检索结果-内蒙古大学图书馆

Denial-of-Service or Fine-Grained Control: Towards Flexible Model Poisoning Attacks on Federated Learning

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hangtao Yao, Zeming Zhang, Leo Yu Hu, Shengshan Chen, Chao Liew, Alan Li, Zhetao School of Cyber Science and Engineering Huazhong University of Science and Technology China Swinburne University of Technology Australia Griffith University Australia National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. Hubei Key Laboratory of Distributed System Security China Hubei Engineering Research Center on Big Data Security China RMIT University Australia Xiangtan University China

Federated learning (FL) is vulnerable to poisoning attacks, where adversaries corrupt the global aggregation results and cause denial-of-service (DoS). Unlike recent model poisoning attacks that optimize the amplitude of malicious perturbations along certain prescribed directions to cause DoS, we propose a Flexible Model Poisoning Attack (FMPA) that can achieve versatile attack goals. We consider a practical threat scenario where no extra knowledge about the FL system (e.g., aggregation rules or updates on benign devices) is available to adversaries. FMPA exploits the global historical information to construct an estimator that predicts the next round of the global model as a benign reference. It then fine-tunes the reference model to obtain the desired poisoned model with low accuracy and small perturbations. Besides the goal of causing DoS, FMPA can be naturally extended to launch a fine-grained controllable attack, making it possible to precisely reduce the global accuracy. Armed with precise control, malicious FL service providers can gain advantages over their competitors without getting noticed, hence opening a new attack surface in FL other than DoS. Even for the purpose of DoS, experiments show that FMPA significantly decreases the global accuracy, outperforming six state-of-the-art attacks. © 2023, CC BY.

关键词： Federated learning

Securing Sdn/Nfv-Enabled Campus Networks with Software-Defined Perimeter-Based Zero-Trust Architecture

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Ruambo, Francis A. Zou, Deqing Lopes, Ivandro O. Yuan, Bin School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Distributed System Security Wuhan China Hubei Engineering Research Center on Big Data Security Wuhan China National Engineering Research Center for Big Data Technology and System Wuhan China Services Computing Technology and System Lab Wuhan China Cluster and Grid Computing Lab Wuhan China Mbeya university of Science and Technology Mbeya131 Tanzania United Republic of Nucleo Operacional para a Sociedade de Informacao Cape Verde Songshan Laboratory Zhengzhou China

Network softwarization is a breakthrough in designing modern networks and providing numerous new network operations and services. This change is exemplified by Software Defined Networks (SDN) and Network Function Virtualization (NFV). As a result, the combination of SDN and NFV (SDN/NFV) frameworks and individual SDN and NFV frameworks have gained substantial traction in network security over the past decade, significantly supporting on-demand protection measures. However, the inherent security shortcomings of SDN, NFV, and SDN/NFV frameworks provide the fundamental issue in implementing security procedures via network softwarization. To solve this issue, we present a Software-Defined Perimeter (SDP)-powered Zero-Trust Architecture (ZTA) to improve security in the SDN/NFV-enabled campus network holistically. In addition to this, we also propose a threat model and quantitatively assess the suggested approach's performance and security. Furthermore, we highlight potential zero-trust network security function implementations in SDN/NFV-enabled infrastructure to increase protection for endpoint devices, network resources, and flows for detecting threats and responding effectively with minimal latency and overhead. © 2023, The Authors. All rights reserved.

关键词： Access control

Research on the Evolution Mechanism of Friction Wear Based on Macroscopic Dynamics

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Jia, Bowen Pei, Shixun Yang, Fangchao Li, Honggang Chen, Bingxue Zhao, Menghao Chen, Yuanhang Wang, Liang Hong, Wei MOE Key Laboratory of Fundamental Physical Quantities Measurement Hubei Key Laboratory of Gravitation and Quantum Physics PGMF School of Physics Huazhong University of Science and Technology Wuhan430074 China School of Aero-engine Engineering Zhengzhou University of Aeronautics Zhengzhou450046 China Intelligent Computing Hardware Center Zhejiang Lab Hangzhou311121 China CYG Sunri Co. Ltd. Shenzhen518057 China

This paper models the macroscopic dynamics of wear based on the linear damage mechanism, abstracting state variables of loss power, friction pair characteristics and debris characteristics. The wear evolution trend is then analyzed from system stability perspective by the Routh criterion. Furthermore, wear evolution mechanism is studied by Monte Carlo simulation within reasonable parameter ranges. Finally, the effects of multiple factors on wear evolution are analyzed by critical parameter perturbation. The results show that the action and correlation coefficients between the state variables would influence the evolution direction of friction wear. The reasonable combination of these parameters can effectively reduce loss power, decrease roughness and fluctuation of friction pairs, and slow growth rate of debris mass. © 2024, The Authors. All rights reserved.

