检索结果-内蒙古大学图书馆

International Seminar on Research of Information Technology and Intelligent Systems (ISRITI)

作者： Fadel Ali Aniati Murni Arymurthy Radityo Eko Prasojo Faculty of Computer Science Universitas Indonesia Depok Indonesia Department of AI & Data Pitik Digital Indonesia South Tangerang Indonesia

Speech Emotion Recognition (SER) is a pivotal area in Human-computer Interaction (HCI) with numerous applications. Traditional SER models rely on supervised learning but face challenges due to limited labeled data and the subjective nature of emotions. Self-supervised learning (SSL) offers an alternative by leveraging unlabeled audio data. WavLM, a large-scale SSL audio model, has shown promise in various speech processing tasks. This paper investigates the fine-tuning of WavLM for SER, analyzing the impact of different segment of layers on performance. We conducted experiments on the IEMOCAP and RAVDESS datasets, comparing various fine-tuned WavLM models with Wav2Vec 2.0 and HuBERT as SSL baselines. Results reveal that WavLM outperforms SSL base-lines, with all-layer fine-tuned WavLM achieving state-of-the-art results. Interestingly, fine-tuning top layers significantly enhances performance, suggesting their role in encoding paralinguistic information. However, fine-tuning all layers remains superior. These findings shed light on optimizing SSL audio models for SER and highlight WavLM's potential in emotion recognition.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Private Image Generation with Dual-Purpose Auxiliary Classifier

Private Image Generation with Dual-Purpose Auxiliary Classif...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Chen Chen Daochang Liu Siqi Ma Surya Nepal Chang Xu School of Computer Science The University of Sydney Faculty of Engineering The University of New South Wales Canberra CSIRO Data61

Privacy-preserving image generation has been important for segments such as medical domains that have sensitive and limited data. The benefits of guaranteed privacy come at the costs of generated images' quality and utility due to the privacy budget constraints. The utility is currently measured by the gen2real accuracy (g2r%), i.e., the accuracy on real data of a downstream classifier trained using generated data. However, apart from this standard utility, we identify the “reversed utility” as another crucial aspect, which computes the accuracy on generated data of a classifier trained using real data, dubbed as real2gen accuracy (r2g%). Jointly considering these two views of utility, the standard and the reversed, could help the generation model better improve transferability between fake and real data. Therefore, we propose a novel private image generation method that incorporates a dual-purpose auxiliary classifier, which alternates between learning from real data and fake data, into the training of differentially private GANs. Additionally, our deliberate training strategies such as sequential training contributes to accelerating the generator's convergence and further boosting the performance upon exhausting the privacy budget. Our results achieve new state-of-the-arts over all metrics on three benchmarks: MNIST, Fashion-MNIST, and CelebA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identifying human values from goal models: An industrial case study

arXiv

引用

arXiv 2023年

作者： Iqbal, Tahira Taveter, Kuldar Strenze, Tarmo Hussain, Waqar Haggag, Omar Matthews, John Alphonsus Piirisild, Anu Institute of Computer Science University of Tartu Estonia Data 61 CSIRO Australia Faculty of Information Technology Monash University Australia

Human values are principles that guide human actions and behaviour in personal and social life. Ignoring human values during requirements engineering introduces a negative impact on software uptake and continued use. Embedding human values into software is admittedly challenging;however, early elicitation of stakeholder values increases the chances of their inclusion into the developed system. Using Pharaon, a research and innovation project of the European Union’s Horizon 2020 program, as a case study we analysed stakeholder requirements expressed as motivational goal models consisting of functional, quality, and emotional goals in three large-scale trial applications of the project. We were able to elicit 9 of 10 human values according to the theory of human values by Schwartz from the motivational goal models that represent the requirements for the three applications. Our findings highlight the dominant trend of stakeholder values being embedded in emotional goals and show that almost 45% of the identified values belong to the value categories of Security and Self-direction. Our research extends prior work in emotional goal modelling in requirements engineering by linking emotional goals to various stakeholder roles and identifying their values based on the Schwartz theory of human values. © 2023, CC BY.

