检索结果-内蒙古大学图书馆

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Learning as a Service

学校读者我要写书评

暂无评论

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Le...

IEEE International Conference on e-science and Grid computing

作者： Zilinghan Li Shilan He Pranshu Chaturvedi Trung-Hieu Hoang Minseok Ryu E. A. Huerta Volodymyr Kindratenko Jordan Fuhrman Maryellen Giger Ryan Chard Kibaek Kim Ravi Madduri Data Science and Learning Division Argonne National Laboratory Lemont IL USA Department of Computer Science University of Illinois at Urbana-Champaign Urbana IL USA National Center for Supercomputing Applications University of Illinois at Urbana-Champaign Urbana IL USA Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Urbana IL USA School of Computing and Augmented Intelligence Arizona State University Tempe AZ USA Department of Physics University of Illinois at Urbana-Champaign Urbana IL USA Department of Computer Science The University of Chicago Chicago IL USA Mathematics and Computer Science Division Argonne National Laboratory Lemont IL USA University of Chicago Consortium for Advanced Science and Engineering Chicago IL USA

Cross-silo privacy-preserving federated learning (PPFL) is a powerful tool to collaboratively train robust and generalized machine learning (ML) models without sharing sensitive (e.g., healthcare of financial) local data. To ease and accelerate the adoption of PPFL, we introduce APPFLx, a ready-to-use platform that provides privacy-preserving cross-silo federated learning as a service. APPFLx employs Globus authentication to allow users to easily and securely invite trustworthy collaborators for PPFL, implements several synchronous and asynchronous FL algorithms, streamlines the FL experiment launch process, and enables tracking and visualizing the life cycle of FL experiments, allowing domain experts and ML practitioners to easily orchestrate and evaluate cross-silo FL under one platform. APPFLx is available online at https://***

关键词：

Distributed Adaptive Fault-Tolerant Output Regulation of Heterogeneous Multi-Agent Systems With Coupling Uncertainties and Actuator Faults

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2020年第4期7卷 1098-1106页

作者： Chao Deng Weinan Gao Weiwei Che the School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore the Department of Electrical and Computer Engineering Allen E.Paulson College of Engineering and ComputingGeorgia Southern UniversityStatesboroGA 30460 USA the State Key Laboratory of Industrial Control Technology Institute of Cyber-Systems and ControlZhejiang UniversityHangzhou 310027 the Institute of Complexity Science Qingdao UniversityQingdao 266071China

In this paper, we consider the distributed adaptive fault-tolerant output regulation problem for heterogeneous multiagent systems with matched system uncertainties and mismatched coupling uncertainties among subsystems under the influence of actuator faults. First, distributed finite-time observers are proposed for all subsystems to observe the state of the exosystem. Then, a novel fault-tolerant controller is designed to compensate for the influence of matched system uncertainties and actuator faults. By using the linear matrix inequality technique, a sufficient condition is provided to guarantee the solvability of the considered problem in the presence of mismatched coupling uncertainties. Moreover, it is shown that the system in closed-loop with the developed controller can achieve output regulation by using the Lyapunov stability theory and cyclic-small-gain ***, a numerical example is given to illustrate the effectiveness of the obtained result.

关键词： Adaptive control cyclic-small-gain fault-tolerant control multi-agent systems(MASs)

Decentralized Nonconvex Robust Optimization over Unsafe Multiagent Systems: System Modeling, Utility, Resilience, and Privacy Analysis

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hu, Jinhui Chen, Guo Li, Huaqing Cheng, Huqiang Guo, Xiaoyu Huang, Tingwen School of Automation Central South University Changsha410083 China Department of Biomedical Engineering City University of Hong Kong Kowloon Hong Kong School of Electrical Engineering and Telecommunications University of New South Wales SydneyNSW2052 Australia Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen518055 China

