检索结果-内蒙古大学图书馆

International Conference on Computational Science and Computational Intelligence (CSCI)

作者： Juan Zuluaga Michael Castillo Divya Syal Andres Calle Navid Shaghaghi Department of Bioengineering (BIOE) Computer Science & Engineering (CSEN) Ethical Pragmatic & Intelligent Computing (EPIC) Laboratory in collaboration with the Healthcare Innovation & Design (HID) Program Information Systems & Analytics (ISA) and Mathematics & Computer Science (MCS) Santa Clara University Santa Clara California USA

Humanity has battled tuberculosis for all of recorded history. Some studies estimate that Mycobacterium tuberculosis may have been around as long as 3 million years but it was only in 1834 when Johann Schonlein officially presented the characteristics of it. Even though the TB epidemic has touched all corners of the world, Africa and Asia are the regions that currently suffer the worst consequences. The purpose of this study is to construct a model within the eVision forecasting environment, capable of forecasting the trend of Tuberculosis cases in India, as India is the country that accounts for the largest percentage of TB cases and deaths worldwide. And being able to make predictions for India may also lead to successful results for other regions in Asia and Africa. In order to do so, this study presents different test cases that show the effectiveness of the model, varying the number of steps for each one of the data sets created. It's important to note, that these data sets are combinations of data gathered from the states with the most TB cases in India in the last years, as well as the total data for India, and supplemental data from Google Trends, as a way to facilitate the machine learning model. Even though the final results were respectable compared to past research done on India and other countries, the model nevertheless has a limitation on the number of weeks ahead which the predictions are still considered to be good; with 7 weeks being the optimal result.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding Audiovisual Deepfake Detection: Techniques, Challenges, Human Factors and Perceptual Insights

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan The Department of Computer Science National Chengchi University Taipei11529 Taiwan The Department of Electrical Engineering The Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Deep Learning has been successfully applied in diverse fields, and its impact on deepfake detection is no exception. Deepfakes are fake yet realistic synthetic content that can be used deceitfully for political impersonation, phishing, slandering, or spreading misinformation. Despite extensive research on unimodal deepfake detection, identifying complex deepfakes through joint analysis of audio and visual streams remains relatively unexplored. To fill this gap, this survey first provides an overview of audiovisual deepfake generation techniques, applications, and their consequences, and then provides a comprehensive review of state-of-the-art methods that combine audio and visual modalities to enhance detection accuracy, summarizing and critically analyzing their strengths and limitations. Furthermore, we discuss existing open source datasets for a deeper understanding, which can contribute to the research community and provide necessary information to beginners who want to analyze deep learning-based audiovisual methods for video forensics. By bridging the gap between unimodal and multimodal approaches, this paper aims to improve the effectiveness of deepfake detection strategies and guide future research in cybersecurity and media integrity. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

Unmasking Illusions: Understanding Human Perception of Audiovisual Deepfakes

arXiv

引用

arXiv 2024年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Institute of Information Science Academia Sinica Taipei11529 Taiwan Institute of Information Systems and Applications National Tsing Hua University Hsinchu300044 Taiwan Department of Computer Science National Chengchi University Taipei11529 Taiwan Department of Electrical Engineering Institute of Communications Engineering National Tsing Hua University Hsinchu300044 Taiwan Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan Institute of Information Science Academia Sinica Taipei11529 Taiwan

The emergence of contemporary deepfakes has attracted significant attention in machine learning research, as artificial intelligence (AI) generated synthetic media increases the incidence of misinterpretation and is difficult to distinguish from genuine content. Currently, machine learning techniques have been extensively studied for automatically detecting deepfakes. However, human perception has been less explored. Malicious deepfakes could ultimately cause public and social problems. Can we humans correctly perceive the authenticity of the content of the videos we watch? The answer is obviously uncertain;therefore, this paper aims to evaluate the human ability to discern deepfake videos through a subjective study. We present our findings by comparing human observers to five state-of-the-art deepfake detection models. To this end, we used gamification concepts to provide 110 participants (55 native English speakers and 55 non-native English speakers) with a web-based platform where they could access a series of 40 videos (20 real and 20 fake) to determine their authenticity. Each participant performed the experiment twice with the same 40 videos in different random orders. The videos are manually selected from the FakeAVCeleb dataset. We found that all AI models performed significantly better than humans when evaluated on the same 40 videos. The study also reveals that while deception is not impossible, humans tend to overestimate their detection capabilities. Our experimental results may help benchmark human versus machine performance, advance forensics analysis, and enable adaptive countermeasures. © 2024, CC BY.

