检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1895-1908页

作者： Lu, Zhi Lu, Songfeng Tang, Xueming Wu, Junjun Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518063 China

Federated learning (FL) safeguards user privacy by uploading gradients instead of raw data. However, inference attacks can reconstruct raw data using gradients uploaded by users in FL. To mitigate this issue, researchers have combined privacy computing techniques with FL. However, these techniques may not ensure the Byzantine robustness of aggregation or the integrity of the aggregated outcomes. Most current robust privacy FL methods assess differences between gradients and benchmarks in the direction, allowing adversaries to poison the aggregation against the magnitude. Furthermore, these methods cannot ensure the integrity of the aggregation results. To overcome these challenges, this study proposes a novel algorithm, robust and verifiable privacy federated learning (RVPFL), which can more effectively eliminate the poisoning attack of the opponent by measuring the direction and magnitude of the gradient in the ciphertext state. The proposed algorithm guarantees the integrity of server aggregation results while safeguarding user privacy. In this study, comprehensive theoretical analysis and experimental validation of RVPFL are conducted to demonstrate its superiority. The proposed RVPFL algorithm solves the Byzantine robustness problem of aggregation and the integrity problem of aggregation results, which helps to research and develop more robust and effective privacy-preserving federal learning techniques. © 2020 IEEE.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Attributing Mental States to Non-Embodied Autonomous Systems: A Systematic Review

Attributing Mental States to Non-Embodied Autonomous Systems...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Wischnewski, Magdalena Research Center Trustworthy Data Science and Security Dortmund Germany

ISBN: (纸本)9798400713958

Rapidly evolving, non-embodied autonomous agents, oftentimes powered by AI, have been shown to trigger mental state attributions by users. However, unlike embodied agents, attributions to non-embodied autonomous agents are not caused by physical presence but by language or abstract interfaces. To better understand this fast-growing field, the present article presents a systematic literature review of mental state attribution to non-embodied autonomous agents. Based on a literature body of 400+ papers, 26 relevant publications were identified, providing an overview of the communities studying mental state attributions, the study’s design choices, and findings of these efforts. The findings indicate that (1) the HCI community is less involved in the study of mental state attributions, (2) a lacking validity of the measures limits the current measurement of mental state attributions, (3) there is a skew towards chat- and voice bots, and (4) mental state attributions increased vulnerabilities of users and shifts in accountability. © 2025 Copyright held by the owner/author(s).

关键词： agent artificial intelligence autonomous mental states mind perception non-embodied

来源：评论

学校读者我要写书评

暂无评论

Aggregation-based dual heterogeneous task allocation in spatial crowdsourcing

引用

Frontiers of Computer science 2024年第6期18卷 215-227页

作者： Xiaochuan LIN Kaimin WEI Zhetao LI Jinpeng CHEN Tingrui PEI College of Information Science and Technology&Cyberspace Security Jinan UniversityGuangzhou 510632China National&Local Joint Engineering Research Center of Network Security Detection and Protection Technology Guangzhou 510632China Guangdong Provincial Key Laboratory of Data Security and Privacy Protection Guangzhou 510632China School of Computer Science Beijing University of Posts and TelecommunicationsBeijing 100876China

Spatial crowdsourcing(SC)is a popular data collection paradigm for numerous *** the increment of tasks and workers in SC,heterogeneity becomes an unavoidable difficulty in task *** researches only focus on the single-heterogeneous task ***,a variety of heterogeneous objects coexist in real-world SC *** dramatically expands the space for searching the optimal task allocation solution,affecting the quality and efficiency of data *** this paper,an aggregation-based dual heterogeneous task allocation algorithm is put *** investigates the impact of dual heterogeneous on the task allocation problem and seeks to maximize the quality of task completion and minimize the average travel *** problem is first proved to be ***,a task aggregation method based on locations and requirements is built to reduce task ***,a time-constrained shortest path planning is also developed to shorten the travel distance in a *** that,two evolutionary task allocation schemes are ***,extensive experiments are conducted based on real-world datasets in various *** with baseline algorithms,our proposed schemes enhance the quality of task completion by up to 25% and utilize 34% less average travel distance.

