检索结果-内蒙古大学图书馆

FedPHE: A Secure and Efficient Federated Learning via Packed Homomorphic Encryption

IEEE Transactions on Dependable and Secure computing 2025年

作者： Li, Yuqing Yan, Nan Chen, Jing Wang, Xiong Hong, Jianan He, Kun Wang, Wei Li, Bo Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Wuhan University RiZhao Information Technology Institute Rizhao276800 China Huazhong University of Science and Technology 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 Wuhan430074 China Shanghai Jiao Tong University School of Cyber Science and Engineering Shanghai200240 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

Cross-silo federated learning (FL) enables multiple institutions (clients) to collaboratively build a global model without sharing private data. To prevent privacy leakage during aggregation, homomorphic encryption (HE) is widely used to encrypt model updates, yet incurs high computation and communication overheads. To reduce these overheads, packed HE (PHE) has been proposed to encrypt multiple plaintexts into a single ciphertext. However, the original design of PHE assumes all clients share a single private key, making the system vulnerable to security threats of ciphertexts being intercepted and decrypted by honest-but-curious clients. Also, it does not consider the heterogeneity among different clients, resulting in undermined training efficiency with slow convergence and stragglers. To address these challenges, we propose FedPHE, a secure and efficient FL framework with PHE by jointly exploiting contribution-aware secure aggregation and straggler-resistant client selection. Using CKKS with sparsification and blinding, FedPHE achieves efficient secure aggregation that allows clients to only provide obscured encrypted updates while the server can perform aggregation by accounting for contributions of local updates. To mitigate the straggler effect, we devise a perturbed sketch-based selection to cherry-pick representative clients with heterogeneous models and computing capabilities in a communication-efficient and privacy-preserving manner. We show, through rigorous security analysis and extensive experiments, that FedPHE can efficiently safeguard clients' privacy, achieve 2.45-6.56× training speedup, cut the communication overhead by 1.32-24.85×, and reduce straggler effects by 1.89-2.78×. © 2004-2012 IEEE.

关键词： Privacy by design

来源：评论

学校读者我要写书评

暂无评论

GALOPA: graph transport learning with optimal plan alignment 23

GALOPA: graph transport learning with optimal plan alignment

引用

Proceedings of the 37th International Conference on Neural Information Processing Systems

作者： Yejiang Wang Yuhai Zhao Zhengkui Wang Ling Li School of Computer Science and Engineering Northeastern University China and Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University China InfoComm Technology Cluster Singapore Institute of Technology Singapore

Self-supervised learning on graphs aims to learn graph representations in an unsupervised manner. While graph contrastive learning (GCL - relying on graph augmentation for creating perturbation views of anchor graphs and maximizing/minimizing similarity for positive/negative pairs) is a popular self-supervised method, it faces challenges in finding label-invariant augmented graphs and determining the exact extent of similarity between sample pairs to be achieved. In this work, we propose an alternative self-supervised solution that (i) goes beyond the label invariance assumption without distinguishing between positive/negative samples, (ii) can calibrate the encoder for preserving not only the structural information inside the graph, but the matching information between different graphs, (iii) learns isometric embeddings that preserve the distance between graphs, a by-product of our objective. Motivated by optimal transport theory, this scheme relies on an observation that the optimal transport plans between node representations at the output space, which measure the matching probability between two distributions, should be consistent with the plans between the corresponding graphs at the input space. The experimental findings include: (i) The plan alignment strategy significantly outperforms the counterpart using the transport distance; (ii) The proposed model shows superior performance using only node attributes as calibration signals, without relying on edge information; (iii) Our model maintains robust results even under high perturbation rates; (iv) Extensive experiments on various benchmarks validate the effectiveness of the proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking 25

Towards high-throughput and low-latency billion-scale vector...

引用

Proceedings of the 23rd USENIX Conference on File and Storage Technologies

作者： Bing Tian Haikun Liu Yuhang Tang Shihai Xiao Zhuohui Duan Xiaofei Liao Hai Jin Xuecang Zhang Junhua Zhu Yu Zhang National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Huawei Technologies Co. Ltd Towards high-throughput and low-latency billion-scale vector search via CPU/GPU collaborative filtering and re-ranking

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present Fusion-ANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of Fusion-ANNS lies in CPU/GPU collaborative filtering and reranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN; 2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy.