关键词： Audiovisual

来源：评论

学校读者我要写书评

暂无评论

FluxProg 2.0 - Teaching Introductory programming Using Flowcharts with Real and Simulated Robots for The Brazilian Robotics Olympiad (OBR)

FluxProg 2.0 - Teaching Introductory Programming Using Flowc...

引用

IEEE Latin American Robotics Symposium, LARS

作者： João Alberto Fabro Matheus Biscaya Gutierrez Fernando Henrique Ratusznei Caetano DAINF - Academic Department of Informatica PPGCA - Graduate Program on Applied Computing LASER-Laboratory for Advanced Robotics and Embedded Systems UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil Information Systems academic - UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil Computer Engineering academic - UTFPR - Federal University of Technology - Paraná Curitiba PR - Brazil

ISBN: (数字)9781665462808

ISBN: (纸本)9781665462815

In this paper, an approach to aid in introductory programming courses is presented, focused on students that had never had any contact with computer programming. The approach, that was introduced in a previous paper [3], presents programming concepts using icons and “flowcharts”, and a 3D robotics simulator (CoppeliaSim), that has free educational use. This time, a real version of the simulated robot, built using Arduino and cheap, easily obtainable electronic components, is also presented. The programs to control the robot are developed by graphically constructing flowcharts on the visual editor, and then following the execution of programs using the simulated (or real) robot, step by step. This graphic program editor is named “FluxProg”, and its 2nd version is now available online, with new features comprising variables, arithmetic and logic expressions, thus providing a complete programming environment.

关键词： Flowcharts Visualization Three-dimensional displays Conferences Education Electronic components Robots

来源：评论

学校读者我要写书评

暂无评论

Experiences with Postdoctoral Training in Human Factors: Mentor and Trainee Perspectives

引用

Proceedings of the Human Factors and Ergonomics Society Annual Meeting 2023年第1期67卷 265 - 269页

作者： Kelly Caine Ken Catchpole Farzan Sasangohar Karen B. Chen Sudeep Hegde Dustin Souders Anthony McDonald Elease J. McLaurin Clemson University School of Computing Clemson SC USA Medical University of South Carolina Clinical Practice and Human Factors Charleston SC USA Texas A&M University Industrial and Systems Engineering Central SC USA North Carolina State University Edward P. Fitts Department of Industrial and Systems Engineering Raleigh NC USA Clemson University Department of Industrial Engineering Central SC USA Clemson University Psychology Department Clemson SC USA University of Wisconsin-Madison Department of Industrial and Systems Engineering Madison WI USA Oak Ridge Institute for Science & Education Fellowship Program Centers for Disease Control & Prevention Philadelphia PA USA

Postdoctoral training positions are becoming more common in the human factors and ergonomics (HFE) discipline. However, conversations related to training in the HFE discipline have largely focused on undergraduate and graduate education. This panel assembles both postdoctoral mentors and former trainees who collectively have a diverse set of HFE-related postdoctoral experiences. By panelists discussing their experiences, observations, and recommendations related to postdoctoral training with the audience, the panel session will support HFE faculty and students in making more informed decisions about if and how a postdoctoral experience (either as a mentor or trainee) could be a part of their career development in HFE.

关键词： education postdoctoral training human factors mentorship

来源：评论

学校读者我要写书评

暂无评论

Any Bluetooth device can be hacked. Know how?