Privacy leakage and Byzantine failures are two adverse factors to the intelligent decision-making process of multiagent systems (MASs). Considering an unsafe MAS with these two issues, this paper targets the resolution of a class of nonconvex optimization problems under the Polyak-Lojasiewicz (P-L) condition. To address this problem, we first identify and construct the unsafe MAS model. Under this kind of unfavorable MASs, we mask the local gradients with Gaussian noises and adopt a resilient aggregation method self-centered clipping (SCC) to design a differentially private (DP) decentralized Byzantine-resilient algorithm, namely DP-SCC-PL, which simultaneously achieves differential privacy and Byzantine resilience. The convergence analysis of DP-SCC-PL is challenging since the convergence error can be contributed jointly by privacy-preserving and Byzantine-resilient mechanisms, as well as the nonconvex relaxation, which is addressed via seeking the contraction relationships among the disagreement measure of reliable agents before and after SCC aggregation, together with the optimal gap. Theoretical results reveal that DP-SCC-PL achieves consensus among all reliable agents and sublinear (inexact) convergence with well-designed step-sizes. It has also been proved that if there are no privacy issues and Byzantine agents, then the asymptotic exact convergence can be recovered. Numerical experiments verify the utility, resilience, and differential privacy of DP-SCC-PL by tackling a nonconvex optimization problem satisfying the P-L condition under various Byzantine attacks. Copyright © 2024, The Authors. All rights reserved.

关键词： Differential privacy

Touchstone benchmark: are we on the right way for evaluating AI algorithms for medical segmentation? 24

学校读者我要写书评

暂无评论

Touchstone benchmark: are we on the right way for evaluating...

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

作者： Pedro R. A. S. Bassi Wenxuan Li Yucheng Tang Fabian Isensee Zifu Wang Jieneng Chen Yu-Cheng Chou Saikat Roy Yannick Kirchhoff Maximilian Rokuss Ziyan Huang Jin Ye Junjun He Tassilo Wald Constantin Ulrich Michael Baumgartner Klaus H. Maier-Hein Paul Jaeger Yiwen Ye Yutong Xie Jianpeng Zhang Ziyang Chen Yong Xia Zhaohu Xing Lei Zhu Yousef Sadegheih Afshin Bozorgpour Pratibha Kumari Reza Azad Dorit Merhof Pengcheng Shi Ting Ma Yuxin Du Fan Bai Tiejun Huang Bo Zhao Haonan Wang Xiaomeng Li Hanxue Gu Haoyu Dong Jichen Yang Maciej A. Mazurowski Saumya Gupta Linshan Wu Jiaxin Zhuang Hao Chen Holger Roth Daguang Xu Matthew B. Blaschko Sergio Decherchi Andrea Cavalli Alan L. Yuille Zongwei Zhou Department of Computer Science Johns Hopkins University and Department of Pharmacy and Biotechnology University of Bologna and Center for Biomolecular Nanotechnologies Istituto Italiano di Tecnologia Department of Computer Science Johns Hopkins University NVIDIA Division of Medical Image Computing German Cancer Research Center (DKFZ) and Helmholtz Imaging German Cancer Research Center (DKFZ) ESAT-PSI KU Leuven Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University Division of Medical Image Computing German Cancer Research Center (DKFZ) and Faculty of Mathematics and Computer Science Heidelberg University and HIDSS4Health - Helmholtz Information and Data Science School for Health Shanghai Jiao Tong University Shanghai Artificial Intelligence Laboratory Division of Medical Image Computing German Cancer Research Center (DKFZ) Division of Medical Image Computing German Cancer Research Center (DKFZ) and Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Helmholtz Imaging German Cancer Research Center (DKFZ) and Interactive Machine Learning Group (IML) DKFZ School of Computer Science and Engineering Northwestern Polytechnical University Australian Institute for Machine Learning The University of Adelaide College of Computer Science and Technology Zhejiang University Hong Kong University of Science and Technology (Guangzhou) Hong Kong University of Science and Technology (Guangzhou) and Hong Kong University of Science and Technology Faculty of Informatics and Data Science University of Regensburg Faculty of Electrical Engineering and Information Technology RWTH Aachen University Faculty of Informatics and Data Science University of Regensburg and Fraunhofer Institute for Digital Medicine MEVIS Electronic & Information Engineering School Harbin Institute of Technology (Shenzhen) Shanghai Jiao Tong University and Beijing Academy of Artificial Intelligence (BAAI) S