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

EdgeThemis: Ensuring Model Integrity for Edge Intelligence 25

EdgeThemis: Ensuring Model Integrity for Edge Intelligence

引用

34th ACM Web Conference, WWW 2025

作者： Yang, Jiyu He, Qiang Zhou, Zheyu Dai, Xiaohai Chen, Feifei Tian, Cong Yang, Yun Swinburne University of Technology Melbourne Australia Huazhong University of Science and Technology Wuhan China Deakin University Melbourne Australia Xidian University Xi’an China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9798400712746

Machine learning (ML) models are widely deployed on edge nodes, such as mobile phones and edge servers, to power a wide range of AI applications over the web. Ensuring the integrity of these edge models is paramount, as they are subject to corruption caused by software/hardware exceptions and malicious tampering, which may undermine model performance, incur economic losses, and pose health risks. Existing data integrity mechanisms designed for files stored on disks cannot properly verify the integrity of models running in GPUs or mitigate the new integrity threats against edge models. This paper proposes EdgeThemis, a novel mechanism for verifying the integrity of edge models through sentinel verification. To enable verifiability for a model M, EdgeThemis embeds a sentinel backdoor and a verification module into M. Then, a challenger can send verification requests to the edge node hosting M to verify its integrity. Next, the sentinel activates the verification module to generate a unique integrity proof tied to the identity of the edge node for verification. Finally, the challenger can verify the integrity proof to detect model corruption. Theoretical analysis proves that EdgeThemis can properly mitigate potential integrity threats against edge models. Experiments demonstrate that EdgeThemis achieves a verification accuracy of 100.00% across various models and different types of model corruption with robustness against replay attacks, theft attacks, and replacement attacks. © 2025 Copyright held by the owner/author(s).

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Network for Segmenting Pathology Lesion of the Focal Lymphocytic Sialadenitis

M2CF-Net: A Multi-Resolution and Multi-Scale Cross Fusion Ne...

引用

Medical Artificial Intelligence (MedAI), IEEE International Conference on

作者： Hao Han Feng Lu Yanhan Deng Xiaofang Luo Hai Jin Wei Tu Xia Xie 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 Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Hainan University Haikou China

In the medical realm, the pivotal role of pathological Whole Slide Images (WSIs) in detecting cancer, tracking disease progression, and evaluating treatment efficacy is indisputable. Nevertheless, the identification and quantification of lesion areas in these gigapixel WSIs present a significant challenge due to their substantial size and the intricate details of lesions. To address these issues, we developed a novel multi-resolution and multi-scale cross fusion network (M 2 CF-Net), adept at managing large-scale pathological WSIs and capturing both fine details and context. Our model particularly focuses on segmenting local lymphocyte infiltration lesions in pathological WSIs of patients diagnosed with primary Sjogren's syndrome. By employing a patch-based training approach and combining interconnected elements via a multi-scale fusion technique, we enhance our model's capacity to detect and analyze structures and features in minor salivary gland section WSIs. Extensive experiments and ablation studies conducted on real-world clinical datasets affirm our model's superior accuracy in identifying lymphocyte-infiltrated regions over state-of-the-art models, with a performance improvement of up to 4.32% in terms of the Dice Similarity Coefficient.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Data Visualization from Natural Language via Large Language Models: An Exploratory Study

arXiv

引用

arXiv 2024年

作者： Wu, Yang Wan, Yao Zhang, Hongyu Sui, Yulei Wei, Wucai Zhao, Wei Xu, Guandong Jin, Hai Huazhong University of Science and Technology China Chongqing University China University of New South Wales Australia University of Technology Sydney Australia 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

The Natural Language to Visualization (NL2Vis) task aims to transform natural-language descriptions into visual representations for a grounded table, enabling users to gain insights from vast amounts of data. Recently, many deep learning-based approaches have been developed for NL2Vis. Despite the considerable efforts made by these approaches, challenges persist in visualizing data sourced from unseen databases or spanning multiple tables. Taking inspiration from the remarkable generation capabilities of Large Language Models (LLMs), this paper conducts an empirical study to evaluate their potential in generating visualizations, and explore the effectiveness of in-context learning prompts for enhancing this task. In particular, we first explore the ways of transforming structured tabular data into sequential text prompts, as to feed them into LLMs and analyze which table content contributes most to the NL2Vis. Our findings suggest that transforming structured tabular data into programs is effective, and it is essential to consider the table schema when formulating prompts. Furthermore, we evaluate two types of LLMs: finetuned models (e.g., T5-Small) and inference-only models (e.g., GPT-3.5), against state-of-the-art methods, using the NL2Vis benchmarks (i.e., nvBench). The experimental results reveal that LLMs outperform baselines, with inference-only models consistently exhibiting performance improvements, at times even surpassing fine-tuned models when provided with certain few-shot demonstrations through in-context learning. Finally, we analyze when the LLMs fail in NL2Vis, and propose to iteratively update the results using strategies such as chain-of-thought, role-playing, and code-interpreter. The experimental results confirm the efficacy of iterative updates and hold great potential for future study. © 2024, CC BY.

关键词： Data visualization

来源：评论

学校读者我要写书评

暂无评论

RETIA: Relation-Entity Twin-Interact Aggregation for Temporal Knowledge Graph Extrapolation

RETIA: Relation-Entity Twin-Interact Aggregation for Tempora...

