检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Pang, Yahao Wu, Xingyuan Zhang, Xiaojin Chen, Wei Jin, Hai 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 Wuhan430074 China Huazhong University of Science and Technology Wuhan China

Significant advancements have been made by Large Language Models (LLMs) in the domains of natural language understanding and automated content creation. However, they still face persistent problems, including substantial computational costs and inadequate availability of training data. The combination of Federated Learning (FL) and LLMs (federated LLMs) offers a solution by leveraging distributed data while protecting privacy, which positions it as an ideal choice for sensitive domains. However, Federated LLMs still suffer from robustness challenges, including data heterogeneity, malicious clients, and adversarial attacks, which greatly hinder their applications. We first introduce the robustness problems in federated LLMs, to address these challenges, we propose FedEAT (Federated Embedding space Adversarial Training), a novel framework that applies adversarial training in the embedding space of client LLM and employs a robust aggregation approach, specifically geometric median aggregation, to enhance the robustness of Federated LLMs. Our experiments demonstrate that FedEAT effectively improves the robustness of Federated LLMs with minimal performance loss. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Turn Jailbreaking Large Language Models via Attention Shifting 39

Multi-Turn Jailbreaking Large Language Models via Attention ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Xiaohu Mo, Fan Wen, Ming Gu, Tu Zheng, Huadi Jin, Hai Shi, Jie School of Cyber Science and Engineering Huazhong University of Science and Technology (HUST) China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab School of Computer Science and Technology HUST China JinYinHu Laboratory China Huawei International China

ISBN: (纸本)157735897X

Large Language Models (LLMs) have achieved significant performance in various natural language processing tasks but also pose safety and ethical threats, thus requiring red teaming and alignment processes to bolster their safety. To effectively exploit these aligned LLMs, recent studies have introduced jailbreak attacks based on multi-turn dialogues. These attacks aim to prompt LLMs to generate harmful or biased content by guiding them through contextual content. However, the underlying reasons for the effectiveness of multi-turn jailbreaks remain unclear. Existing attacks often focus on optimizing queries and escalating toxicity to construct dialogues, lacking a thorough analysis of the inherent vulnerabilities of LLMs. In this paper, we first conduct an in-depth analysis of the differences between single-turn and multi-turn jailbreaks and find that successful multi-turn jailbreaks can effectively disperse the attention of LLMs on keywords associated with harmful behaviors, especially in historical responses. Based on this, we propose ASJA, a new multi-turn jailbreak approach by shifting the attention of LLMs, specifically by iteratively fabricating the dialogue history through a genetic algorithm to induce LLMs to generate harmful content. Extensive experiments on three LLMs and two datasets show that our approach surpasses existing approaches in jailbreak effectiveness, the stealth of jailbreak prompts, and attack efficiency. Our work emphasizes the importance of enhancing the robustness of LLMs’ attention mechanism in multi-turn dialogue scenarios for a better defense strategy. 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

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection

FedMoS: Taming Client Drift in Federated Learning with Doubl...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： Xiong Wang Yuxin Chen Yuqing Li Xiaofei Liao Hai Jin Bo Li 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 China School of Cyber Science and Engineering Wuhan University Wuhan China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients’ selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal ${{\mathcal{O}}}\left({{T^{ - 2/3}}}\right)$ convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Research on Fault Diagnosis Method Based on Structural Causal Model in Tennessee Eastman Process 7th

Research on Fault Diagnosis Method Based on Structural Causa...

引用

7th International Conference on Computing, Control and Industrial engineering, CCIE 2023

作者： Pu, Haoyuan Liu, Jie Chen, Zhi Yang, Xiaohua Ren, Changan Xu, Zhuoran Jian, Yifan School of Computer Science University of South China Hengyang China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China Intelligent Equipment Software Evaluation Engineering Technology Research Center of Hunan Hengyang China CNNC Key Laboratory on High Trusted Computing Hengyang China School of Nuclear Science and Technology University of South China Hengyang China

ISBN: (纸本)9789819927296

In the practical application of fault diagnosis in large-scale chemical systems, due to the danger of faults, the machine learning diagnosis methods used in current research often face the problem of scarcity of fault samples. This makes it difficult for the model to be trained effectively, thus affecting the fault detection rate of the model. Therefore, for the fault diagnosis of chemical system with small sample data, this paper proposes a diagnostic method that uses structural causal model to further combine the diagnostic results of the two machine learning methods, thereby improving global diagnostic performance. With the help of powerful system description ability of structural causal model, we can establish a causal graph for diagnostic process of the chemical system, and accurately construct the corresponding structural equations for the various diagnostic results of the two machine learning methods to combine them, thus improve the fault detection rate. The global results make up for the shortcomings of single machine learning method in small sample chemical system fault diagnosis. The verification on the chemical system simulation platform Tennessee Eastman process shows that, compared with the diagnosis results of the selected Gaussian Naive Bayes method and the K-nearest neighbour method, the results obtained by our method are effectively improved in fault detection rate of each fault in TEP. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Failure analysis

来源：评论

学校读者我要写书评

暂无评论

Ethereum smart contract security research:survey and future research opportunities

引用

Frontiers of computer science 2021年第2期15卷 143-160页

作者： Zeli WANG Hai JIN Weiqi DAI Kim-Kwang Raymond CHOO Deqing ZOU National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabHubei Engineering Research Center on Big Data SecurityWuhan430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan430074China School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan430074China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518057China Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Blockchain has recently emerged as a research trend,with potential applications in a broad range of industries and *** particular successful Blockchain technology is smart contract,which is widely used in commercial settings(e.g.,high value financial transactions).This,however,has security implications due to the potential to financially benefit from a security incident(e.g.,identification and exploitation of a vulnerability in the smart contract or its implementation).Among,Ethereum is the most active and ***,in this paper,we systematically review existing research efforts on Ethereum smart contract security,published between 2015 and ***,we focus on how smart contracts can be maliciously exploited and targeted,such as security issues of contract program model,vulnerabilities in the program and safety consideration introduced by program execution *** also identify potential research opportunities and future research agenda.

关键词： smart contract security blockchain vulnerability unreliable data

来源：评论

学校读者我要写书评

暂无评论

Tailoring Highly Confined Electric-field Based Optical Skyrmions

Tailoring Highly Confined Electric-field Based Optical Skyrm...

引用

Progress in Electromagnetic Research Symposium (PIERS)

作者： J. Chen X. Shen Y. Zeng Q. Zhan School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai China Shanghai Key Laboratory of Modern Optical System University of Shanghai for Science and Technology Shanghai China

ISBN: (数字)9798350375909

ISBN: (纸本)9798350375916

Optical skyrmions are quasi-particles with nontrivial topological textures, which hold potential applications in optical information processing, transmission, and storage. There are various three-dimensional physical vectors to construct the optical skyrmions, such as spin skyrmions, Stokes skyrmions, Poynting vector skyrmions, and so on. Here, we present a method to construct tightly focused electric-field skyrmions based on the array antenna radiation theory. A multiple concentric-ring array of dipoles (MCAD) is placed at the focal region of the high numerical aperture (NA) lens to mimic the topological structure of the desired electric field skyrmion, and the radiation pattern of the MCAD is derived to form the incident fields at the pupil planes of the high NA lenses in a 4π focusing setup. The characteristics of the generated focal field are quantitatively evaluated by using the Debye diffraction integral theory. The results demonstrate that two types of electric field vector topologies, i.e., skyrmion and meron, can be created with adjustable polarity, vorticity, and helicity. Additionally, the normal direction of the plane containing the skyrmion or meron can also be customized, increasing the degrees of freedom in tailoring optical skyrmions.

关键词： Electric potential Optical diffraction Information processing Vectors Topology Electric fields Pupils

来源：评论

学校读者我要写书评

暂无评论

Streamflow Prediction in the Mekong River Basin Using Deep Neural Networks

引用

IEEE Access 2023年 11卷 97930-97943页

作者： Nguyen, Thi-Thu-Ha Vu, Duc-Quang Mai, Son T. Dang, Thanh Duc National Taiwan University Department of Bioenvironmental Systems Engineering Taipei10617 Taiwan National Central University Department of Computer Science and Information System Taoyuan320317 Taiwan Thai Nguyen University of Education Thai Nguyen250000 Viet Nam Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom Institute for Computational Science and Artificial Intelligence Van Lang University Laboratory of Environmental Sciences and Climate Change Ho Chi Minh City70000 Viet Nam Van Lang University Faculty of Environment Ho Chi Minh City70000 Viet Nam

In recent years, the Mekong River Basin (MRB), one of the largest river basins in Southeast Asia, has experienced severe impacts from extreme droughts and floods. Streamflow forecasting has become crucial for effective risk management strategies in the region. However, this task presents significant challenges due to rapid climate changes and the presence of numerous newly constructed upstream dams, which disrupt the natural flow. In this paper, we develop multiple deep learning models (incl. Multi-Layer Perceptron (MLP), Convolutional Neural Network (CNN), Long short-term Memory (LSTM), and Transformer) to predict streamflow with different lead time forecasts based on observed meteorological variables and climatic indices (i.e., discharge, water level, precipitation, and temperature) from 1979 to 2019. The results indicate that LSTM obtains high performance for streamflow prediction in both dry and wet seasons while Transformer is not recommended for long-term prediction, especially in the dry season. The proposed deep learning models capture well the fluctuation of river flow in the MRB during the period of high-dam development, especially LSTM (NSE ≥ 0.8). The models' performances are enhanced with the adding of temperature for short-term prediction while precipitation was the most sensitive variable for long-term one. Such proposed models are essential for government agencies to plan mitigation and adaptation strategies at different periods, which can range from days to years. © 2013 IEEE.

