检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： He, Jialuo Chen, Wei Zhang, Xiaojin National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China School of Microelectronics and Communication Engineering Chongqing University Chongqing 400044 China School of Software Engineering Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)157735897X

Federated Learning (FL) has emerged as a promising approach for privacy-preserving model training across decentralized devices. However, it faces challenges such as statistical heterogeneity and susceptibility to adversarial attacks, which can impact model robustness and fairness. Personalized FL attempts to provide some relief by customizing models for individual clients. However, it falls short in addressing server-side aggregation vulnerabilities. We introduce a novel method called FedAA, which optimizes client contributions via Adaptive Aggregation to enhance model robustness against malicious clients and ensure fairness across participants in non-identically distributed settings. To achieve this goal, we propose an approach involving a Deep Deterministic Policy Gradient-based algorithm for continuous control of aggregation weights, an innovative client selection method based on model parameter distances, and a reward mechanism guided by validation set performance. Empirically, extensive experiments demonstrate that, in terms of robustness, FedAA outperforms the state-of-the-art methods, while maintaining comparable levels of fairness, offering a promising solution to build resilient and fair federated systems. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

BRAINGUARD: Privacy-Preserving Multisubject Image Reconstructions from Brain Activities 39

BRAINGUARD: Privacy-Preserving Multisubject Image Reconstruc...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Tian, Zhibo Quan, Ruijie Ma, Fan Zhan, Kun Yang, Yi School of Information Science and Engineering Lanzhou University China College of Computing and Data Science Nanyang Technological University Singapore College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)157735897X

Reconstructing perceived images from human brain activity forms a crucial link between human and machine learning through Brain-Computer Interfaces. Early methods primarily focused on training separate models for each individual to account for individual variability in brain activity, overlooking valuable cross-subject commonalities. Recent advancements have explored multisubject methods, but these approaches face significant challenges, particularly in data privacy and effectively managing individual variability. To overcome these challenges, we introduce BRAINGUARD, a privacy-preserving collaborative training framework designed to enhance image reconstruction from multisubject fMRI data while safeguarding individual privacy. BRAINGUARD employs a collaborative global-local architecture where individual models are trained on each subject’s local data and operate in conjunction with a shared global model that captures and leverages cross-subject patterns. This architecture eliminates the need to aggregate fMRI data across subjects, thereby ensuring privacy preservation. To tackle the complexity of fMRI data, BRAINGUARD integrates a hybrid synchronization strategy, enabling individual models to dynamically incorporate parameters from the global model. By establishing a secure and collaborative training environment, BRAINGUARD not only protects sensitive brain data but also improves the image reconstructions accuracy. Extensive experiments demonstrate that BRAINGUARD sets a new benchmark in both high-level and low-level metrics, advancing the state-of-the-art in brain decoding through its innovative design. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Active learning

来源：评论

学校读者我要写书评

暂无评论

An agent-based model of citation behavior

arXiv

引用

arXiv 2025年

作者： Chacko, George Park, Minhyuk Ramavarapu, Vikram Grama, Ananth Robles Granda, Pablo Warnow, Tandy Siebel School of Computing and Data Science Grainger College of Engineering University of Illinois Urbana-ChampaignIL United States Department of Computer Science Purdue University United States

Whether citations can be objectively and reliably used to measure productivity and scientific quality of articles and researchers can, and should, be vigorously questioned. However, citations are widely used to estimate the productivity of researchers and institutions, effectively creating a ‘grubby’ motivation to be well-cited. We model citation growth, and this grubby interest using an agent-based model (ABM) of network growth. In this model, each new node (article) in a citation network is an autonomous agent that cites other nodes based on a ‘citation personality’ consisting of a composite bias for locality, preferential attachment, recency, and fitness. We ask whether strategic citation behavior (reference selection) by the author of a scientific article can boost subsequent citations to it. Our study suggests that fitness and, to a lesser extent, out degree and locality effects are influential in capturing citations, which raises questions about similar effects in the real world. © 2025, CC BY.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence based Facial Emotion Recognition with Deep Neural GAN Augmentation 8