ISBN: (纸本)9798331314385

How can we test AI performance? This question seems trivial, but it isn't. Standard benchmarks often have problems such as in-distribution and small-size test sets, oversimplified metrics, unfair comparisons, and short-term outcome pressure. As a consequence, good performance on standard benchmarks does not guarantee success in real-world scenarios. To address these problems, we present Touchstone, a large-scale collaborative segmentation benchmark of 9 types of abdominal organs. This benchmark is based on 5,195 training CT scans from 76 hospitals around the world and 5,903 testing CT scans from 11 additional hospitals. This diverse test set enhances the statistical significance of benchmark results and rigorously evaluates AI algorithms across out-of-distribution scenarios. We invited 14 inventors of 19 AI algorithms to train their algorithms, while our team, as a third party, independently evaluated these algorithms. In addition, we also evaluated pre-existing AI frameworks—which, differing from algorithms, are more flexible and can support different algorithms—including MONAI from NVIDIA, nnU-Net from DKFZ, and numerous other open-source frameworks. We are committed to expanding this benchmark to encourage more innovation of AI algorithms for the medical domain.

关键词：

Optimizing Generative AI Networking: A Dual Perspective with Multi-Agent Systems and Mixture of Experts

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhang, Ruichen Du, Hongyang Niyato, Dusit Kang, Jiawen Xiong, Zehui Zhang, Ping Kim, Dong In The College of Computing and Data Science Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications China The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

In the continued development of next-generation networking and artificial intelligence content generation (AIGC) services, the integration of multi-agent systems (MAS) and the mixture of experts (MoE) frameworks is becoming increasingly important. Motivated by this, this article studies the contrasting and converging of MAS and MoE in AIGC-enabled networking. First, we discuss the architectural designs, operational procedures, and inherent advantages of using MAS and MoE in generative AI to explore its functionality and applications fully. Next, we review the applications of MAS and MoE frameworks in content generation and resource allocation, emphasizing their impact on networking operations. Subsequently, we propose a novel multi-agent-enabled MoE-proximal policy optimization (MoE-PPO) framework for 3D object generation and data transfer scenarios. The framework uses MAS for dynamic task coordination of each network service provider agent and MoE for expert-driven execution of respective tasks, thereby improving overall system efficiency and adaptability. The simulation results demonstrate the effectiveness of our proposed framework and significantly improve the performance indicators under different network conditions. Finally, we outline potential future research directions. © 2024, CC BY.

关键词： Multi agent systems

Graph Neural Network Enabled Fluid Antenna Systems: A Two-Stage Approach

学校读者我要写书评

暂无评论

arXiv 2025年

作者： He, Changpeng Lu, Yang Chen, Wei Ai, Bo Wong, Kai-Kit Niyato, Dusit State Key Laboratory of Advanced Rail Autonomous Operation China School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China School of Electronics and Information Engineering Beijing Jiaotong University Beijing100044 China Department of Electronic and Electrical Engineering University College London LondonWC1E 6BT United Kingdom Yonsei Frontier Laboratory The School of Integrated Technology Yonsei University Seoul03722 Korea Republic of College of Computing and Data Science Nanyang Technological University Singapore639798 Singapore

An emerging fluid antenna system (FAS) brings a new dimension, i.e., the antenna positions, to deal with the deep fading, but simultaneously introduces challenges related to the transmit design. This paper proposes an "unsupervised learning to optimize" paradigm to optimize the FAS. Particularly, we formulate the sum-rate and energy efficiency (EE) maximization problems for a multiple-user multiple-input single-output (MU-MISO) FAS and solved by a two-stage graph neural network (GNN) where the first stage and the second stage are for the inference of antenna positions and beamforming vectors, respectively. The outputs of the two stages are jointly input into a unsupervised loss function to train the two-stage GNN. The numerical results demonstrates that the advantages of the FAS for performance improvement and the two-stage GNN for real-time and scalable optimization. Besides, the two stages can function separately. © 2025, CC BY.

关键词： Graph neural networks

Towards a Quantum Algorithm for the Incompressible Nonlinear Navier-Stokes Equations

学校读者我要写书评

暂无评论

Towards a Quantum Algorithm for the Incompressible Nonlinear...