关键词： Floods

来源：评论

学校读者我要写书评

暂无评论

HeadSonic: Usable Bone Conduction Earphone Authentication via Head-conducted Sounds

引用

IEEE Transactions on Mobile Computing 2025年

作者： He, Zhixiang Chen, Jing He, Kun Gu, Yangyang Deng, Qiyi Zhang, Zijian Du, Ruiying Zhao, Qingchuan Wu, Cong Wuhan University School of Cyber Science and Engineering Wuhan430072 China State Key Lab of Intelligent Transportation System Beijing China Beijing Institute of Technology School of Cyberspace Science and Technology China City University of Hong Kong Department of Computer Science Hong Kong The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong

Earables (ear wearables) are rapidly emerging as a new platform encompassing a diverse of personal applications, prompting the development of authentication schemes to protect user privacy. Existing earable authentication methods are all specifically designed for air-conduction earphones, which are not suited for bone conduction earphones (BCEs) that rely on bone conduction mechanisms. In this paper, we propose HeadSonic, a usable BCE authentication system based on the unique head-conducted sounds, which can be acquired when the user wears the BCE device. Specifically, the system emits a millisecond-level sound to initiate the authentication session. The signal captured by the BCE microphone is propagated through the user’s head, which is unique in density, geometry, and bone-tissue ratio. It operates implicitly, while maintaining robustness across different behaviors. Extensive experiments involving 60 subjects demonstrate that HeadSonic achieves a commendable balanced accuracy of 96.59%, proving its efficacy and resilience against replay and synthesis attacks. Our dataset and source codes are available at https://***/r/HeadSonic1CE4. © 2025 IEEE. All rights reserved.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Trust Evaluation-based Machine Learning for WSNs

Trust Evaluation-based Machine Learning for WSNs

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Aditya Kumar Karan Singh Satvik Vats School of Computer and System Sciences Jawaharlal Nehru University New Delhi India Computer Science and Engineering Graphic Era Hill University Dehradun India

Wireless sensor networks (WSNs) have many different applications in industries such as intrusion detection, healthcare, and environmental monitoring. To ensure their success, it is essential to establish trust among the sensor nodes to enhance trustworthiness, collaboration, and security. However, current trust management methods for large-scale WSNs have several drawbacks, including low dependability, high communication, and memory overhead, which make them ineffective. To address these issues, a new approach has been proposed, which uses trust evaluation-based machine learning for WSNs. This method involves determining trust attributes using a model and then creating a new algorithm based on machine learning to categorize and combine these trust features into a final trust value. This trust value can be used in decision-making to improve the effectiveness of WSNs.

关键词： Wireless sensor networks Analytical models Machine learning algorithms Computational modeling Support vector machine classification Machine learning Predictive models

来源：评论

学校读者我要写书评

暂无评论

Design of Concurrent engineering systems for Global Product Development Using Artificial Intelligence 10th

Design of Concurrent Engineering Systems for Global Product ...

引用

10th International Conference on Innovations in computer science and engineering, ICICSE 2022

作者： Karn, Arodh Lal Mehbodniya, Abolfazl Webber, Julian L. Jayagopal, Vellingiri Stalin David, D. Rangasamy, Rajasekar Sengan, Sudhakar Department of Financial and Actuarial Mathematics School of Mathematics and Physics Xi’an Jiaotong-Liverpool University Jiangsu Suzhou215123 China Kuwait City Kuwait Department of Software and System Engineering School of Information Technology and Engineering Vellore Institute of Technology Tamil Nadu Vellore632014 India Department of Information Technology Vel Tech Multi Tech Dr. Rangarajan Dr. Sakunthala Engineering College Tamil Nadu Chennai600072 India Department of Computer Science and Engineering GITAM School of Technology GITAM University Karnataka Bengaluru561203 India Department of Computer Science and Engineering PSN College of Engineering and Technology Tamil Nadu Tirunelveli627152 India

ISBN: (纸本)9789811974540

Competition and concurrent engineering (CE) businesses are growing. Faster product creation, quality improvement, manufacturing process adoption, and reduced client demand cost are vital for corporate success. Implement concurrent engineering to make high-quality goods. CE is a parallel, systematic method to design. The chief executive officer (CEO’s) approach impacted how many firms build products. You may use the fundamental ideas of concurrent engineering conversation and the failure mode and effects analysis (FMEA) tool. To provide a smooth and efficient CE environment, conduct the product development process from market research to detailed design. Concurrent engineering is a novel product development (NPD) approach. Concurrency and cross-functional integration separate CE from traditional product development. NPD continues through developing ideas, validation, proof-of-concept validation, Minimum Viable Product development, pre-launch, and post-launch. In other words, product discovery should continue throughout its life span. Each organization's growth operations operate simultaneously. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Product development

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：