Artificial Intelligence based Facial Emotion Recognition wit...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Menaka, D. Priya, D. Karthika Lenus, C. Reeda Ashwini, A. Shermila, P. Josephin Prathaban, Banu Priya Noorul Islam Centre for Higher Education Department of Electronics and Instrumentation Engineering Kumaracoil India Easwari Engineering College Department of Artificial Intelligence and Data Science Ramapuram Chennai India S.A.Engineering College Department of Physics Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Ece Chennai India R.M.K.College of Engineering and Technology Department of Artificial Intelligence and Data Science Chennai India Srm Institute of Science and Technology Kattankulathur School of Computing Department of Networking and Communication Chennai India

ISBN: (纸本)9798350367904

Facial recognition system in computer vision is widely used in human-computer interface and clinical diagnostics. Nonetheless, achieving high accuracy in this task still poses a challenge due to issues of inadequate amount and imbalance of data to train the models as well as issues of generalization and robustness. The findings of this research propose the use of Generative Adversarial Network (GAN) data augmentation for face emotion classification specifically for this approach. The proposed strategy is based on the generation of artificial 'emotional' images on the face using Deep Neural Self Attention GANs (DNSAGANs). This way, to capture all the variations of facial expressions the GAN takes a large number of images and thus makes the augmented data richer and more realistic. This larger data set is then used to train a deep learning architecture that performs the face emotion classification thereby enabling the network to learn enhanced discriminative features. To collect face photos the FER2013 dataset is used. The training process, entrained the generator and discriminator to minimize the mean squared error while the discriminator was simultaneously trained to robustly distinguish generated images from real ones. Altogether, the proposed Adam optimizer was more accurate than Adagrad and Adadelta for all epochs. The percentage of accuracy is about 88.64 % for 100 epochs using the proposed optimizer techniques. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Safe exploitative play with untrusted type beliefs 24

Safe exploitative play with untrusted type beliefs

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Tongxin Li Tinashe Handina Shaolei Ren Adam Wierman School of Data Science The Chinese University of Hong Kong Shenzhen China Computing + Mathematical Sciences California Institute of Technology Pasadena Electrical & Computer Engineering University of California Riverside

ISBN: (纸本)9798331314385

The combination of the Bayesian game and learning has a rich history, with the idea of controlling a single agent in a system composed of multiple agents with unknown behaviors given a set of types, each specifying a possible behavior for the other agents. The idea is to plan an agent's own actions with respect to those types which it believes are most likely to maximize the payoff. However, the type beliefs are often learned from past actions and likely to be incorrect. With this perspective in mind, we consider an agent in a game with type predictions of other components, and investigate the impact of incorrect beliefs to the agent's payoff. In particular, we formally define a tradeoff between risk and opportunity by comparing the payoff obtained against the optimal payoff, which is represented by a gap caused by trusting or distrusting the learned beliefs. Our main results characterize the tradeoff by establishing upper and lower bounds on the Pareto front for both normal-form and stochastic Bayesian games, with numerical results provided.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

arXiv

引用

arXiv 2024年

作者： Wang, Yichen Chou, Yuxuan Zhou, Ziqi Zhang, Hangtao Wan, Wei Hu, Shengshan Li, Minghui National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China School of School of Software Engineering Huazhong University of Science and Technology China