关键词： Requirements engineering

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Malware Detection in the Industrial Internet of Things: A Comprehensive Analysis

Deep Learning Approaches for Malware Detection in the Indust...

引用

Information Technology (ACIT)

作者： Ghassan Samara Mohammad Abu Fadda Abeer Al-Mohtaseb Raed Alazaidah Alrefai Mohamed N. Mahmoud Odeh Mohammad Aljaidi Mohammed Mahmod Shuaib Mohammad Kanan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Faculty of Information Technology Zarqa University Zarqa Jordan Department of Data Science and AI Faculty of Information Technology Zarqa University Zarqa Jordan Department of Mathematics Faculty of Science Zarqa University Zarqa Jordan Department of Industrial Engineering University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

This survey aims to identify hazards associated with the Internet of Things (IoT), focusing on malware that can infiltrate various devices, applications, and systems within the Industrial Internet of Things (IIoT). Such malware enables malicious actors to manipulate these systems. This research utilizes deep learning as a method for detecting malicious programs. Additionally, it provides hypotheses and background information on deep learning and the IIoT, along with an overview of the types of malware that can compromise IoT applications. Finally, the study presents findings related to the research hypotheses and relevant topics.

关键词： Deep learning Surveys Accuracy Focusing Malware Hazards Object recognition Information technology Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Systematic Biases in LLM Simulations of Debates

Systematic Biases in LLM Simulations of Debates

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Taubenfeld, Amir Dover, Yaniv Reichart, Roi Goldstein, Ariel The Hebrew University of Jerusalem School of Computer Science and Engineering Israel Google Research United States The Hebrew University Business School Jerusalem Israel Federmann Center for the Study of Rationality Hebrew University Jerusalem Israel Faculty of Data and Decision Sciences Technion Israel Department of Cognitive and Brain Sciences Hebrew University Jerusalem Israel

ISBN: (纸本)9798891761643

The emergence of Large Language Models (LLMs), has opened exciting possibilities for constructing computational simulations designed to replicate human behavior accurately. Current research suggests that LLM-based agents become increasingly human-like in their performance, sparking interest in using these AI agents as substitutes for human participants in behavioral studies. However, LLMs are complex statistical learners without straightforward deductive rules, making them prone to unexpected behaviors. Hence, it is crucial to study and pinpoint the key behavioral distinctions between humans and LLM-based agents. In this study, we highlight the limitations of LLMs in simulating human interactions, particularly focusing on LLMs' ability to simulate political debates on topics that are important aspects of people's day-to-day lives and decision-making processes. Our findings indicate a tendency for LLM agents to conform to the model's inherent social biases despite being directed to debate from certain political perspectives. This tendency results in behavioral patterns that seem to deviate from well-established social dynamics among humans. We reinforce these observations using an automatic self-fine-tuning method, which enables us to manipulate the biases within the LLM and demonstrate that agents subsequently align with the altered biases. These results underscore the need for further research to develop methods that help agents overcome these biases, a critical step toward creating more realistic simulations. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Empowering Open data Sharing for Social Good: A Privacy-Aware Approach

arXiv

引用

arXiv 2024年

作者： Carvalho, Tânia Antunes, Luís Costa, Cristina Moniz, Nuno Faculty of Computer Science University of Porto Portugal TekPrivacy Porto Portugal Faculty of Medicine University of Porto Portugal Lucy Family Institute for Data and Society University of Notre Dame IN United States

