检索结果-内蒙古大学图书馆

Physical Adversarial Attack Meets Computer Vision: A Decade Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Wei, Hui Tang, Hao Jia, Xuemei Wang, Zhixiang Yu, Hanxun Li, Zhubo Satoh, Shin'ichi Van Gool, Luc Wang, Zheng School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University Wuhan China National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University Beijing100871 China Colleage of Software and Technology Zhejiang University Hangzhou China School of Cyber Science and Engineering Wuhan University Wuhan China Digital Content and Media Sciences Research Division National Institute of Informatics Japan Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Japan Computer Vision Lab of ETH Zurich Zürich8092 Switzerland KU Leuven Leuven3000 Belgium INSAIT Sofia Bulgaria

Despite the impressive achievements of Deep Neural Networks (DNNs) in computer vision, their vulnerability to adversarial attacks remains a critical concern. Extensive research has demonstrated that incorporating sophisticated perturbations into input images can lead to a catastrophic degradation in DNNs’ performance. This perplexing phenomenon not only exists in the digital space but also in the physical world. Consequently, it becomes imperative to evaluate the security of DNNs-based systems to ensure their safe deployment in real-world scenarios, particularly in security-sensitive applications. To facilitate a profound understanding of this topic, this paper presents a comprehensive overview of physical adversarial attacks. Firstly, we distill four general steps for launching physical adversarial attacks. Building upon this foundation, we uncover the pervasive role of artifacts carrying adversarial perturbations in the physical world. These artifacts influence each step. To denote them, we introduce a new term: adversarial medium. Then, we take the first step to systematically evaluate the performance of physical adversarial attacks, taking the adversarial medium as a first attempt. Our proposed evaluation metric, hiPAA, comprises six perspectives: Effectiveness, Stealthiness, Robustness, Practicability, Aesthetics, and Economics. We also provide comparative results across task categories, together with insightful observations and suggestions for future research directions. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

On the Emergence of Autonomous Systems towards Deep Thinking Machines and General AI Driven by Abstract Intelligence Theories and Intelligent Mathematics

学校读者我要写书评

暂无评论

On the Emergence of Autonomous Systems towards Deep Thinking...

IEEE International Conference on Cognitive informatics

作者： Yingxu Wang President International Institute of Cognitive Informatics and Cognitive Computing (I2CICC) Visiting Professor: Stanford Univ. (2008|16) MIT (2012) UC Berkeley (2008) Oxford Univ. (1995|2018-22) Dept. of Electrical and Software Engineering Schulich School of Engineering and Hotchkiss Brain Institute University of Calgary Calgary AB Canada

ISBN: (纸本)9781665421201

Thinking and inference are key essences of human intelligence as René Descartes stated that "I think therefore I am (1637)." The ultimate goal of General AI (GAI) [1], [2], [3], [4] is to enable machine thinking and inference [5], [6], [7], [8], [9] beyond data-based learning [10], [11] towards run-time intelligence generation [9], [12] driven by Autonomous Systems (AS) [13], [14] and cognitive robots [15]. Basic research on machine thinking is powered by Abstract Intelligence theories [16], [17], [18], [19], [20], [21] and Intelligent Mathematics (IM) [22], [23], [24], [25], [26], [27], [28], [29], [30], [31], [32] towards enabling symbiotic and collective intelligence [13], [33] and cognitive systems [34], [35], [36], [37], [38], [39].This keynote lecture presents theoretical foundations of and latest advances in machine thinking and inference driven by AS, GAI, and cognitive robots. Latest breakthroughs in IMs and run-time behavior generation by cognitive systems and AS are elaborated. Emerging paradigms of machine thinking autonomies are introduced to demonstrate the next generation of general AI and symbiotic intelligent systems. The advances in AS are expected to lead to a wide range of novel applications in deep machine thinking, machine knowledge learning, cognitive robots, inference computers, brain-inspired systems, and mission-critical intelligent systems.