关键词： task allocation aggregation shortest path dual heterogeneous spatial crowdsourcing

来源：评论

学校读者我要写书评

暂无评论

On the Independence of Adversarial Transferability to Topological Changes in the dataset 10

On the Independence of Adversarial Transferability to Topolo...

引用

10th IEEE International Conference on data science and Advanced Analytics, DSAA 2023

作者： Newen, Carina Muller, Emmanuel Tu Dortmund Research Center Trustworthy Data Science & Security Computer Science Dortmund Germany

ISBN: (纸本)9798350345032

One curious property of neural networks is the vulnerability to specific attacks, often called adversarial examples. One of the directions adversarial transferability research has taken is to focus on dataset features. The transferability of adversarials is often linked to those common global features being present or not. To validate this theory, we tested if the transferability of attacks occurs when the underlying global features of a dataset remain the same. This is because topology promises to preserve the properties of an object under continuous deformations. In this paper, we test the correlation between topological similarities using the mapper algorithm by Singh et al. to generate an approximation of the topology in a graphical manner and a distance notion provided by the NetLSD algorithm, which promises size, scale, and permutation invariance. These two algorithms allow us to show that adversarial transferability is, in fact, independent of the topological similarity of datasets. We implement our findings in https://***/KDD-OpenSource/Topological-Transf. This is an astounding new insight, as former theories have led us to expect that if the assumption is true that global features are relevant for transferability, those should be captured using algorithms that detect global features under only topological change- Unless, of course, the transferability and those global features are explicitly agnostic to topological change. This might point to current research regarding adversarial transferability in different directions. More specifically, we take an experimental approach using topological approximation methods to capture essential features of datasets. Past studies concerning adversarial examples show that attacks can transfer in unforeseen ways and between different neural network architectures and may produce severe vulnerabilities in sophisticated learners. However, when tackling the problem of vulnerabilities to adversarial attacks, only a few a

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Resource investment for DDoS attack resistant SDN: a practical assessment

引用

science China(Information sciences) 2023年第7期66卷 112-129页

作者： Bin YUAN Fan ZHANG Jun WAN Huan ZHAO Shui YU Deqing ZOU Qiangsheng HUA Hai JIN School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Engineering Research Center on Big Data Security Shenzhen Huazhong University of Science and Technology Research Institute School of Computer Science and Technology Huazhong University of Science and Technology Cluster and Grid Computing Lab School of Computer Science University of Technology Sydney

Software-defined networks(SDNs) present a novel network architecture that is widely used in various datacenters. However, SDNs also suffer from many types of security threats, among which a distributed denial of service(DDoS) attack, which aims to drain the resources of SDN switches and controllers,is one of the most common. Once the switch or controller is damaged, the network services can be *** defense schemes against DDoS attacks have been proposed from the perspective of attack detection;however, such defense schemes are known to suffer from a time consuming and unpromising accuracy, which could result in an unavailable network service before specific countermeasures are taken. To address this issue through a systematic investigation, we propose an elaborate resource-management mechanism against DDoS attacks in an SDN. Specifically, by considering the SDN topology, we leverage the M/M/c queuing model to measure the resistance of an SDN to DDoS attacks. Network administrators can therefore invest a reasonable number of resources into SDN switches and SDN controllers to defend against DDoS attacks while guaranteeing the quality of service(QoS). Comprehensive analyses and empirical data-based experiments demonstrate the effectiveness of the proposed approach.