The Covid-19 pandemic has affected the world at multiple levels. data sharing was pivotal for advancing research to understand the underlying causes and implement effective containment strategies. In response, many countries have promoted the availability of daily cases to support research initiatives, fostering collaboration between organisations and making such data available to the public through open data platforms. Despite the several advantages of data sharing, one of the major concerns before releasing health data is its impact on individuals’ privacy. Such a sharing process should be based on state-of-the-art methods in data Protection by Design and by Default. In this paper, we use a data set related to Covid-19 cases in the second largest hospital in Portugal to show how it is feasible to ensure data privacy while improving the quality and maintaining the utility of the data. Our goal is to demonstrate how knowledge exchange in multidisciplinary teams of healthcare practitioners, data privacy, and data science experts is crucial to co-developing strategies that ensure high utility of de-identified data. © 2024, CC BY-NC-SA.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Fortifying database Security: Integrating Advanced Honeypot Technology for Resilient SQL Injection Defense

Fortifying Database Security: Integrating Advanced Honeypot ...

引用

Communication, computer sciences and Engineering (IC3SE), International Conference on

作者： Kumaran U Thammisetty Swetha G. S. N. Santhosh Reddy Harini Ala Senthil Murugan Nagarajan B. Umah Department of Computer Science & Engineering Amrita School of Computing Bengaluru India Department of Computer Science & Engineering (Data Science) Madanapalle Institute of Technology & Science Madanapalle Andhra Pradesh India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru Karnataka India Department of Mathematics Faculty of Science Technology and Medicine University of Luxembourg Luxembourg Department of Computer Science & Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Bengaluru Karnataka India

ISBN: (数字)9798350366846

ISBN: (纸本)9798350366853

The dynamic nature of cyber threats necessitates the development of novel approaches to strengthen database system security. The novel method for fortifying defenses against SQL injection attacks—a pervasive and ongoing danger in the field of cybersecurity—is presented in this study. The suggested methodology creates a strong and adaptable defense mechanism by seamlessly integrating cutting-edge honeypot technology with current SQL injection mitigation techniques. Our approach, which we have named HoneySQLGuard, uses carefully con- structed honeypot tables inside the database system. These tables serve as sly bait, drawing potential attackers’ attention away from genuine data and toward themselves. By utilizing the most recent developments in technology, Honey SQL Guard surpasses the limitations of conventional signature-based detection techniques and is able to adjust to changing attack strategies via anomaly and machine learning. The honeypot tables are cleverly incorporated within the database architecture, making them invisible to an outside observer when compared to real tables. The technology immediately recognizes and isolates unusual behavior suggestive of SQL injection attempts by closely monitoring and analyzing query patterns. Furthermore, HoneySQLGuard has real-time reporting and alerting functions that guarantee an early reaction to any possible intrusions. Extensive testing is conducted to validate the effectiveness of the proposed solution, which shows it can dramatically lower the success rate of SQL injection attacks while keeping false-positive rates low. This study advances the subject by providing a thorough and flexible method for fortifying databases against SQL injection attacks, in line with the industry's increasing demand for robust cybersecurity defenses.

关键词： Protocols Prevention and mitigation Machine learning SQL injection Observers database systems Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Classifier Performance on Reduced Feature Sets

Comparative Analysis of Classifier Performance on Reduced Fe...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Raed Alazaidah Wael Hadi Suhaila Abu Owaida Alaa Bani-bakr Mo'ath Alluwaici Muhyeeddin Alqaraleh Department of Data Science Faculty of Information Technology Zarqa University Zarqa Jordan Department of Information Security Faculty of Information Technology University of Petra Amman Jordan Department of Computer Science Faculty of Information Technology Al-al-Bayt University Mafraq Jordan Department of Cyber Security Faculty of Information Technology Zarqa University Zarqa Jordan Department of Computer Science Faculty of Information Technology Zarqa University Zarqa Jordan Software Engineering Department Faculty of Information Technology Zarqa University Zarqa Jordan

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

In this study, we examine the impact of feature reduction on the performance of various classifiers within the Weka environment. Utilizing the Pima Indians Diabetes database, we compare the Accuracy, Precision, Recall, F1-measure, and other relevant metrics across classifiers like BayesNet, NaiveBayes, and NaiveBayesMul when applied to full and reduced feature sets. The reduction process involves halving the attribute count, aiming to assess the efficacy of machine learning models in scenarios with constrained feature availability. Our results indicate significant differences in the performance of the models, offering insights into the trade-offs between model complexity and predictive power in medical dataset applications.