As deep neural networks (DNNs) are widely applied in the physical world, many researches are focusing on physical-world adversarial examples (PAEs), which introduce perturbations to inputs and cause the model’s incorrect outputs. However, existing PAEs face two challenges: unsatisfactory attack performance (i.e., poor transferability and insufficient robustness to environment conditions), and difficulty in balancing attack effectiveness with stealthiness, where better attack effectiveness often makes PAEs more perceptible. In this paper, we explore a novel perturbation-based method to overcome the challenges. For the first challenge, we introduce a strategy Deceptive RF injection based on robust features (RFs) that are predictive, robust to perturbations, and consistent across different models. Specifically, it improves the transferability and robustness of PAEs by covering RFs of other classes onto the predictive features in clean images. For the second challenge, we introduce another strategy Adversarial Semantic Pattern Minimization, which removes most perturbations and retains only essential adversarial patterns in AEs. Based on the two strategies, we design our method Robust Feature Coverage Attack (RFCoA), comprising Robust Feature Disentanglement and Adversarial Feature Fusion. In the first stage, we extract target class RFs in feature space. In the second stage, we use attention-based feature fusion to overlay these RFs onto predictive features of clean images and remove unnecessary perturbations. Experiments show our method’s superior transferability, robustness, and stealthiness compared to existing state-of-the-art methods. Additionally, our method’s effectiveness can extend to Large Vision-Language Models (LVLMs), indicating its potential applicability to more complex tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

eDEM-CONNECT: An Ontology-Based Chatbot for Family Caregivers of People with Dementia 12th

eDEM-CONNECT: An Ontology-Based Chatbot for Family Caregive...

引用

12th International Conference on Mobile Communication and Healthcare, MobiHealth 2023

作者： Boiting, Maurice Tschorn, Niklas Suravee, Sumaiya Yordanova, Kristina Halek, Margareta Jagoda, Franziska A. Lüdtke, Stefan Burmann, Anja Fraunhofer Institute for Software and Systems Engineering ISST Dortmund44147 Germany Institute for Data Science Universität Greifswald Greifswald17489 Germany School of Nursing Science Faculty of Health Universiät Witten/Herdecke Witten58453 Germany Institute for Visual and Analytic Computing Universät Rostock Rostock18059 Germany

ISBN: (纸本)9783031606649

Home care of people with dementia (PwD) is mainly organized and carried out by non-professional family caregivers, who struggle to interpret the needs of PwD correctly and are confronted with the challenging behavior of their relatives. Although support services for family caregivers are widespread in Germany, they are rarely used due to the fact that information is poorly organized and relatives are faced with a flood of disorganized, outdated, and confusing content. Due to the technical development of chatbot technologies (ChatGPT), chatbots gain more and more relevance. Based on the new technological possibilities, we developed an online communication and service platform with an integrated chatbot within the eDEM-CONNECT project, with the aim of making structured and easily understandable information accessible for family caregivers. This work focuses on the development of a chatbot pipeline that has broad domain knowledge through a provided ontology on the topic of agitation of PwD. This allows the chatbot to provide relevant and peer-reviewed information to family members. In our approach, a patient history is first taken based on several diagnostic questions so that relevant information can be output in a later step. For this purpose, we demonstrate that agitations in natural language can be correctly recognized by the used BERT model and that our developed chatbot is able to select further diagnostic questions based on the predictions of a Markov logic network. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2024.

关键词： Neurodegenerative diseases

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of AI Powered Vehicle Toll Collection System Based on RFID and Internet of Things (IoT) Assistance

Experimental Evaluation of AI Powered Vehicle Toll Collectio...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Pulikanti, Jyothi Jayaraj, R. Purushotham, S. Devi, V. Saranya Antony, A.Santhi Mary Chitra, M.P. Qis College of Engineering and Technology Department of Aimlds Andhra Pradesh Ongole India School of Computing Srm Institute of Science and Technology Department of Data Science and Buisness Systems Kattankulathur Chennai India Sona College of Technology Department of Eee Salem India Qis College of Engineering and Technology Department of Ece AndhraPradesh Ongole India Loyola-ICAM College of Engineering and Technology Department of Eee Nungambakkam Loyola Campus Chennai India Panimalar Engineering College Department of Electronics and Communication Engineering Chennai India

ISBN: (纸本)9798331543617

This paper presents the experimental evaluation of an AI-powered vehicle toll collection system, utilizing RFID technology and IoT integration. The system was designed to automate toll collection, reducing transaction time and improving accuracy while minimizing human intervention. The methodology involved RFID-based vehicle identification, real-time data transfer via IoT, and automatic toll deductions from prepaid accounts. The system was evaluated based on transaction speed, accuracy, user satisfaction, and system reliability. Results show that the automated system significantly reduced average transaction times from 32.5 seconds (manual) to 10 seconds (automated) during peak hours. Additionally, the system demonstrated a 100% accuracy rate in detecting unregistered vehicles and low-balance scenarios. User satisfaction was high, with an average rating of 4.6 out of 5. System reliability was also excellent, achieving an average uptime of 99.5% across multiple toll booth locations. The AI-powered toll collection system proved to be highly efficient in automating toll processes, reducing congestion, and improving the user experience. These findings suggest that such systems can effectively modernize toll management, contributing to time savings, reduced operational costs, and enhanced security. © 2024 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

A data Serialization-based Framework for Efficient IoT Management

A Data Serialization-based Framework for Efficient IoT Manag...

引用

IEEE World Forum on Internet of Things (WF-IoT)

作者： Khayal Huseynov Lal Verda Cakir Sarah Al-Shareeda Mehmet Özdem Berk Canberk BTS Group Turkey School of Computing Engineering and The Built Environment Edinburgh Napier University UK Department of AI and Data Engineering Istanbul Technical University Turkey Türk Telekom Turkey

ISBN: (数字)9798350373011

ISBN: (纸本)9798350373028

The Internet of Things (IoT) management relies on the efficient and timely transfer of data from sensors to applications. Processing required data transformations at the edge gateway introduces spatial complexity issues, particularly concerning resource constraints and latency requirements. By adopting a zero-copy binary format, Flatbuffers, we reduce the spatial complexity of processing at IoT edge gateway. However, at the service applications, interoperability challenges may arise when dealing with binary data formats compared to text-based formats. To accommodate the constraints of IoT edge gateways and service applications, we introduce a framework that aims to improve the data exchange rate between the IoT layer and the management layer while maintaining interoperability. Our comparative analysis across three scenarios, involving single and multiple sensors, shows that the proposed FlatBuffers-based framework outperforms the conventional JSON and Protocol Buffers formats in terms of frequency. These findings highlight the significant potential of FlatBuffers in boosting the real-time interaction capabilities of IoT systems.

关键词： Exchange rates Protocols Logic gates Boosting Real-time systems Sensors Complexity theory Internet of Things Interoperability

来源：评论

学校读者我要写书评

暂无评论

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motion 39

Autonomous LLM-Enhanced Adversarial Attack for Text-to-Motio...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Miao, Honglei Ma, Fan Quan, Ruijie Zhan, Kun Yang, Yi School of Information Science and Engineering Lanzhou University China College of Computer Science and Technology Zhejiang University China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Human motion generative models have enabled promising applications, but the ability of text-to-motion (T2M) models to produce realistic motions raises security concerns if exploited maliciously. Despite growing interest in T2M, limited research focus on safeguarding these models against adversarial attacks, with existing work on text-to-image models proving insufficient for the unique motion domain. In the paper, we propose ALERT-Motion, an autonomous framework that leverages large language models (LLMs) to generate targeted adversarial attacks against black-box T2M models. Unlike prior methods that modify prompts through predefined rules, ALERT-Motion uses the knowledge of LLMs of human motion to autonomously generate subtle yet powerful adversarial text descriptions. It comprises two key modules: an adaptive dispatching module that constructs an LLM-based agent to iteratively refine and search for adversarial prompts;and a multimodal information contrastive module that extracts semantically relevant motion information to guide the agent’s search. Through this LLM-driven approach, ALERT-Motion produces adversarial prompts querying victim models to produce outputs closely matching targeted motions, while avoiding obvious perturbations. Evaluations across popular T2M models demonstrate ALERT-Motion’s superiority over previous methods, achieving higher attack success rates with stealthier adversarial prompts. This pioneering work on T2M adversarial attacks highlights the urgency of developing defensive measures as motion generation technology advances, urging further research into safe and responsible deployment. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

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：