检索结果-内蒙古大学图书馆

Optimal Hub Placement and Deadlock-Free Routing for Payment Channel Network Scalability

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2023年

关键词： Scalability

FINDER: A Simple and Effective Defender against Unnoticeable Graph Injection Attacks

学校读者我要写书评

暂无评论

FINDER: A Simple and Effective Defender against Unnoticeable...

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Linlin Su Jinyan Wang Zeming Gan Xianxian Li Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Graph Neural Networks (GNNs) have various applications in real-life scenarios. However, they are vulnerable to adversarial attacks, especially Graph Injection Attacks (GIAs). The flexible and high-risk GIAs pose a significant threat by injecting malicious nodes into the graph. Regrettably, defense strategies to resist GIAs are still scarce. The current defenders lack comprehensive strategies that can effectively resist a wide range of injection techniques. Particularly, when confronted with highly unnoticeable GIAs, the performance of these defenses is significantly diminished. In this paper, we propose a simple and effective GIA defense method named Faithful INjection DefendER (FINDER). FINDER evaluates the impact of the nodes on their neighbors in the context of message aggregation to identify the potential injected nodes in the graph. By blocking identified injected nodes from interacting with the benign nodes, FINDER prevents the further propagation of misinformation and the spread of adversarial influence throughout the graph. Through extensive experiments conducted on three benchmarks, FINDER demonstrates remarkable performance in accurately identifying injected nodes and defending various GIAs.

关键词： Privacy Resists Benchmark testing Graph neural networks Security Fake news

Efficient Adaptive label Refinement for label Noise Learning

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Zhang, Wenzhen Cheng, Debo Lu, Guangquan Zhou, Bo Li, Jiaye Zhang, Shichao School of Computer Science and Engineering Guangxi Normal University Guangxi Guilin541004 China Guangxi Key Lab of Multi-Source Information Mining & Security Guangxi Normal University Guangxi Guilin541004 China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guangxi Guilin541004 China UniSA STEM University of South Australia AdelaideSA5095 Australia Guangxi Collaborative Innovation Center of Modern Sericulture and Silk Hechi University Guangxi Hechi546300 China The State Key Laboratory of Blockchain and Data Security Zhejiang University Zhejiang Hangzhou310027 China

Deep neural networks are highly susceptible to overfitting noisy labels, which leads to degraded performance. Existing methods address this issue by employing manually defined criteria, aiming to achieve optimal partitioning in each iteration to avoid fitting noisy labels while thoroughly learning clean samples. However, this often results in overly complex and difficult-to-train models. To address this issue, we decouple the tasks of avoiding fitting incorrect labels and thoroughly learning clean samples and propose a simple yet highly applicable method called Adaptive label Refinement (ALR). First, inspired by label refurbishment techniques, we update the original hard labels to soft labels using the model’s predictions to reduce the risk of fitting incorrect labels. Then, by introducing the entropy loss, we gradually ‘harden’ the high-confidence soft labels, guiding the model to better learn from clean samples. This approach is simple and efficient, requiring no prior knowledge of noise or auxiliary datasets, making it more accessible compared to Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

Efficient Federated Learning Using Dynamic Update and Adaptive Pruning with Momentum on Shared Server Data

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Ji Jia, Juncheng Zhang, Hong Yun, Yuhui Wang, Leye Zhou, Yang Dai, Huaiyu Dou, Dejing Hithink RoyalFlush Information Network Co. Ltd. Hangzhou China School of Computer Science and Technology Soochow University Collaborative Innovation Center of Novel Software Technology and Industrialization Suzhou China School of Computer Science and Technology Soochow University Suzhou China Baidu Research Beijing China Key Lab of High Confidence Software Technologies Ministry of Education Software Institute Peking University Beijing China Department of Computer Science and Software Engineering Auburn University Auburn United States Department of Electrical and Computer Engineering North Carolina State University NC United States BEDI Cloud and School of Computer Science Fudan University Beijing China

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three original contributions, to leverage the shared insensitive data on the server in addition to the distributed data in edge devices so as to efficiently train a global model. First, we propose a simple dynamic server update algorithm, which takes advantage of the shared insensitive data on the server while dynamically adjusting the update steps on the server in order to speed up the convergence and improve the accuracy. Second, we propose an adaptive optimization method with the dynamic server update algorithm to exploit the global momentum on the server and each local device for superior accuracy. Third, we develop a layer-adaptive model pruning method to carry out specific pruning operations, which is adapted to the diverse features of each layer so as to attain an excellent trade-off between effectiveness and efficiency. Our proposed FL model, FedDUMAP, combines the three original techniques and has a significantly better performance compared with baseline approaches in terms of efficiency (up to 16.9 times faster), accuracy (up to 20.4% higher), and computational cost (up to 62.6% smaller). © 2024, CC BY.