关键词： Symbiosis Computers Autonomous systems Human intelligence Mission critical systems Collective intelligence Mathematics

A Consensus Privacy Metrics Framework for Synthetic Data

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Pilgram, Lisa Dankar, Fida K. Drechsler, Jörg Elliot, Mark Domingo-Ferrer, Josep Francis, Paul Kantarcioglu, Murat Kong, Linglong Malin, Bradley Muralidhar, Krishnamurty Myles, Puja Prasser, Fabian Raisaro, Jean Louis Yan, Chao El Emam, Khaled School of Epidemiology and Public Health University of Ottawa ON Canada CHEO Research Institute ON Canada Department of Nephrology and Medical Intensive Care Charité – Universitätsmedizin Berlin Berlin Germany Department for Statistical Methods Institute for Employment Research Nuernberg Germany Institute for Statistics Ludwig-Maximilians-Universität Munich Germany Joint Program in Survey Methodology University of Maryland United States The Cathie Marsh Institute Research School of Social Sciences University of Manchester Manchester United Kingdom Department of Computer Engineering and Mathematics Universitat Rovira i Virgili Catalonia Tarragona Spain Max Planck Institute for Software Systems Germany Department of Computer Science Virginia Tech United States Department of Mathematical and Statistical Sciences University of Alberta Alberta Canada Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Biostatistics Vanderbilt University Medical Center NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States Department of Marketing and Supply Chain Management University of Oklahoma Oklahoma United States Medicines and Healthcare products Regulatory Agency London United Kingdom Berlin Institute of Health at Charité Universitätsmedizin Berlin Medical Informatics Group Berlin Germany Biomedical Data Science Center University Hospital Lausanne Lausanne Switzerland

Synthetic data generation is one approach for sharing individual-level data. However, to meet legislative requirements, it is necessary to demonstrate that the individuals’ privacy is adequately protected. There is no consolidated standard for measuring privacy in synthetic data. Through an expert panel and consensus process, we developed a framework for evaluating privacy in synthetic data. Our findings indicate that current similarity metrics fail to measure identity disclosure, and their use is discouraged. For differentially private synthetic data, a privacy budget other than close to zero was not considered interpretable. There was consensus on the importance of membership and attribute disclosure, both of which involve inferring personal information about an individual without necessarily revealing their identity. The resultant framework provides precise recommendations for metrics that address these types of disclosures effectively. Our findings further present specific opportunities for future research that can help with widespread adoption of synthetic data. © 2025, CC BY.

关键词： Differential privacy

Transformers in Medical Image Analysis: A Review

学校读者我要写书评

暂无评论

arXiv 2022年

作者： He, Kelei Gan, Chen Li, Zhuoyuan Rekik, Islem Yin, Zihao Ji, Wen Gao, Yang Wang, Qian Zhang, Junfeng Shen, Dinggang Medical School of Nanjing University Nanjing China National Institute of Healthcare Data Science Nanjing University Nanjing China State Key Laboratory for Novel Software Technology Nanjing University Nanjing China BASIRA Lab Faculty of Computer and Informatics Engineering Istanbul Technical University Istanbul Turkey School of Science and Engineering Computing University of Dundee United Kingdom School of Biomedical Engineering ShanghaiTech University Shanghai China Department of Research and Development Shanghai United Imaging Intelligence Co. Ltd. Shanghai China

Transformers have dominated the field of natural language processing, and recently impacted the computer vision area. In the field of medical image analysis, Transformers have also been successfully applied to full-stack clinical applications, including image synthesis/reconstruction, registration, segmentation, detection, and diagnosis. Our paper aims to promote awareness and application of Transformers in the field of medical image analysis. Specifically, we first overview the core concepts of the attention mechanism built into Transformers and other basic components. Second, we review various Transformer architectures tailored for medical image applications and discuss their limitations. Within this review, we investigate key challenges revolving around the use of Transformers in different learning paradigms, improving the model efficiency, and their coupling with other techniques. We hope this review can give a comprehensive picture of Transformers to the readers in the field of medical image analysis. © 2022, CC BY-SA.

关键词： Diagnosis

A framework for managing enterprise architecture debts - Outline and research directions 10

学校读者我要写书评

暂无评论

A framework for managing enterprise architecture debts - Out...