关键词： Wear of materials

PFS3F: Probabilistic Fusion of Superpixel-wise and Semantic-aware Structural Features for Hyperspectral Image Classification

学校读者我要写书评

暂无评论

IEEE Transactions on Circuits and Systems for Video Technology 2025年

作者： Zhang, Ying Duan, Puhong Liang, Lianhui Kang, Xudong Li, Jun Plaza, Antonio Hunan University of Technology College of Railway Transportation Zhuzhou412007 China Hunan University School of Robotics Changsha410082 China Guangxi University School of Electrical Engineering Nanning530004 China China University of Geosciences Hubei Key Laboratory of Intelligent Geo-Information Processing the School of Computer Science Wuhan430078 China Hyperspectral Computing Laboratory Department of Technology of Computers and Communications Escuela Politecnica University of Extremadura CaceresE-10071 Spain

Processing high-dimensional data cubes and developing high-performance classifiers are core objectives in the field of hyperspectral image classification (HSIC). Superpixel-based methods are widely used in HSIC due to their efficacy in reducing redundant information and enhancing local features. However, imprecise segmentation, especially in complex structures and textures of hyperspectral images (HSIs), may lead to inconsistencies in the regions extracted by superpixels and the boundaries between different ground objects. Such inconsistencies significantly degrade the classification performance of HSIs. Alternatively, when parameter settings are inaccurate, edge-aware feature extraction methods often introduce sharpening artifacts at the image boundaries, resulting in a decrease in classification accuracy. To effectively address these challenges, we propose a novel probabilistic fusion method for HSIC. This method consists of the following stages. First, spatial information is extracted by a multiscale superpixel segmentation method and then probabilistically optimized by the extended random walk (ERW) method. Next, semantic-aware structural features (S2Fs) are extracted along with edge information of different objects. Lastly, a probabilistic framework is proposed to fuse the class probabilities of superpixel-based spatial information and semantic-aware structural features. Experimental results on three real datasets show state-of-the-art classification performance, even with limited training sets. ©1991-2012 IEEE.

关键词： Superpixels

A prediction-correction based iterative convolution-thresholding method for topology optimization of heat transfer problems

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Huangxin Dong, Piaopiao Wang, Dong Wang, Xiao-Ping School of Mathematical Sciences Fujian Provincial Key Laboratory on Mathematical Modeling and High Performance Scientific Computing Xiamen University Fujian361005 China School of Science and Engineering The Chinese University of Hong Kong Guangdong Shenzhen518172 China Shenzhen International Center for Industrial and Applied Mathematics Shenzhen Research Institute of Big Data Guangdong518172 China

In this paper, we propose an iterative convolution-thresholding method (ICTM) based on prediction-correction for solving the topology optimization problem in steady-state heat transfer equations. The problem is formulated as a constrained minimization problem of the complementary energy, incorporating a perimeter/surface-area regularization term, while satisfying a steady-state heat transfer equation. The decision variables of the optimization problem represent the domains of different materials and are represented by indicator functions. The perimeter/surface-area term of the domain is approximated using Gaussian kernel convolution with indicator functions. In each iteration, the indicator function is updated using a prediction-correction approach. The prediction step is based on the variation of the objective functional by imposing the constraints, while the correction step ensures the monotonically decreasing behavior of the objective functional. Numerical results demonstrate the efficiency and robustness of our proposed method, particularly when compared to classical approaches based on the ICTM. Copyright © 2024, The Authors. All rights reserved.

关键词： Convolution

A Prediction-Correction Based Iterative Convolution-Thresholding Method for Topology Optimization of Heat Transfer Problems

学校读者我要写书评

暂无评论

SSRN 2024年

关键词： Convolution

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ye, Maoyuan Zhang, Jing Liu, Juhua Liu, Chenyu Yin, Baocai Liu, Cong Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China IFLYTEK Research IFLYTEK CO. LTD. China College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue 639798 Singapore