关键词： Federated learning

A Multimedia Approach to Problem Descriptions for Fine-Grained Detail Characterization

学校读者我要写书评

暂无评论

A Multimedia Approach to Problem Descriptions for Fine-Grain...

IEEE International Requirements Engineering Conference Workshops (REW)

作者： Bowen Zheng Zhi Li Hongbin Xiao School of Computer Science and Engineering Guangxi Normal University Guilin China Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China

Requirements analysis has always been regarded as the starting point and focus of requirements engineering. The Problem Frames (PF) approach provides a problem-oriented requirements analysis method by describing the software's operating environment in detail. It can effectively bridge the gap between requirements analysis and system design. However, an intuitive and convenient means of elaborating the rich details of complex requirements and their contexts is missing from the literature. Currently, the main methods for describing requirements are through textual descriptions or formal language descriptions, which can result in the PF model containing a large amount of textual representations, and increasing the difficulty and time required for user understanding. In this paper, we present the PF2Detail, a tool that enables fine-grained descriptions of the PF model. Building upon the PF model construction, PF2Detail incorporates multimedia to describe complex requirements in context. Each node in the model can include multimedia, text, or formal language to provide detailed characterizations. Additionally, users can view detailed information about any node in the model and navigate the entire model, aiming to enhance the level of details in the PF model descriptions.

关键词：

DARR: A Dual-Branch Arithmetic Regression Reasoning Framework for Solving Machine Number Reasoning 39

学校读者我要写书评

暂无评论

DARR: A Dual-Branch Arithmetic Regression Reasoning Framewor...

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Chengtai Tan, Yee Yang He, Yuting Ren, Jianfeng Bai, Ruibin Zhao, Yitian Yu, Heng Jiang, Xudong The Digital Port Technologies Lab School of Computer Science University of Nottingham Ningbo China China Cixi Institute of Biomedical Engineering Ningbo Institute of Industrial Technology Chinese Academy of Sciences China School of Computer Science University of Nottingham Malaysia Malaysia Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China Beacons of Excellence Research and Innovation Institute University of Nottingham Ningbo China China School of Electrical & Electronic Engineering Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Abstract visual reasoning (AVR) is a critical ability of humans, and it has been widely studied, but arithmetic visual reasoning, a unique task in AVR to reason over number sense, is less studied in the literature. To facilitate this research, we construct a Machine Number Reasoning (MNR) dataset to assess the model's ability in arithmetic visual reasoning over number sense and spatial layouts. To solve the MNR tasks, we propose a Dual-branch Arithmetic Regression Reasoning (DARR) framework, which includes an Intra-Image Arithmetic Regression Reasoning (IIARR) module and a Cross-Image Arithmetic Regression Reasoning (CIARR) module. The IIARR includes a set of Intra-Image Regression Blocks to identify the correct number orders and the underlying arithmetic rules within individual images, and an Order Gate to determine the correct number order. The CIARR establishes the arithmetic relations across different images through a '3-to-1' regressor and a set of '2-to-1' regressors, with a Selection Gate to select the most suitable '2-to-1' regressor and a gated fusion to combine the two kinds of regressors. Experiments on the MNR dataset show that the DARR outperforms state-of-the-art models for arithmetic visual reasoning. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Digital arithmetic

LOGCAN++: Adaptive Local-global class-aware network for semantic segmentation of remote sensing imagery