引用

International Conference on Data Engineering

作者： Kangzheng Liu Feng Zhao Guandong Xu Xianzhi Wang Hai Jin 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 Data Science and Machine Intelligence Lab University of Technology Sydney Sydney Australia

Temporal knowledge graph (TKG) extrapolation aims to predict future unknown events (facts) based on historical information, and has attracted considerable attention due to its great practical significance. Accurate representations (embeddings) of entities and relations form the basis of TKG extrapolation. Recent work has been devoted to improving the rationality of entity representations. However, on the one hand, ignoring relation modeling results in incomplete relation representations; therefore, some approaches aggregate only immediately adjacent entities of relations, but this can lead to the "message islands" problem of relation modeling. On the other hand, ignoring the association constraints between relations and entities can make the embeddings of both relations and entities prone to overfitting. To address the abovementioned challenges, we propose an advanced method, namely, RETIA. For the former issue, we generate twin hyperrelation subgraphs for each historical subgraph and then aggregate both the adjacent entities and relations in the hyperrelation subgraphs through a graph convolutional network (GCN). About the latter concern, we propose a twin-interact module (TIM), which provides communication channels for relation aggregation and entity aggregation during the evolution of the historical sequence. Experiments conducted on five public datasets show that RETIA has made great improvements across several evaluation metrics. Our released code is available at https://***/CGCL-codes/RETIA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graft: Efficient Inference Serving for Hybrid Deep Learning with SLO Guarantees via DNN Re-alignment

arXiv

引用

arXiv 2023年

作者： Wu, Jing Wang, Lin Jin, Qirui Liu, Fangming The National Engineering Research Center for Big Data Technology and System The Services Computing Technology and System Lab Cluster and Grid Computing Lab in The School of Computer Science and Technology Huazhong University of Science and Technology 1037 Luoyu Road Wuhan430074 China Paderborn University TU Darmstadt Germany Peng Cheng Laboratory Huazhong University of Science and Technology China

Deep neural networks (DNNs) have been widely adopted for various mobile inference tasks, yet their ever-increasing computational demands are hindering their deployment on resource-constrained mobile devices. Hybrid deep learning partitions a DNN into two parts and deploys them across the mobile device and a server, aiming to reduce inference latency or prolong battery life of mobile devices. However, such partitioning produces (non-uniform) DNN fragments which are hard to serve efficiently on the server. This paper presents Graft—an efficient inference serving system for hybrid deep learning with latency service-level objective (SLO) guarantees. Our main insight is to mitigate the non-uniformity by a core concept called DNN re-alignment, allowing multiple heterogeneous DNN fragments to be restructured to share layers. To fully exploit the potential of DNN re-alignment, Graft employs fine-grained GPU resource sharing. Based on that, we propose efficient algorithms for merging, grouping, and re-aligning DNN fragments to maximize request batching opportunities, minimizing resource consumption while guaranteeing the inference latency SLO. We implement a Graft prototype and perform extensive experiments with five types of widely used DNNs and real-world network traces. Our results show that Graft improves resource efficiency by up to 70% compared with the state-of-the-art inference serving systems. © 2023, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

SocialEdge: Socialized Learning-Based Request Scheduling for Edge-Cloud Systems

SocialEdge: Socialized Learning-Based Request Scheduling for...

引用

International Conference on Distributed computing Systems

作者： Ziwei Wang Yunfeng Zhao Chao Qiu Qiang He Xin Wang Xiaofei Wang Qinghua Hu College of Intelligence and Computing Tianjin University Tianjin China Guangdong Laboratory of Artificial Intelligence and DigitalEconomy (SZ) Shenzhen China School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computing Technologies Swinburne University of Technology Australia National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Huazhong University of Science and Technology Wuhan China

The ability for cloud data centres and edge data centres to collaborate unleashes the potential of the edge-cloud system. However, its sophistication causes unexpected issues in request scheduling, such as Insufficient intelligence, complicated hierarchy and limited cooperation. Traditional resource optimization methods for the edge-cloud system struggle to accommodate such intricate situations. In this paper, inspired by the behaviors and regulations in human society, we propose a socialized learning-based scheduling approach for the edge-cloud system, namely SocialEdge. In order to adapt to time-varying requests and dynamic service prevalence, we propose a learning-based approach, multi-agent advantage actor-critic (MAA2C) and graph convolutional networks-based MAA2C for two phases, respectively, which can improve individual intelligence to achieve optimal dispatch and orchestration decisions. Then, to make use of hierarchy correlation, we develop the socialized refining inter the layers, where inference results from one layer guide the training process of the other layer so that optimization-critical knowledge can be abstracted. Besides, we apply socialized cooperation to each layer, where federated averaging with MAA2C is implemented to ensure cooperation over private data for achieving optimal global solutions. Experimental evaluations on a proof-of-concept testbed along with two real traces demonstrate that baselines have 105% more delay than SocialEdge while being 76.6% less time efficiency and 21.6% less throughput.

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：