10th International Workshop on Enterprise Modeling and Information Systems Architectures, EMISA 2020

作者： Alexander, Peter Hacks, Simon Jung, Jürgen Lichter, Horst Steffens, Ulrike Uludağ, Ömer RWTH Aachen University Research Group Software Construction Aachen Germany KTH Royal Institute of Technology Network and Systems Engineering Stockholm Sweden Frankfurt University of Applied Sciences Faculty of Computer Science and Engineering Frankfurt Germany Hamburg University of Applied Sciences Department of Computer Science Hamburg Germany Technical University of Munich Department of Informatics Munich Germany

Even though enterprise architecture management (EAM) offers a wide range of methods and tools for aligning business with IT, an architect’s work is challenged by reality. The evolution of enterprise architecture (EA) and given constraints (e.g. legacy systems and processes) lead to debts which may complicate and hinder opportunities;however, the management of such debts has not been considered in EAM research. This paper presents a framework for strategically managing EA-debt-related issues and propose open questions as well as future research directions in this field. Copyright © 2020 for this paper by its authors.

关键词： Legacy systems

Trustworthy and Responsible AI for Human-Centric Autonomous Decision-Making Systems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dehghani, Farzaneh Dibaji, Mahsa Anzum, Fahim Dey, Lily Basdemir, Alican Bayat, Sayeh Boucher, Jean-Christophe Drew, Steve Eaton, Sarah Elaine Frayne, Richard Ginde, Gouri Harris, Ashley Ioannou, Yani Lebel, Catherine Lysack, John Arzuaga, Leslie Salgado Stanley, Emma Souza, Roberto de Souza Santos, Ronnie Wells, Lana Williamson, Tyler Wilms, Matthias Wahid, Zaman Ungrin, Mark Gavrilova, Marina Bento, Mariana Department of Biomedical Engineering University of Calgary Calgary Canada Hotchkiss Brain Institute University of Calgary Calgary Canada Department of Electrical and Software Engineering University of Calgary Calgary Canada Department of Computer Science University of Calgary Calgary Canada Department of Philosophy University of Calgary Calgary Canada Department of Geomatics Engineering University of Calgary Calgary Canada Department of Political Science University of Calgary Calgary Canada Werklund School of Education Specialization Leadership University of Calgary Calgary Canada Cumming School of Medicine Department of Radiology University of Calgary Calgary Canada Department of Communication Media and Film University of Calgary Calgary Canada Faculty of Social Work University of Calgary Calgary Canada Centre for Health Informatics University of Calgary Calgary Canada Faculty of Veterinary Medicine University of Calgary Calgary Canada

Artificial Intelligence (AI) has paved the way for revolutionary decision-making processes, which if harnessed appropriately, can contribute to advancements in various sectors, from healthcare to economics. However, its black box nature presents significant ethical challenges related to bias and transparency. AI applications are hugely impacted by biases, presenting inconsistent and unreliable findings, leading to significant costs and consequences, highlighting and perpetuating inequalities and unequal access to resources. Hence, developing safe, reliable, ethical, and Trustworthy AI systems is essential. Our team of researchers working with Trustworthy and Responsible AI, part of the Transdisciplinary Scholarship Initiative within the University of Calgary, conducts research on Trustworthy and Responsible AI, including fairness, bias mitigation, reproducibility, generalization, interpretability, and authenticity. In this paper, we review and discuss the intricacies of AI biases, definitions, methods of detection and mitigation, and metrics for evaluating bias. We also discuss open challenges with regard to the trustworthiness and widespread application of AI across diverse domains of human-centric decision making, as well as guidelines to foster Responsible and Trustworthy AI models. © 2024, CC BY.

关键词： Intelligent systems

Variability Visualization of IEC 61131-3 Legacy software for Planned Reuse

学校读者我要写书评

暂无评论

Variability Visualization of IEC 61131-3 Legacy Software for...

IEEE International Conference on Systems, Man and Cybernetics

作者： Juliane Fischer Birgit Vogel-Heuser Jan Wilch Frieder Loch Kathrin Land Ina Schaefer Chair of Automation and Information Systems Technical University of Munich Garching Germany Institute of Software Engineering and Automotive Informatics Technical University of Braunschweig Braunschweig Germany

ISBN: (数字)9781728185262

ISBN: (纸本)9781728185279

Automated production systems (aPS) are variant-rich, design-to-order systems and an increasing proportion of their functionality is implemented by control software. In control software development, software reuse is still commonly performed via clone-and-own despite many drawbacks, e.g., copying errors. This unplanned reuse leads to a high amount of historically grown software variants, which contain valuable domain expertise. Therefore, to enable planned reuse of existing control software solutions, an analysis of legacy software, inducing documentation of identified variability, is required. While so-called software Product Lines enable the documentation of variability, they lack suitable variability visualization tailored to the needs of aPS stakeholders such as application or module developers. To address this gap, this paper introduces a variability visualization concept tailored to the needs of aPS stakeholders with the aim of supporting them in their daily tasks. The concept was evaluated successfully within a master student's course by use of a prototypical implementation of the visualization concept.

关键词： Visualization Documentation software software product lines Stakeholders Task analysis software reusability

Multi-model Fusion Solution for IEEE UV 2022 “Vision Meets Algae” Object Detection Challenge

学校读者我要写书评

暂无评论

Multi-model Fusion Solution for IEEE UV 2022 “Vision Meets ...

International Conference on Universal Village (UV)

作者： Xiaoxiao Peng Yueyi Wang Dayu Chen Yuchen Tian Keyu Huang Jianfeng Zheng Department of Automatic Driving Software Engineering smart Motor (Shanghai) Robot Technology Co. Ltd Shanghai China Department of Informatics King’s College London London United Kingdom Department of Algorithm Strategy Didi Chuxing Hangzhou China Institute of Advanced Technology University of Science and Technology of China Anhui China Department of Algorithm Strategy Koto Communication Technology Co. Ltd Xiamen China

This report summarizes the fourth-place solution of the “Vision Meets Algae” object detection challenge held on IEEE UV’2022 focuses on object detection in marine biology images obtained through the microscope. First, we experimented with a large number of backbones and necks to improve mAP by enhancing the model structure. Then, we designed and tested a variety of data augmentation schemes based on algal characteristics from a data perspective. Finally, with multiple models ensembled adopted, our methods achieve 57.579% mAP on the test set.

关键词：

Exploring the integration of multi criteria decision analysis in the clean energy biodiesels applications: A systematic review and gap analysis

学校读者我要写书评

暂无评论

engineering Applications of Artificial Intelligence 2024年 133卷

作者： Alamoodi, A.H. Garfan, Salem Al-Zuhairi, Omar Zaidan, B.B. Zaidan, A.A. Albahri, O.S. Y.Y. Ahmaro, Ibraheem Albahri, A.S. Yussof, Salman Magableh, Aws A. Institute of Informatics and Computing in Energy Universiti Tenaga Nasional Malaysia Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Perak Malaysia Applied Science Research Center Applied Science Private University Amman Jordan Low Dimensional Materials Research Centre Department of Physics Faculty of Science Universiti Malaya Kuala Lumpur50603 Malaysia SP Jain School of Global Management Lidcombe SydneyNSW2141 Australia International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Victorian Institute of Technology Australia Computer Techniques Engineering Department Mazaya University College Nasiriyah Iraq Computer Science Department College of Information Technology Hebron University Hebron Palestine Technical College Imam Ja'afar Al-Sadiq University Baghdad Iraq Department of Information Systems Yarmouk University Irbid Jordan Baghdad Iraq Department of Computing College of Computing and Informatics Universiti Tenaga Nasional Malaysia Departments of Software Engineering Prince Sultan University Riyad Saudi Arabia

Biodiesel has gained tremendous attention from researchers due to its environmentally friendly and renewable fuel manufactured domestically from vegetable oils or animal fats. Multiple factors, including emission and fuel efficiency, measure the performance of biodiesel. These characteristics make the process of evaluation and benchmarking a multi-criteria decision-making (MCDM) problem. This research attempts to survey the literature for multi-criteria decision-making applications on biodiesel. This systematic review was carried out on four scientific databases: PubMed, ScienceDirect, IEEE Xplore, and WoS. The collected articles were summarized and mapped into a coherent taxonomy, while the main challenges, motivations, and recommendations were collected and categorized for better understanding and finding out essential characteristics. The final set of included articles was 33, and they were categorized into six different categories. Most articles (n=15/33) investigated the evaluation and selection of biodiesel alternatives using MCDM. Furthermore, a state-of-art bibliometric analysis is provided. The analysis demonstrates several challenges in this area, such as source selection, optimum fuel blending, and uncertainty. This article is expected to assist future researchers in addressing the current gaps and contribute to advancing this area. © 2024 Elsevier Ltd

关键词： Biodiesel