Quantum computing and engineering (QCE), IEEE International Conference on

作者： Muralikrishnan Gopalakrishnan Meena Yu Zhang Weiwen Jiang Youzuo Lin Stefanie Günther Xinfeng Gao National Center for Computational Sciences Oak Ridge National Laboratory Oak Ridge TN USA Theoretical Division Los Alamos National Laboratory Los Alamos NM USA Department of Electrical and Computer Engineering George Mason University Fairfax VA USA School of Data Science and Society University of North Carolina at Chapel Hill Chapel Hill NC USA Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore CA USA Department of Mechanical and Aerospace Engineering University of Virginia Charlottesville VA USA

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

In this work, we present novel concepts for quantum algorithms to solve transient, nonlinear partial differential equations (PDEs). The challenge lies in how to effectively represent, encode, process, and evolve the nonlinear system of PDEs on quantum computers. We will discuss the new techniques using the incompressible Navier-Stokes equations as an example, because it represents the fundamental nonlinear feature and yet removes certain complexity in physics, allowing us to focus on the design of quantum algorithms. Previous attempts solving nonlinear PDEs in quantum computation have often involved storing multiple copies of solutions or employing linearizations. Neither is practical due to exponential scaling with evolution time or insufficient solution accuracy. We propose a new framework based on matrix product states (MPSs) and matrix product operators (MPOs), in addition to the Krylov subspace methods. For example, the solution variables of the Navier-Stokes equations are represented by MPSs, and the linear and nonlinear terms are processed by MPOs. The time evolution of the operators is attained by a fast-forwarding algorithm using Krylov subspace methods. Furthermore, we discuss various techniques for efficient encoding of MPSs, measurement reduction for MPOs, and use of tensor operations to treat multi-variate, multi-physics characteristics of Navier-Stokes.

关键词： computers Quantum algorithm Tensors Fluids Partial differential equations Encoding Transient analysis Nonlinear systems Physics Navier-Stokes equations

Two-Stream Regression Network for Dental Implant Position Prediction

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Yang, Xinquan Li, Xuguang Li, Xuechen Chen, Wenting Shen, Linlin Li, Xin Deng, Yongqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Research Center for Medical Image Analysis and Diagnosis Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Department of Stomatology Shenzhen University General Hospital Shenzhen China Department of Electrical Engineering City University of Hong Kong Hong Kong

In implant prosthesis treatment, the design of surgical guide requires lots of manual labors and is prone to subjective variations. When deep learning based methods has started to be applied to address this problem, the space between teeth are various and some of them might present similar texture characteristic with the actual implant region. Both problems make a big challenge for the implant position prediction. In this paper, we develop a two-stream implant position regression framework (TSIPR), which consists of an implant region detector (IRD) and a multi-scale patch embedding regression network (MSPENet), to address this issue. For the training of IRD, we extend the original annotation to provide additional supervisory information, which contains much more rich characteristic and do not introduce extra labeling costs. A multi-scale patch embedding module is designed for the MSPENet to adaptively extract features from the images with various tooth spacing. The global-local feature interaction block is designed to build the encoder of MSPENet, which combines the transformer and convolution for enriched feature representation. During inference, the RoI mask extracted from the IRD is used to refine the prediction results of the MSPENet. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed TSIPR achieves superior performance than existing methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Embeddings

PMU-Spill: Performance Monitor Unit Counters Leak Secrets in Transient Executions

学校读者我要写书评

暂无评论

PMU-Spill: Performance Monitor Unit Counters Leak Secrets in...

IEEE Asian Hardware-Oriented Security and Trust (AsianHOST)

作者： Pengfei Qiu Qiang Gao Dongsheng Wang Yongqiang Lyu Chang Liu Xiaoyong Li Chunlu Wang Gang Qu Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Tsinghua University Beijing China Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Ministry of Education Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Beijing China Department of Electrical and Computer Engineering Institute for Systems Research University of Maryland Maryland USA

ISBN: (纸本)9781665461153

The processor's Performance Monitor Unit (PMU) allows the recording of architectural and microarchitectural events for profiling purposes. In this study, we reveal a security issue caused by the fact that current PMU implementations are capable of recording some events that happened during transient executions. We propose the PMU -Spill attack, a new kind of attack that enables attackers to maliciously leak the secret data in transient executions. We demonstrate on real hardware that PMU -Spill attack can leak the secret data stored in Intel Software Guard Extensions (SGX). In addition, we perform a thorough study to reveal all the vulnerable PMU counters and find that 20 of them can be used to achieve PMU -Spill attack. Our experiments suggest that the throughput of PMU -Spill attack is up to 575.3 bytes per second (Bps) with an average error rate of 1.89% when leaking the SGX-protected secret data.

关键词： Side-channel attacks Throughput Phasor measurement units Hardware Software Recording Security