The Segment Anything Model (SAM), a profound vision foundation model pretrained on a large-scale dataset, breaks the boundaries of general segmentation and sparks various downstream applications. This paper introduces Hi-SAM, a unified model leveraging SAM for hierarchical text segmentation. Hi-SAM excels in segmentation across four hierarchies, including pixel-level text, word, text-line, and paragraph, while realizing layout analysis as well. Specifically, we first turn SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach. We use this TS model to iteratively generate the pixel-level text labels in a semi-automatical manner, unifying labels across the four text hierarchies in the HierText dataset. Subsequently, with these complete labels, we launch the end-to-end trainable Hi-SAM based on the TS architecture with a customized hierarchical mask decoder. During inference, Hi-SAM offers both automatic mask generation (AMG) mode and promptable segmentation (PS) mode. In the AMG mode, Hi-SAM segments pixel-level text foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing. As for the PS mode, Hi-SAM provides word, text-line, and paragraph masks with a single point click. Experimental results show the state-of-the-art performance of our TS model: 84.86% fgIOU on Total-Text and 88.96% fgIOU on TextSeg for pixel-level text segmentation. Moreover, compared to the previous specialist for joint hierarchical detection and layout analysis on HierText, Hi-SAM achieves significant improvements: 4.73% PQ and 5.39% F1 on the text-line level, 5.49% PQ and 7.39% F1 on the paragraph level layout analysis, requiring 20× fewer training epochs. The code is available at Hi-SAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Masks

A Phase-Field-Based Multiple-Relaxation-Time Lattice Boltzmann Method for Incompressible Multiphase Flows with Density and Viscosity Contrasts

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Yuan, Xiaolei Wu, Yao Zhang, Chunhua Chai, Zhenhua Shi, Baochang College of Mathematics and Information Science Hebei University Baoding071002 China Institute of Interdisciplinary Research for Mathematics and Applied Science School of Mathematics and Statistics Huazhong University of Science and Technology Wuhan430074 China Hubei Key Laboratory of Engineering Modeling and Scientific Computing Huazhong University of Science and Technology Wuhan430074 China Department of Mechanics and Aerospace Engineering Southern University of Science and Technology Guangdong Shenzhen518055 China

In this work, we present a unified framework of phase-field-based multiple-relaxation-time lattice Boltzmann (MRT-LB) method for incompressible multiphase flows with density and viscosity contrasts where a block-lower-triangular relaxation matrix is introduced. The present framework includes the classic MRT-LB model and central-moments-based LB model (CLBM, a particular version of the MRT-LB model). The governing equations of incompressible multiphase flows can be reproduced precisely through the direct Taylor expansion method at the second-order of expansion parameters. In this work, the pressure $p$ is re-estimated, and we prove that the present pressure expression is suitable for classic MRT model, CLBM and various lattice structures. In addition, theoretical analysis and modeling are both carried out in the velocity space. As a result, the present model has a similar structure to the traditional Bhatnagar-Gross-Krook (BGK) model and is very easy to analyze and implement. We then test the present model (mainly CLBM) by five classic physical problems. The results show that the present model is found to be accurate and has better numerical stability over the BGK model, and has the ability to simulate multiphase flow problems with large density ratio ($1000$). © 2022, The Authors. All rights reserved.

关键词： Multiphase flow

MAP-based Problem-Agnostic Diffusion Model for Inverse Problems

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Tao, Pingping Liu, Haixia Su, Jing Yang, Xiaochen Tan, Hongchen Shandong University Library No. 180 West Culture Road Shandong Weihai264209 China School of Mathematics and Statistics Hubei Key Laboratory of Engineering Modeling and Scientific Computing Institute of Interdisciplinary Research for Mathematics and Applied Science Huazhong University of Science and Technology No. 1037 Luoyu road Hubei Wuhan430074 China Dapartment of Basic Sciences Dalian University of Science and Technology No. 999-26 Harbor Road Liaoning Dalian116052 China School of Computer Science and Technology Harbin Institute of Technology No. 2 West Culture Road Shandong Weihai264209 China Institute of Future Technology Dalian University of Technology No. 2 Lingong Road Liaoning Dalian116081 China

Diffusion models have indeed shown great promise in solving inverse problems in image processing. In this paper, we propose a novel, problem-agnostic diffusion model called the maximum a posteriori (MAP)-based guided term estimation method for inverse problems. To leverage unconditionally pretrained diffusion models to address conditional generation tasks, we divide the conditional score function into two terms according to Bayes’ rule: an unconditional score function (approximated by a pretrained score network) and a guided term, which is estimated using a novel MAP-based method that incorporates a Gaussian-type prior of natural images. This innovation allows us to better capture the intrinsic properties of the data, leading to improved performance. Numerical results demonstrate that our method preserves contents more effectively compared to state-of-the-art methods—for example, maintaining the structure of glasses in super-resolution tasks and producing more coherent results in the neighborhood of masked regions during inpainting. Our numerical implementation is available at https://***/liuhaixias1/ MAP-DIFFUSION-IP. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems