检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Liang, Ruichao Chen, Jing Wu, Cong He, Kun Wu, Yueming Cao, Ruochen Du, Ruiying Liu, Yang Zhao, Ziming Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan430072 China Cyber Security Lab College of Computing and Data Science Nanyang Technological University Singapore Department of Computer Science and Engineering University at Buffalo New York United States

Smart contracts, the cornerstone of decentralized applications, have become increasingly prominent in revolutionizing the digital landscape. However, vulnerabilities in smart contracts pose great risks to user assets and undermine overall trust in decentralized systems. Fuzzing, a prominent security testing technique, is extensively explored to detect vulnerabilities. But current smart contract fuzzers fall short of expectations in testing efficiency for two primary reasons. Firstly, smart contracts are stateful programs, and existing approaches, primarily coverage-guided, lack effective feedback from the contract state. Consequently, they struggle to effectively explore the contract state space. Secondly, coverage-guided fuzzers, aiming for comprehensive program coverage, may lead to a wastage of testing resources on benign code areas. This wastage worsens in smart contract testing, as the mix of code and state spaces further complicates comprehensive testing. To address these challenges, we propose VULSEYE, a stateful directed graybox fuzzer for smart contracts guided by vulnerabilities. Different from prior works, VULSEYE achieves stateful directed fuzzing by prioritizing testing resources to code areas and contract states that are more prone to vulnerabilities. We introduce Code Targets and State Targets into fuzzing loops as the testing targets of VULSEYE. We use static analysis and pattern matching to pinpoint Code Targets, and propose a scalable backward analysis algorithm to specify State Targets. We design a novel fitness metric that leverages feedback from both the contract code space and state space, directing fuzzing toward these targets. With the guidance of code and state targets, VULSEYE alleviates the wastage of testing resources on benign code areas and achieves effective stateful fuzzing. In comparison with state-of-the-art fuzzers, VULSEYE demonstrated superior effectiveness and efficiency. Notably, it uncovered 4,845 vulnerabilities in 42,738 rea

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning

arXiv

引用

arXiv 2024年

作者： Bu, Dake Huang, Wei Han, Andi Nitanda, Atsushi Suzuki, Taiji Zhang, Qingfu Wong, Hau-San Department of Computer Science City University of Hong Kong Hong Kong Center for Advanced Intelligence Project RIKEN Japan Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Mathematical Informatics The University of Tokyo Japan

Transformer-based large language models (LLMs) have displayed remarkable creative prowess and emergence capabilities. Existing empirical studies have revealed a strong connection between these LLMs' impressive emergence abilities and their in-context learning (ICL) capacity, allowing them to solve new tasks using only task-specific prompts without further fine-tuning. On the other hand, existing empirical and theoretical studies also show that there is a linear regularity of the multi-concept encoded semantic representation behind transformer-based LLMs. However, existing theoretical work fail to build up an understanding of the connection between this regularity and the innovative power of ICL. Additionally, prior work often focuses on simplified, unrealistic scenarios involving linear transformers or unrealistic loss functions, and they achieve only linear or sub-linear convergence rates. In contrast, this work provides a fine-grained mathematical analysis to show how transformers leverage the multi-concept semantics of words to enable powerful ICL and excellent out-of-distribution ICL abilities, offering insights into how transformers innovate solutions for certain unseen tasks encoded with multiple cross-concept semantics. Inspired by empirical studies on the linear latent geometry of LLMs, the analysis is based on a concept-based low-noise sparse coding prompt model. Leveraging advanced techniques, this work showcases the exponential 0-1 loss convergence over the highly non-convex training dynamics, which pioneeringly incorporates the challenges of softmax self-attention, ReLU-activated MLPs, and cross-entropy loss. Empirical simulations corroborate the theoretical findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Revolutionizing Influenza A Detection in Humans: Unleashing the Power of XGBoost Classification

Revolutionizing Influenza A Detection in Humans: Unleashing ...

引用

Women in Innovation, Technology & Entrepreneurship (ICWITE), IEEE International Conference for

作者： V Nikhil S A Sahaaya Arul Mary B Natarajan A. Bajulunisha R.S. Anuradha K Venkatraman Department of Computer Science and Engineering (AIE) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Computer Science Engineering VIT University Chennai India Department of Artificial Intelligence & Data Science M.A.M College of Engineering and Technology Tiruchirappalli India Department of Artificial Intelligence & Data Science Panimalar Engineering College Chennai India

Influenza A, a zoonotic virus potentially affecting and infecting humans, poses a significant global health threat. This research paper presents a comprehensive study on predicting Influenza A outbreaks by applying the XGBoost classification algorithm. The study utilizes two substantial datasets: one from the World Health Organization (WHO) containing global Influenza A epidemiological data from 2003 to 2023 and the other encompassing Influenza A infections in New York counties from 2009 to 2019. Both datasets underwent pre-processing, with essential features selected to develop an XGBoost Classification model for forecasting Influenza A cases in humans. The models exhibited impressive accuracy and performance metrics. Specifically, the WHO dataset demonstrated an AUC of 0.996 and an accuracy score of 0.99, while the New York dataset displayed an AUC of 0.992 and an accuracy score of 0.978. These outcomes underscore the model’s capability to differentiate between positive and negative cases, showcasing high precision, accuracy, and F1 scores. The implications of this research extend to various domains, including the early detection of outbreaks, informed decision-making processes, and the implementation of public health interventions. The findings emphasize the pivotal role of high-quality and comprehensive datasets in training effective predictive models. Furthermore, the study points towards potential future avenues, such as personalized predictions, geo-spatial analysis, and integrating these predictive models with healthcare systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resilient Collaborative Caching for Multi-Edge Systems with Robust Federated Deep Learning

引用

IEEE/ACM Transactions on Networking 2024年

作者： Chen, Zheyi Liang, Jie Yu, Zhengxin Cheng, Hongju Min, Geyong Li, Jie Fuzhou University College of Computer and Data Science Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou350116 China Ministry of Education Engineering Research Center of Big Data Intelligence Fuzhou350002 China Lancaster University School of Computing and Communications LancasterLA1 4YW United Kingdom University of Exeter Faculty of Environment Science and Economy Department of Computer Science ExeterEX4 4QF United Kingdom Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai200240 China

As a key technique for future networks, the performance of emerging multi-edge caching is often limited by inefficient collaboration among edge nodes and improper resource configuration. Meanwhile, achieving optimal cache hit rates poses substantive challenges without effectively capturing the potential relations between discrete user features and diverse content libraries. These challenges become further sophisticated when caching schemes are exposed to adversarial attacks that seriously impair cache performance. To address these challenges, we introduce RoCoCache, a resilient collaborative caching framework that uniquely integrates robust federated deep learning with proactive caching strategies, enhancing performance under adversarial conditions. First, we design a novel partitioning mechanism for multi-dimensional cache space, enabling precise content recommendations in user classification intervals. Next, we develop a new Discrete-Categorical Variational Auto-Encoder (DC-VAE) to accurately predict content popularity by overcoming posterior collapse. Finally, we create an original training mode and proactive cache replacement strategy based on robust federated deep learning. Notably, the residual-based detection for adversarial model updates and similarity-based federated aggregation are integrated to avoid the model destruction caused by adversarial updates, which enables the proactive cache replacement adapting to optimized cache resources and thus enhances cache performance. Using the real-world testbed and datasets, extensive experiments verify that the RoCoCache achieves higher cache hit rates and efficiency than state-of-the-art methods while ensuring better robustness. Moreover, we validate the effectiveness of the components designed in RoCoCache for improving cache performance via ablation studies. © 1993-2012 IEEE.

关键词： cache space partitioning content popularity prediction Multi-edge collaborative caching proactive cache replacement robust federated deep learning

来源：评论

学校读者我要写书评

暂无评论

Zero-shot ECG classification with multimodal learning and test-time clinical knowledge enhancement 24

Zero-shot ECG classification with multimodal learning and te...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Che Liu Zhongwei Wan Cheng Ouyang Anand Shah Wenjia Bai Rossella Arcucci Data Science Institute and Department of Earth Science and Engineering Imperial College London UK Ohio State University Columbus Department of Engineering Science University of Oxford Oxford UK and Institute of Clinical Sciences Imperial College London UK Department of Infectious Disease Epidemiology Imperial College London UK and Royal Brompton and Harefield Hospitals UK Data Science Institute and Department of Computing and Department of Brain Sciences Imperial College London UK

Electrocardiograms (ECGs) are non-invasive diagnostic tools crucial for detecting cardiac arrhythmic diseases in clinical practice. While ECG Self-supervised Learning (eSSL) methods show promise in representation learning from unannotated ECG data, they often overlook the clinical knowledge that can be found in reports. This oversight and the requirement for annotated samples for downstream tasks limit eSSL's versatility. In this work, we address these issues with the Multimodal ECG Representation Learning (MERL) framework. Through multimodal learning on ECG records and associated reports, MERL is capable of performing zero-shot ECG classification with text prompts, eliminating the need for training data in downstream tasks. At test time, we propose the Clinical Knowledge Enhanced Prompt Engineering (CKEPE) approach, which uses Large Language Models (LLMs) to exploit external expert-verified clinical knowledge databases, generating more descriptive prompts and reducing hallucinations in LLM-generated content to boost zero-shot classification. Based on MERL, we perform the first benchmark across six public ECG datasets, showing the superior performance of MERL compared against eSSL methods. Notably, MERL achieves an average AUC score of 75.2% in zero-shot classification (without training data), 3.2% higher than linear probed eSSL methods with 10% annotated training data, averaged across all six datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)

arXiv

引用

arXiv 2024年

作者： Hu, Jerry Yao-Chieh Wu, Weimin Song, Zhao Liu, Han Center for Foundation Models Generative AI Department of Computer Science Department of Statistics and Data Science Northwestern University EvanstonIL60208 United States Simons Institute for the Theory of Computing UC Berkeley BerkeleyCA94720 United States

We investigate the statistical and computational limits of latent Diffusion Transformers (DiTs) under the low-dimensional linear latent space assumption. Statistically, we study the universal approximation and sample complexity of the DiTs score function, as well as the distribution recovery property of the initial data. Specifically, under mild data assumptions, we derive an approximation error bound for the score network of latent DiTs, which is sub-linear in the latent space dimension. Additionally, we derive the corresponding sample complexity bound and show that the data distribution generated from the estimated score function converges toward a proximate area of the original one. Computationally, we characterize the hardness of both forward inference and backward computation of latent DiTs, assuming the Strong Exponential Time Hypothesis (SETH). For forward inference, we identify efficient criteria for all possible latent DiTs inference algorithms and showcase our theory by pushing the efficiency toward almost-linear time inference. For backward computation, we leverage the low-rank structure within the gradient computation of DiTs training for possible algorithmic speedup. Specifically, we show that such speedup achieves almost-linear time latent DiTs training by casting the DiTs gradient as a series of chained low-rank approximations with bounded error. Under the low-dimensional assumption, we show that the statistical rates and the computational efficiency are all dominated by the dimension of the subspace, suggesting that latent DiTs have the potential to bypass the challenges associated with the high dimensionality of initial data. © 2024, CC BY-NC-SA.

关键词： Distribution transformers

来源：评论

学校读者我要写书评

暂无评论

FedMUA: Exploring the Vulnerabilities of Federated Learning to Malicious Unlearning Attacks

arXiv

引用

arXiv 2025年

作者： Chen, Jian Lin, Zehui Lin, Wanyu Shi, Wenlong Yin, Xiaoyan Wang, Di Department of Data Science and Artificial Intelligence The Hong Kong Polytechnic University Hong Kong Department of Data Science and Artificial Intelligence The Department of Computing The Hong Kong Polytechnic University Hong Kong School of Electronic Information and Communications Huazhong University of Science and Technology Wuhan430074 China School of Information Science and Technology Northwest University Xi’an China Division of Computer Electrical and Mathematical Sciences and Engineering King Abdullah University of Science and Technology Saudi Arabia

Recently, the practical needs of "the right to be forgotten" in federated learning gave birth to a paradigm known as federated unlearning, which enables the server to forget personal data upon the client’s removal request. Existing studies on federated unlearning have primarily focused on efficiently eliminating the influence of requested data from the client’s model without retraining from scratch, however, they have rarely doubted the reliability of the global model posed by the discrepancy between its prediction performance before and after unlearning. To bridge this gap, we take the first step by introducing a novel malicious unlearning attack dubbed FedMUA, aiming to unveil potential vulnerabilities emerging from federated learning during the unlearning process. Specifically, clients may act as attackers by crafting malicious unlearning requests to manipulate the prediction behavior of the global model. The crux of FedMUA is to mislead the global model into unlearning more information associated with the influential samples for the target sample than anticipated, thus inducing adverse effects on target samples from other clients. To achieve this, we design a novel two-step method, known as Influential Sample Identification and Malicious Unlearning Generation, to identify and subsequently generate malicious feature unlearning requests within the influential samples. By doing so, we can significantly alter the predictions pertaining to the target sample by initiating the malicious feature unlearning requests, leading to the deliberate manipulation for the user adversely. Additionally, we design a new defense mechanism that is highly resilient against malicious unlearning attacks. Extensive experiments on three realistic datasets reveal that FedMUA effectively induces misclassification on target samples and can achieve an 80% attack success rate by triggering only 0.3% malicious unlearning requests. Copyright © 2025, The Authors. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Adaptive Contextual Caching for Mobile Edge Large Language Model Service

arXiv

引用

arXiv 2025年

作者： Liu, Guangyuan Liu, Yinqiu Wang, Jiacheng Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui College of Computing and Data Science The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore College of Computing and Data Science Nanyang Technological University Singapore Department of Electrical and Electronic Engineering University of Hong Kong Hong Kong School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore

Mobile edge Large Language Model (LLM) deployments face inherent constraints, such as limited computational resources and network bandwidth. Although Retrieval-Augmented Generation (RAG) mitigates some challenges by integrating external knowledge bases, inefficient cache management can still result in high retrieval latency and frequent cache updates. To address these issues, we propose an Adaptive Contextual Caching (ACC) framework that anticipates user needs by proactively caching semantically relevant data for mobile-edge LLMs. ACC utilizes a deep reinforcement learning (DRL) module to refine cache replacement policies, balancing user context, document similarity, and the overhead associated with cache misses. Experimental results demonstrate that ACC increases cache hit rates to over 80% after only 11 training episodes, outperforming FIFO, LRU, and semantic-only caching while reducing retrieval latency by up to 40%. In particular, ACC also reduces local caching overhead (i.e., the cost of updating the cache when a miss occurs) by as much as 55%, enabling scalable, low-latency LLM services in resource-constrained edge environments. © 2025, CC BY.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Cloud computing-Enhanced and Raspberry Pi-powered Solution for Remote Ear, Nose, and Throat Consultations with AI-Driven Diagnostics 5

Cloud Computing-Enhanced and Raspberry Pi-powered Solution f...

引用

5th IEEE International Conference for Emerging Technology, INCET 2024

作者： Giriprasad, S. Karpagam, T. Nalini, V. Mishra, Nilamadhab Mohankumar, N. Malathi, N. Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Tamil Nadu Chennai India Department of Mathematics Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Tamil Nadu Chennai India School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh India Department of Electronics and Communication Engineering B.V. Raju Institute of Technology Telangana India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350361155

The cutting-edge telemedicine program presents a game-changing alternative for patients seeking ENT (ear, nose, and throat) consultations from a distant location. Utilizing the capabilities of Raspberry Pi devices, powerful artificial intelligence, and cloud computing, the system allows otoscopic tests to be performed without interruption while securely transmitting data to the cloud. On a web-based platform, interactive patient-professional consultations are made possible via real-time communication, which is made possible by WebRTC. Cloud services are very important because of their ability to provide scalable storage as well as AI-driven diagnostics for accurate evaluations. The system complies with the requirements for healthcare compliance, emphasizes security and privacy, and features encryption from beginning to finish. This integrated approach promises scalability, reliability, and advanced diagnostic capabilities, and it reshapes the landscape of remote ENT care with accessible and technologically advanced healthcare solutions. With a user-friendly interface for patients and a cloud-hosted application for healthcare professionals, this integrated approach provides patients with advanced healthcare solutions. © 2024 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Advancing IC Fault Localization and Diagnosis Through Machine Learning

Advancing IC Fault Localization and Diagnosis Through Machin...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Rajasekar, P. Kumar, Alok Prema Latha, V. Jayapal, N. Santhoshi, Boddu Soundarya Karthik, K. Sivaramkumar, Mathiyalagan School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamil Nadu Kattankulathur603203 India Guru Gobind Singh Educational Society Department of Electrical and Electronics Engineering Technical Campus Jharkhand Bokaro827013 India Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering Andhra Pradesh Vaddeswaram522302 India Kongunadu College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Trichy621215 India S.R.K.R Engineering College Department of Mechanical Engineering Andhra Pradesh Bhimavaram534204 India Velammal College of Engineering and Technology Department of Electronics and Communication Engineering Tamil Nadu Madurai625009 India Saveetha University Department of Biosciences Chennai602105 India

ISBN: (纸本)9798331509828

Fault localization and diagnosis of Integrated Circuits (ICs) are essential for maintaining dependability in contemporary electronic systems. This research presents a sophisticated system utilizing data Augmentation, Wrapper-based feature selection, and deep learning to improve the precision of defect identification and localization. data Augmentation methods, such as synthetic fault data generation via SMOTE, rectify dataset imbalances, facilitating the model's generalization across various fault scenarios. Wrapper-based feature selection utilizes Recursive Feature Elimination (RFE) to discern the most significant characteristics, including timing delays, voltage levels, and signal patterns, so diminishing dimensionality while preserving essential information. The framework is centred around a deep learning model that integrates Convolutional Neural Networks (CNNs) for spatial fault detection and Long Short-Term Memory (LSTM) networks for temporal analysis. Experimental findings indicate a notable enhancement in fault localization precision, less false positives, and improved model interpretability. This method offers a scalable and resilient alternative for integrated circuit defect diagnosis, tackling the increasing complexity of contemporary electronic systems. © 2025 IEEE.

关键词： Convolutional neural networks

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：