Cyber Security and Applications

引用

Cyber Security and Applications 2024年 2卷

作者： Muraleedhara, Prathibha Christo, Mary Subaja J, Jaya Yuvasini  D College of Technology – Information Security and Program Management University of Houston 77204 TX United States Department of Networking and Communication School of Computing SRM Institute of Science and Technology Kantankulathur Chennai India Department of Electronics and Communication Engineering Hindustan College of Engineering and Technology India Assistant Professor Department of Computer Science and Business Systems Thiagarajar College of Engineering Madurai 625015 India

In today's world, Bluetooth technology is integrated into almost every device we use, from wireless headsets, mice, and keyboards to cars and smart home devices. But with the convenience of this technology comes the risk of privacy and security breaches. Each Bluetooth device has potential vulnerabilities that cybercriminals can exploit and take advantage of. It is important to create awareness about various Bluetooth vulnerabilities, exploits, and ways to prevent them. This article examines the dark side of Bluetooth technology by explaining how hackers can find ways to bypass the advanced security features of laptops, phones, cars, or smart home devices to compromise the devices and steal personal sensitive data. Whether it is a casual user of Bluetooth technology or a business owner with multiple devices, understanding these risks is crucial to protecting yourself and your information. This article begins by explaining the basics of Bluetooth technology and how it works. Followed by a list of security risks involved while using Bluetooth and finally, it highlights the best practices to protect the devices and the data they contain. © 2024

关键词： Ad hoc networks and security risk Bluetooth Exploit Threat Vulnerability

来源：评论

学校读者我要写书评

暂无评论

Towards Safe AI Clinicians: A Comprehensive Study on Large Language Model Jailbreaking in Healthcare

arXiv

引用

arXiv 2025年

作者： Zhang, Hang Lou, Qian Wang, Yanshan Intelligent Systems Program School of Computing and Information University of Pittsburgh PA United States Department of Computer Science University of Central Florida OrlandoFL United States Department of Health Information Management University of Pittsburgh PA United States Department of Biomedical Informatics University of Pittsburgh PA United States Clinical and Translational Science Institute University of Pittsburgh PittsburghPA United States University of Pittsburgh Medical Center PittsburghPA United States

Large language models (LLMs) are increasingly utilized in healthcare applications. However, their deployment in clinical practice raises significant safety concerns, including the potential spread of harmful information. This study systematically assesses the vulnerabilities of seven LLMs to three advanced black-box jailbreaking techniques within medical contexts. To quantify the effectiveness of these techniques, we propose an automated and domain-adapted agentic evaluation pipeline. Experiment results indicate that leading commercial and open-source LLMs are highly vulnerable to medical jailbreaking attacks. To bolster model safety and reliability, we further investigate the effectiveness of Continual Fine-Tuning (CFT) in defending against medical adversarial attacks. Our findings underscore the necessity for evolving attack methods evaluation, domain-specific safety alignment, and LLM safety-utility balancing. This research offers actionable insights for advancing the safety and reliability of AI clinicians, contributing to ethical and effective AI deployment in healthcare. © 2025, CC BY-NC-SA.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Modular boundaries in recurrent neural networks

arXiv

引用

arXiv 2023年

作者： Tanner, Jacob C. Mansour, Sina L. Coletta, Ludovico Gozzi, Alessandro Betzel, Richard F. Cognitive Science Program 2 School of Informatics Computing and Engineering Indiana University BloomingtonIN47405 United States National University of Singapore Singapore Fondazione Bruno Kessler Trento Italy Functional Neuroimaging Lab Istituto Italiano di Tecnologia Center for Neuroscience and Cognitive Systems Rovereto Italy Department of Psychological and Brain Sciences Indiana University BloomingtonIN47405 United States

Recent theoretical and experimental work in neuroscience has focused on the representational and dynamical character of neural manifolds –subspaces in neural activity space wherein many neurons coactivate. Importantly, neural populations studied under this "neural manifold hypothesis" are continuous and not cleanly divided into separate neural populations. This perspective clashes with the "modular hypothesis" of brain organization, wherein neural elements maintain an "all- or-nothing" affiliation with modules. In line with this modular hypothesis, recent research on recurrent neural networks suggests that multi-task networks become modular across training, such that different modules specialize for task-general dynamical motifs [1, 2]. If the modular hypothesis is true, then it would be important to use a dimensionality reduction technique that captures modular structure. Here, we investigate the features of such a method. We leverage RNNs as a model system to study the character of modular neural populations, using a community detection method from network science known as modularity maximization to partition neurons into distinct modules. These partitions allow us to ask the following question: do these modular boundaries matter to the system? We find evidence that they do. First, we find that these boundaries neatly divide the representational content and role of neurons. Next, we find that these boundaries can be directly inferred from features of the weight matrix in feed-forward neural networks, and are related to clustering of the Jacobian matrix in recurrent neural networks. We also find that the weights of input neurons to recurrent neurons partially inform their modular structure, an observation that we corroborated using structural and functional imaging data from mice and humans. Finally, we find that the dynamics of these RNNs reflected the boundaries between modules. Collectively, our results suggest that neural populations in RNNs sometimes form modu

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Pattern Classification Applying Neighbourhood Component Analysis and Swarm Evolutionary Algorithms: A Coupled Methodology

Pattern Classification Applying Neighbourhood Component Anal...

引用

Congress on Evolutionary Computation

作者： Gabriel M. C. Leite Carolina G. Marcelino Elizabeth F. Wanner Carlos E. Pedreira Silvia Jiménez-Fernández Sancho Salcedo-Sanz Systems and Computing Program (PESC) Federal University of Rio de Janeiro Rio de Janeiro Brazil Institute of Computing UFRJ UAH Rio de Janeiro Madrid Brazil Spain CEFET-MG Belo Horizonte Brazil Universidad de Alcalá Madrid Spain

In this work we present a pattern classification approach coupling the Neighbourhood Component Analysis (NCA) classifier with the Canonical Differential Evolutionary Particle Swarm Optimization (C-DEEPSO). The standard NCA uses the conjugate gradient method to minimize the classification error. Here we propose an approach using the C-DEEPSO instead. In the experimental design, the coupled approach is applied to 20 benchmark data sets, and its performance is compared with the standard NCA using the conjugate gradient. The experimental analysis shows the usage of an evolutionary approach to enhance the performance of a machine learning algorithm can be competitive when compared to well-known iterative optimization techniques, and even outperform them in some problems. A real-world problem classifying cyber-attacks to an industrial control system of gas pipelines is also solved by the proposed approach. The results obtained indicate the proposed approach can successfully identify possible cyber-attacks to the control system. In this way, the NCA coupled to C-DEEPSO can work as an Intrusion Detection systems (IDS), being able to guarantee an acceptable security level.

关键词： Machine learning algorithms Industrial control Pipelines Pattern classification Intrusion detection Iterative algorithms Security

来源：评论

学校读者我要写书评

暂无评论

Double-SP Method to Enhance Privacy and Security of Smart City Applications

Double-SP Method to Enhance Privacy and Security of Smart Ci...

引用

International Conference on computing for Sustainable Global Development (INDIACom)

作者： Nour Mahmoud Bahbouh Abdulelah Alhussain Hassan Hakami Yaser Mohammed Aljohani Adnan Ahmed Abi Sen Ahmad Alkhodre Aeshah Alsughayyir Department of Information and Communication Sciences Granada University Granada Spain Saudi Electronic University Al-Madinah Saudi Arabia YasRef Program Yanbu Saudi Arabia Computing and Information Technology Islamic University Al-Madinah Saudi Arabia Faculty of Computer and Information Systems Islamic University Al-Madinah Saudi Arabia College of Computer Science and Engineering Taibah University Al-Madinah Saudi Arabia

Smart cities promise a lot of well-being to their users in all areas of life through millions of applications and services. Smart services rely heavily on collecting data and the preferences of users. But on the dark side, the users' information is posed to threat and penetration during transmission or stored far in the clouds. Depending on encryption only is not sufficient if the attacker has strong resources or if the attacker is the service provider (SP) itself. In addition, changing data before sending is not a practical solution in many systems because of the adverse impact on the quality of a main service. This research presented a new idea to address the issue of protection. The proposed method enhanced the privacy and security of users' data without affecting the accuracy of service. The core of the suggested solution relies on a knowledge base of services that are managed by experts. Also, the solution depends on fog nodes to measure the level of security and privacy of users' queries without delay. Moreover, the fog nodes manage contact with SPs. Finally, the proposed method divided the SP into two, one for user queries and the other for user data. The simulation and analytical discussion on a practical case in smart cities demonstrated the superiority of the proposed approach over previous methods in the level of protection by maintaining the quality of services, and the resistance to attacks.

关键词： Resistance Privacy Data privacy Machine learning algorithms Smart cities Knowledge based systems Quality of service

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：