关键词： SDN security DDoS attacks resource management queueing theory QoS

来源：评论

学校读者我要写书评

暂无评论

kProtoClust:Towards Adaptive k-Prototype Clustering without Known k

引用

Computers, Materials & Continua 2025年第3期82卷 4949-4976页

作者： Yuan Ping Huina Li Chun Guo Bin Hao School of Information Engineering Xuchang UniversityXuchang461000China Henan Province Engineering Technology Research Center of Big Data Security andApplications Xuchang461000China College of Computer Science and Technology Guizhou UniversityGuiyang550025China Here Data Technology Shenzhen518000China

Towards optimal k-prototype discovery,k-means-like algorithms give us inspirations of central samples collection,yet the unstable seed samples selection,the hypothesis of a circle-like pattern,and the unknown K are still challenges,particularly for non-predetermined data *** propose an adaptive k-prototype clustering method(kProtoClust)which launches cluster exploration with a sketchy division of K clusters and finds evidence for splitting and *** behalf of a group of data samples,support vectors and outliers from the perspective of support vector data description are not the appropriate candidates for prototypes,while inner samples become the first candidates for instability reduction of *** from the representation of samples in traditional,we extend sample selection by encouraging fictitious samples to emphasize the representativeness of *** get out of the circle-like pattern limitation,we introduce a convex decomposition-based strategy of one-cluster-multiple-prototypes in which convex hulls of varying sizes are prototypes,and accurate connection analysis makes the support of arbitrary cluster shapes *** by geometry,the three presented strategies make kProtoClust bypassing the K dependence well with the global and local position relationship analysis for data *** results on twelve datasets of irregular cluster shape or high dimension suggest that kProtoClust handles arbitrary cluster shapes with prominent accuracy even without the prior knowledge K.

关键词： Prototype finding convex hull support vector data description geometrical information

来源：评论

学校读者我要写书评

暂无评论

52 Weeks Later: Attitudes Towards COVID-19 Apps for Different Purposes Over Time

引用

Proceedings of the ACM on Human-Computer Interaction 2023年第CSCW2期7卷 1-45页

作者： Kowalewski, Marvin Utz, Christine Degeling, Martin Schnitzler, Theodor Herbert, Franziska Schaewitz, Leonie Farke, Florian M. Becker, Steffen Dürmuth, Markus Ruhr University Bochum Bochum Germany CISPA Helmholtz Center for Information Security Saarbrücken Germany Research Center Trustworthy Data Science and Security TU Dortmund University Dortmund Germany Max Planck Institute for Security and Privacy Bochum Germany Leibniz University Hannover Hannover Germany

The COVID-19 pandemic has prompted countries around the world to introduce smartphone apps to support disease control efforts. Their purposes range from digital contact tracing to quarantine enforcement to vaccination passports, and their effectiveness often depends on widespread adoption. While previous work has identified factors that promote or hinder adoption, it has typically examined data collected at a single point in time or focused exclusively on digital contact tracing apps. In this work, we conduct the first representative study that examines changes in people's attitudes towards COVID-19-related smartphone apps for five different purposes over the first 1.5 years of the pandemic. In three survey rounds conducted between Summer 2020 and Summer 2021 in the United States and Germany, with approximately 1,000 participants per round and country, we investigate people's willingness to use such apps, their perceived utility, and people's attitudes towards them in different stages of the pandemic. Our results indicate that privacy is a consistent concern for participants, even in a public health crisis, and the collection of identity-related data significantly decreases acceptance of COVID-19 apps. Trust in authorities is essential to increase confidence in government-backed apps and foster citizens' willingness to contribute to crisis management. There is a need for continuous communication with app users to emphasize the benefits of health crisis apps both for individuals and society, thus counteracting decreasing willingness to use them and perceived usefulness as the pandemic evolves. © 2023 Owner/Author.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

ChatGPT as a Negotiator: An Analysis of its Adherence with Proportionality and Equality 7

ChatGPT as a Negotiator: An Analysis of its Adherence with P...

引用

7th International Conference on Algorithms, Computing and Artificial Intelligence, ACAI 2024

作者： Aksoy, Meltem Tsishetska, Veronika Computer Science Research Center Trustworthy Data Science and Security Technical University Dortmund Dortmund Germany Computer Science Technical University Dortmund Dortmund Germany

ISBN: (纸本)9798331529314

This study examines the adherence of ChatGPT (GPT-3.S and GPT-4) to fairness principles, specifically proportionality and equality, in negotiation scenarios. Three distinct negotiation contexts were explored: work-study program funding, company sale proceeds division, and employee bonus allocation. The models were prompted to prioritize proportionality, equality, or no specific fairness principle to assess how they respond in different ethical frameworks. A combination of qualitative and quantitative methods, including dialogue analysis, sentiment tracking, and fairness scoring, was used to evaluate their ne-gotiation behaviors. Results indicate that both models tend to favor proportionality by default, with GPT-4 showing greater adaptability compared to GPT-3.S. When explicitly directed to prioritize equality, the models followed these instructions but maintained a largely assertive negotiation style with limited engagement in dynamic exchanges. Sentiment analysis revealed that both models adopted increasingly positive tones as nego-tiations progressed. However, both versions were susceptible to prompt manipulation, potentially compromising fairness in some outcomes. This research highlights the potential of LLMs like ChatGPT in automating fair negotiations, though improvements in consistency, adaptability, and safeguards against manipulation are necessary for more robust, ethical applications in real-world scenarios. © 2024 IEEE.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Bridging the Early science Gap with Artificial Intelligence Evaluating Large Language Models as Tools for Early Childhood science Education

Bridging the Early Science Gap with Artificial Intelligence ...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Bush, Annika Alibakhshi, Amin Research Center Trustworthy Data Science and Security University Alliance Ruhr TU Dortmund Dortmund Germany Research Center Trustworthy Data Science and Security University Alliance Ruhr Ruhr University Bochum Bochum Germany

ISBN: (纸本)9798400713958

Early childhood science education is crucial for developing scientific literacy, yet translating complex scientific concepts into age-appropriate content remains challenging for educators. Our study evaluates four leading Large Language Models (LLMs) - GPT-4, Claude, Gemini, and Llama - on their ability to generate preschool-appropriate scientific explanations across biology, chemistry, and physics. Through systematic evaluation by 30 nursery teachers using established pedagogical criteria, we identify significant differences in the models’ capabilities to create engaging, accurate, and developmentally appropriate content. Unexpectedly, Claude outperformed other models, particularly in biological topics, while all LLMs struggled with abstract chemical concepts. Our findings provide practical insights for educators leveraging AI in early science education and offer guidance for developers working to enhance LLMs’ educational applications. The results highlight the potential and current limitations of using LLMs to bridge the early science literacy gap. © 2025 Copyright held by the owner/author(s).

关键词： Early Childhood Education Educational Technology Large Language Models Natural sciences Preschool science Education

来源：评论

学校读者我要写书评

暂无评论

The Complexity of Learning LTL, CTL and ATL Formulas 42

The Complexity of Learning LTL, CTL and ATL Formulas

引用

42nd International Symposium on Theoretical Aspects of Computer science, STACS 2025

作者： Bordais, Benjamin Neider, Daniel Roy, Rajarshi TU Dortmund University Center for Trustworthy Data Science and Security University Alliance Ruhr Dortmund Germany Department of Computer Science University of Oxford United Kingdom

ISBN: (纸本)9783959773652

We consider the problem of learning temporal logic formulas from examples of system behavior. Learning temporal properties has crystallized as an effective means to explain complex temporal behaviors. Several efficient algorithms have been designed for learning temporal formulas. However, the theoretical understanding of the complexity of the learning decision problems remains largely unexplored. To address this, we study the complexity of the passive learning problems of three prominent temporal logics, Linear Temporal Logic (LTL), Computation Tree Logic (CTL) and Alternating-time Temporal Logic (ATL) and several of their fragments. We show that learning formulas with unbounded occurrences of binary operators is NP-complete for all of these logics. On the other hand, when investigating the complexity of learning formulas with bounded occurrences of binary operators, we exhibit discrepancies between the complexity of learning LTL, CTL and ATL formulas (with a varying number of agents). © Benjamin Bordais, Daniel Neider, and Rajarshi Roy.

关键词： Temporal logic

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：