关键词： Measurement Productivity data analysis Accuracy Systematics databases Machine learning Predictive models Diabetes Reliability

来源：评论

学校读者我要写书评

暂无评论

EdgeAuth: An intelligent token-based collaborative authentication scheme

EdgeAuth: An intelligent token-based collaborative authentic...

引用

作者： Jiang, Xutong Dou, Ruihan He, Qiang Zhang, Xuyun Dou, Wanchun State Key Laboratory for Novel Software Technology Nanjing University Nanjing China Faculty of Mathematics University of Waterloo Waterloo Canada Department of Computer Science and Software Engineering Swinburne University of Technology Melbourne Australia Department of Computing Macquarie University Sydney Australia College of Big Data and Intelligent Engineering Southwest Forestry University China

Edge computing is regarded as an extension of cloud computing that brings computing and storage resources to the network edge. For some Industrial Internet of Things (IIoT) applications such as supply-chain supervision and collaboration, Internet of Vehicles, real-time video analysis and so forth, users should be authenticated before visiting the geographically distributed edge servers. Limited by the considerable latency between the cloud and edge servers, and the limited capacity of edge servers, it is infeasible to copy the authentication method from cloud servers when users are authenticated in edge servers. In view of this challenge, this paper proposes a novel token-based authentication scheme, named EdgeAuth, that enables fast edge user authentication through collaboration among cloud servers and edge servers. Under the EdgeAuth scheme, edge servers can rapidly verify the credentials of users who have been authenticated by the cloud server. EdgeAuth can also protect users from a series of authentication attacks, for example, the replay attack, DoS attack and man-in-the-middle attack. The results of experiments conducted on a simulated edge computing environment validate the usefulness of EdgeAuth through a comparison in latency and throughput against two baseline schemes. © 2023 John Wiley & Sons Ltd.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values

arXiv

引用

arXiv 2024年

作者： Zheng, Yu Koh, Huan Yee Jin, Ming Chi, Lianhua Wang, Haishuai Phan, Khoa T. Chen, Yi-Ping Phoebe Pan, Shirui Xiang, Wei Department of Computer Science and Information Technology La Trobe University Australia Department of Data Science and AI Faculty of IT Monash University Australia School of Information and Communication Technology Griffith University Australia Zhejiang University China

The detection of anomalies in multivariate time series data is crucial for various practical applications, including smart power grids, traffic flow forecasting, and industrial process control. However, real-world time series data is usually not well-structured, posting significant challenges to existing approaches: (1) The existence of missing values in multivariate time series data along variable and time dimensions hinders the effective modeling of interwoven spatial and temporal dependencies, resulting in important patterns being overlooked during model training;(2) Anomaly scoring with irregularly-sampled observations is less explored, making it difficult to use existing detectors for multivariate series without fully-observed values. In this work, we introduce a novel framework called GST-Pro, which utilizes a graph spatiotemporal process and anomaly scorer to tackle the aforementioned challenges in detecting anomalies on irregularly-sampled multivariate time series. Our approach comprises two main components. First, we propose a graph spatiotemporal process based on neural controlled differential equations. This process enables effective modeling of multivariate time series from both spatial and temporal perspectives, even when the data contains missing values. Second, we present a novel distribution-based anomaly scoring mechanism that alleviates the reliance on complete uniform observations. By analyzing the predictions of the graph spatiotemporal process, our approach allows anomalies to be easily detected. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods, regardless of whether there are missing values present in the data. Our code is available: https://***/huankoh/GST-Pro. © 2024, CC BY.

关键词： Time series

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：