviours, shed light on the underlying time-variant gain mechanisms for different species, and can be used for systematic data fitting. © 2024, Crown.

关键词： Cognitive computational modelling Drift–diffusion model Perceptual decision-making Time-variant gain Urgency signal

来源：评论

学校读者我要写书评

暂无评论

A NEW HOPE: Contextual Privacy Policies for Mobile Applications and An Approach Toward Automated Generation 33

A NEW HOPE: Contextual Privacy Policies for Mobile Applicati...

引用

33rd USENIX Security Symposium, USENIX Security 2024

作者： Pan, Shidong Tao, Zhen Hoang, Thong Zhang, Dawen Li, Tianshi Xing, Zhenchang Xu, Xiwei Staples, Mark Rakotoarivelo, Thierry Lo, David School of Computing Australian National University Australia Software and Computational Systems Research Program CSIRO's Data61 Khoury College of Computer Sciences Northeastern University United States School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9781939133441

Privacy policies have emerged as the predominant approach to conveying privacy notices to mobile application users. In an effort to enhance both readability and user engagement, the concept of contextual privacy policies (CPPs) has been proposed by researchers. The aim of CPPs is to fragment privacy policies into concise snippets, displaying them only within the corresponding contexts within the application's graphical user interfaces (GUIs). In this paper, we first formulate CPP in mobile application scenario, and then present a novel multimodal framework, named SEEPRIVACY, specifically designed to automatically generate CPPs for mobile applications. This method uniquely integrates vision-based GUI understanding with privacy policy analysis, achieving 0.88 precision and 0.90 recall to detect contexts, as well as 0.98 precision and 0.96 recall in extracting corresponding policy segments. A human evaluation shows that 77% of the extracted privacy policy segments were perceived as well-aligned with the detected contexts. These findings suggest that SEEPRIVACY could serve as a significant tool for bolstering user interaction with, and understanding of, privacy policies. Furthermore, our solution has the potential to make privacy notices more accessible and inclusive, thus appealing to a broader demographic. A demonstration of our work can be accessed at https://***/SeePrivacy/. © USENIX Security Symposium *** rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Malware Detection and Analysis in Android Applications with Mobile Security Framework (MobSF) Using a Permission-Based Approach 12th

Malware Detection and Analysis in Android Applications with ...

引用

12th International Conference on Frontiers of intelligent computing: Theory and Applications, FICTA 2024

作者： Kizito, Mark Homayounvala, Elaheh Kazemian, Hassan Araujo, Istteffanny Intelligent Systems Research Group School of Computing and Digital Media London Metropolitan University 166-220 Holloway Rd LondonN7 8DB United Kingdom

ISBN: (纸本)9789819601424

This paper examines security concerns in Android applications arising from violations to the principle of least privilege. Using mobile security framework (MobSF), static and dynamic analysis techniques were used in evaluating how non-essential permission groups that are not core to application functions greatly increase risks of unauthorized system access by attackers, data breaches and privacy concerns, enlarged attack surfaces, and hijacking system resources among others. A permission-based approach systematically identifies malware and highlights dangerous permission groups that magnify security risks. The findings of this research study emphasis on meticulous auditing of permissions to prevent security threats in Android applications and to safeguard user-sensitive data. The conducted experiments compared essential core permissions to non-essential ones regarding application functionality and overall system security. It was also noted that background permissions potentially pose a great deal of risk to security when granted without proper rationale as this increases attack surfaces within the application itself. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Android malware

来源：评论

学校读者我要写书评

暂无评论

Optimal Tracking Performance of Networked Control systems Under DoS and Its Applications

Optimal Tracking Performance of Networked Control Systems Un...

引用

2024 China Automation Congress, CAC 2024

作者： Ren, Xinyu Li, Bo Zhao, Feng Chen, Xiangyong Zhang, Xianhe Jiang, Xiaowei School of Automation China University of Geosciences Hubei Key Laboratory of Advanced Control and Intelligent Automation of Complex Systems Engineering Research Center of Intelligent Technology for Geo-Exploration Ministry of Education Wuhan China School of Finance Anhui University of Finance and Economics Bengbu China Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong Linyi University Linyi China School of Automation and Electrical Engineering Key Laboratory of Complex systems and Intelligent Computing in Universities of Shandong Linyi University Linyi China School of Electrical Engineering and Automation Hubei Normal University Huangshi China

ISBN: (纸本)9798350368604

This paper investigates the optimal tracking performance (OTP) of multiple-input multiple-output (MIMO) discrete networked control systems (NCSs) under the influence of Denial of Service (DoS) attack, channel noise, and bandwidth constraints. The channel noise is assumed to be additive Gaussian white noise (AWGN). Due to the randomness of DoS attack, a Bernoulli distribution is used for DoS modeling. Utilizing frequency domain analysis methods, coprime factorization, all-pass decomposition, and Youla parameterization, an explicit expression for the optimal tracking performance (OTP) of the system under the two-degree-of-freedom (TDOF) controller is derived. The analysis indicates that non-minimum phase (NMP) zeros, unstable poles (UPs), DoS attack, and network constraints affect the OTP of NCSs. Finally, the theoretical results are validated through simulations of MIMO NCS and vehicle control system. © 2024 IEEE.

关键词： White noise

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：