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ma, Xiaowen Lian, Rongrong Wu, Zhenkai Guo, Hongbo Yang, Fan Ma, Mengting Wu, Sensen Du, Zhenhong Song, Siyang Zhang, Wei The School of Software Technology Zhejiang University Hangzhou310027 China The school of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai200030 China The School of Computer Science and Technology Zhejiang University Hangzhou310027 China The School of Earth Sciences Zhejiang University Hangzhou310027 China The Innovation Center of Yangtze River Delta Zhejiang University Zhejiang Jiaxing314103 China The HUBG Lab Department of Computer Science University of Exeter United Kingdom

Remote sensing images usually characterized by complex backgrounds, scale and orientation variations, and large intra-class variance. General semantic segmentation methods usually fail to fully investigate the above issues, and thus their performances on remote sensing image segmentation are limited. In this paper, we propose our LOGCAN++, a semantic segmentation model customized for remote sensing images, which is made up of a Global Class Awareness (GCA) module and several Local Class Awareness (LCA) modules. The GCA module captures global representations for class-level context modeling to reduce the interference of background noise. The LCA module generates local class representations as intermediate perceptual elements to indirectly associate pixels with the global class representations, targeting at dealing with the large intra-class variance problem. In particular, we introduce affine transformations in the LCA module for adaptive extraction of local class representations to effectively tolerate scale and orientation variations in remote sensing images. Extensive experiments on three benchmark datasets show that our LOGCAN++ outperforms current mainstream general and remote sensing semantic segmentation methods and achieves a better trade-off between speed and accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantic Segmentation

Node Classification in Graph Neural Networks under Dual Consistency

学校读者我要写书评

暂无评论

Node Classification in Graph Neural Networks under Dual Cons...

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Qiyu Li Xianxian Li De Li Jinyan Wang Key Lab of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin China Guangxi Key Lab of Multi-Source Information Mining and Security Guangxi Normal University Guilin China School of Computer Science and Engineering Guangxi Normal University Guilin China

In recent years, graph neural networks (GNNs) have become a popular semi-supervised learning method for processing graph-structured data. However, traditional graph neural network models rely heavily on labeled data during learning while neglecting the potential of unlabeled data. To further exploit unlabeled data, pseudo-labeling-based methods select high-confidence pseudo-labeling during training and assign unlabeled nodes to join the training accordingly. Unfortunately, there is a confidence bias in the training process with this approach. On the other hand, self-supervised learning trains GNNs models to learn embeddings by mining the supervised information in the data. Since the training process does not introduce labeling information, the discriminative information of classes is not learned. To this end, for node classification in GNNs we propose a novel method that combines self-supervised and semi-supervised approaches, namely SLCSL, which mainly consists of two modules, random neighbors node consistency and class-centered consistency. Random neighbors node consistency explores rich node representations in unlabeled data by aligning random neighbor nodes. To make full use of labeled information, class-centered consistency establishes relationships between labeled and unlabeled nodes, thus enabling unlabeled nodes to be better aware of class information. Finally, experiments are conducted on various real-world datasets, and the results show that SLCSL outperforms the current state-of-the-art methods.

关键词：

DiffusionAD: Norm-guided One-step Denoising Diffusion for Anomaly Detection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Hui Wang, Zheng Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of CS Fudan University China Shanghai Collaborative Innovation Center of Intelligent Visual Computing China School of Computer Science Zhejiang University of Technology China

Anomaly detection has garnered extensive applications in real industrial manufacturing due to its remarkable effectiveness and efficiency. However, previous generative-based models have been limited by suboptimal reconstruction quality, hampering their overall performance. We introduce DiffusionAD, a novel anomaly detection pipeline comprising a reconstruction sub-network and a segmentation sub-network. A fundamental enhancement lies in our reformulation of the reconstruction process using a diffusion model into a noise-to-norm paradigm. Here, anomalous regions are perturbed with Gaussian noise and reconstructed as normal, overcoming the limitations of previous models by facilitating anomaly-free restoration. Additionally, we propose a rapid one-step denoising paradigm, significantly faster than the traditional iterative denoising in diffusion models. Furthermore, the introduction of the norm-guided paradigm elevates the accuracy and fidelity of reconstructions. The segmentation sub-network predicts pixel-level anomaly scores using the input image and its anomaly-free restoration. Comprehensive evaluations on four standard and challenging benchmarks reveal that DiffusionAD outperforms current state-of-the-art approaches, demonstrating the effectiveness and broad applicability of the proposed pipeline. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection