检索结果-内蒙古大学图书馆

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

IEEE Transactions on Dependable and Secure computing 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong The School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China The School of Computing Kent Interdisciplinary Research Centre in Cyber Security University of Kent CanterburyCT2 7NF United Kingdom Shenzhen Institute of Advanced Technology Chinese Academy of Sciences China The Intelligent Transportation Systems Lab Innopolis University Innopolis Russia The School of Computer Science and Technology Xidian University China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. © 2004-2012 IEEE. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SAM-PS: Zero-shot Parking-slot Detection based on Large Visual Model

SAM-PS: Zero-shot Parking-slot Detection based on Large Visu...

引用

IEEE Symposium on intelligent Vehicle

作者： Heng Zhai Jilin Mei Liang Chen Fangzhou Zhao Xijun Zhao Yu Hu Research Center for Intelligent Computing Systems Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Information Science and Technology ShanghaiTech University Shanghai China Shanghai Innovation Center for Processor Technologies(SHIC) China North Artificial Intelligence & Innovation Research Institute Collective Intelligence & Collaboration Laboratory (CIC) School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

Large visual models have recently demonstrated their promising performance on zero-shot transfer. However, so far, none of the existing methods explicitly possess the ability to perform zero-shot transfer on parking-slot detection, which results in current deep-learning based methods relying on training datasets, and methods based on traditional computer vision exhibiting poor robustness. In this paper, we propose a large visual model-based parking-slot detection method, which utilizes a large visual model (segment anything) to segment an around-view image and infer parking-slots by analyzing the relationship of marking-points in masks. In addition, we classify real-world parking-slots into two categories, line-based and area-based. The proposed method employs a two-stage approach which has a manually designed post-processing step without training. Multiple experiments have been carried out on public benchmarks, and our method demonstrates the capability for zero-shot transfer. The code will be released at https://***/Zhai0123/SAM-PS.

关键词： Training Learning systems Visualization Image segmentation Analytical models intelligent vehicles Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Cloud Server-Aided Unbalanced Private Set Intersection Cardinality Protocol

引用

International Journal of Network Security 2024年第6期26卷 1044-1052页

作者： Li, Yunyun Liu, Momeng Zhang, Yingbo Shaanxi Key Laboratory of Clothing Intelligence State and Local Joint Engineering Research Center for Advanced Networking and Intelligent Information Services School of Computer Science Xi’an Polytechnic University No. 58 Shan-gu Road Lintong Xi’an710600 China

In the case of a large-scale outbreak of infectious diseases such as COVID-19, in order to curb the spread of the virus while not revealing personal privacy, privacy contact tracing is used to track and notify people who have come into contact with infected users. Fortunately, private set intersection cardinality (PSI-CA) can determine whether there is an intersection with infected users without revealing any user information. In this paper, we use a cloud server and permute+share to address the low communication efficiency and user privacy leakage in the process of contact tracing. The cloud server’s powerful computing and storage capabilities can be used to enhance data processing efficiency during the tracing process. Additionally, by using permute+share to process sensitive data, users can only access the replaced data, protecting their privacy from leakage. Finally, we conduct comparative experiments to demonstrate that our solution outperforms existing approaches in terms of both security and performance. © (2024), (International Journal of Network Security). All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

FedCST: Federated Learning on Heterogeneous Resource-constrained Devices Using Clustering and Split Training

FedCST: Federated Learning on Heterogeneous Resource-constra...

引用

IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C)

作者： Zhilu Wang Haiyang Lin Qi Liu Yonghong Zhang Xiaodong Liu Nanjing University of Information Science and Technology School of Computer Science Nanjing Jiangsu China Nanjing University of Information Science and Technology School of Software Nanjing Jiangsu China Jiangsu Province Engineering Research Center of Advanced Computing and Intelligent Services Nanjing Jiangsu China Nanjing University of Information Science and Technology School of Automation Nanjing Jiangsu China Edinburgh Napier University School of Computing Edinburgh UK

ISBN: (数字)9798350365658

ISBN: (纸本)9798350365665

With the rapid development of 5G and Internet of Things (IoT) technologies, edge devices such as sensors, smartphones, and wearable devices have become increasingly prevalent. The massive amount of distributed data generated by these devices offers unprecedented opportunities for deep learning, especially in fields like computer vision and edge computing. However, this data often exists in isolated data silos, and due to its privacy-sensitive nature, it cannot be directly processed in a centralized manner. Additionally, the data heterogeneity and devices heterogeneity further exacer-bates the challenges in federated learning (FL). Moreover, with the implementation of data privacy protection regulations, user demand for privacy protection is growing significantly. Therefore, how to effectively utilize dispersed data for distributed collaborative learning while ensuring data privacy is a pressing issue that needs to be addressed in the field of FL. In response to these challenges, this work has conducted research on clustering and segmentation FL algorithms for heterogeneous resource-constrained devices. A lightweight homogeneous device clustering strategy has been designed, which incorporates a split learning (SL) mechanism to enhance the accuracy and training efficiency of FL models. This approach reduces the load on resource-constrained devices and improves privacy security. Consequently, this method can meet the dual requirements of privacy protection and computational efficiency in real-world scenarios.

关键词： Training Data privacy Privacy Federated learning Computational modeling Distributed databases Security Internet of Things Protection Edge computing

来源：评论

学校读者我要写书评

暂无评论

Estimation of load factors of trains using multi-source data for complex metro systems 7

Estimation of load factors of trains using multi-source data...

引用

7th International Conference on Big Data computing and Communications, BigCom 2021

作者： Wu, Hexiang Liu, Tong Li, Chengfan Tong, Weiqin Feng, Zhenni Zhao, Shimin Shanghai University School of Computer Engineering and Science China Shanghai Engineering Research Center of Intelligent Computing System China Donghua University School of Computer Science and Technology China Shanghai Shentong Metro Co. Ltd. China

ISBN: (纸本)9781665442527

Metro systems play a significant role of urban transportation in large cities. It is critical for metro system managers to understand load factors of trains. Although the wide deployment of automated fare collection (AFC) system brings us a lot of convenience, only the information likes tap-in and tap-out time stamp and stations of each trip can be directly obtained from AFC records, the train and the route chosen by the passengers are uncertain. The information is necessary for achieving the load factors of trains. Considering that AFC records contain the no-transfer trips, one-transfer trips and multi-transfer trips, the problem becomes particularly complicated. Benefiting from machine learning, we propose an effective data-mining method to better understand the train and route chosen by a passenger with considering the impacts of time and space. We also classify passengers based on the similarity of passenger travel characteristics, which can automatically select the initial cluster centres in data. We validate our approach using a large-scale dataset collected from the Shanghai Metro system, and results demonstrate that our approach works effectively. © 2021 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Admission Control with Latency Considerations for 5G Mobile Edge computing

Admission Control with Latency Considerations for 5G Mobile ...

引用

IEEE International Symposium on World of Wireless Mobile and Multimedia Networks (WoWMoM)

作者： Ye Zhang Wuyungerile Li Winston K.G. Seah Inner Mongolia Key Lab. of Wireless Networking & Mobile Computing Engineering Research Center of Ecological Big Data Ministry of Education School of Computer Science Inner Mongolia University Hohhot China Wireless Networks Research Group School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand

The fifth generation (5G) mobile network is a new generation of broadband mobile communication technology with the potential to address the increasing demands of new user services and applications that have stringent low latency and high bandwidth requirements. Besides the enhanced mobile broadband (eMBB) which is an evolution of broadband services from previous generations, the ultra reliable low latency communication (URLLC) service comes with stringent delay requirements that are needed to support new applications like autonomous vehicles, augmented/virtual reality, etc. Mobile or multiple access edge computing (MEC) emerged to provide services and computing resources for users at the network edge to provide faster access speeds and lower end-to-end delays. To better meet user needs and maximize resource utilization, network resources need to be allocated and managed efficiently. Admission control for user requests is one of the methods used that can effectively prevent network congestion, thereby improving the overall performance of the system. In this paper, we propose a RED-based Admission Control with Latency Considerations (REDAL) algorithm for user admission control that aims to increase throughput, meet users’ delay requirements and reduce packet discard rate. By explicitly accounting for user traffic delay constraints and bandwidth requirements, we are able to meet the strict delay constraints of URLLC traffic while meeting the bandwidth requirements of eMBB traffic. We validate our approach in an MEC scenario to demonstrate high resource utilization and also keeping the request discard rate below 20%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Auto-MatRegressor材料性能自动预测器:解放材料机器学习"调参师"

引用

science Bulletin 2023年第12期68卷 1259-1270,M0004页

作者：刘悦王双燕杨正伟 Maxim Avdeev 施思齐 School of Computer Engineering and Science Shanghai UniversityShanghai 200444China Shanghai Engineering Research Center of Intelligent Computing System Shanghai 200444China State Key Laboratory of Advanced Special Steel School of Materials Science and EngineeringShanghai UniversityShanghai 200444China Materials Genome Institute Shanghai UniversityShanghai 200444China Zhejiang Laboratory Hangzhou 311100China Australian Nuclear Science and Technology Organisation Sydney 2232Australia School of Chemistry The University of SydneySydney 2006Australia

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材... 详细信息

机器学习因其能够快速、精准拟合数据的潜在模式而被广泛应用于材料构效关系研究。然而,材料科学家往往需要进行繁琐的模型选择及参数寻优才能构建出高精度预测模型,为了解放材料机器学习"调参师",本文研发了基于元学习的材料性能自动预测器,采集了60份文献公开数据集与60份标准数据集,基于此训练18种常用回归算法并获得其预测性能,定义与计算了27个刻画数据集特点的元特征,以此构建了一份蕴含建模经验的元数据集;同时,创建了表征数据集所属材料类型的类别树,将其嵌入基于距离的元学习算法,进一步耦合贝叶斯优化算法,实现领域知识和元数据协同驱动下的自动算法推荐和模型参数确定,实验结果表明,材料科学家仅需为新材料性能预测任务提供数据集,便可利用该预测器高效地构建具有与文献报道相当或更高预测精度的机器学习模型.

关键词：机器学习贝叶斯优化算法预测器材料科学家元数据参数寻优预测性能材料性能

来源：评论

学校读者我要写书评

暂无评论

Mirror Contrastive Loss Based Sliding Window Transformer for Subject-Independent Motor Imagery Based EEG Signal Recognition 4th

Mirror Contrastive Loss Based Sliding Window Transformer for...

引用

4th International Workshop on Human Brain and Artificial Intelligence, HBAI 2024

作者： Luo, Jing Mao, Qi Shi, Weiwei Shi, Zhenghao Wang, Xiaofan Lu, Xiaofeng Hei, Xinhong Shaanxi Key Laboratory for Network Computing and Security Technology and Human–Machine Integration Intelligent Robot Shaanxi University Engineering Research Center School of Computer Science and Engineering Xi’an University of Technology Shaanxi Xi’an China

ISBN: (纸本)9789819640003

While deep learning models have been extensively utilized in motor imagery based EEG signal recognition, they often operate as black boxes. Motivated by neurological findings indicating that the mental imagery of left or right-hand movement induces event-related desynchronization (ERD) in the contralateral sensorimotor area of the brain, we propose a Mirror Contrastive Loss based Sliding Window Transformer (MCL-SWT) to enhance subject-independent motor imagery-based EEG signal recognition. Specifically, our proposed mirror contrastive loss enhances sensitivity to the spatial location of ERD by contrasting the original EEG signals with their mirror counterparts—mirror EEG signals generated by interchanging the channels of the left and right hemispheres of the EEG signals. Moreover, we introduce a temporal sliding window transformer that computes self-attention scores from high temporal resolution features, thereby improving model performance with manageable computational complexity. We evaluate the performance of MCL-SWT on subject-independent motor imagery EEG signal recognition tasks, and our experimental results demonstrate that MCL-SWT achieved accuracies of 66.48% and 75.62%, surpassing the state-of-the-art (SOTA) model by 2.82% and 2.17%, respectively. Furthermore, ablation experiments confirm the effectiveness of the proposed mirror contrastive loss. A code demo of MCL-SWT is available at https://***/roniusLuo/MCL_SWT. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

LinNet: linear network for efficient point cloud representation learning 24

LinNet: linear network for efficient point cloud representat...

引用

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

作者： Hao Deng Kunlei Jing Shengmei Cheng Cheng Liu Jiawei Ru Jiang Bo Lin Wang State-Province Joint Engineering and Research Center of Advanced Networking and Intelligent Information Services School of Information Science and Technology Northwest University and Shaanxi Key Laboratory of Higher Education Institution of Generative Artificial Intelligence and Mixed Reality School of Software Engineering Xi'an Jiaotong University and Department of Computing The Hong Kong Polytechnic University

ISBN: (纸本)9798331314385

Point-based methods have made significant progress, but improving their scalability in large-scale 3D scenes is still a challenging problem. In this paper, we delve into the point-based method and develop a simpler, faster, stronger variant model, dubbed as LinNet. In particular, we first propose the disassembled set abstraction (DSA) module, which is more effective than the previous version of set abstraction. It achieves more efficient local aggregation by leveraging spatial anisotropy and channel anisotropy separately. Additionally, by mapping 3D point clouds onto 1D space-filling curves, we enable parallelization of down-sampling and neighborhood queries on GPUs with linear complexity. LinNet, as a purely point-based method, outperforms most previous methods in both indoor and outdoor scenes without any extra attention, and sparse convolution but merely relying on a simple MLP. It achieves the mIoU of 73.7%, 81.4%, and 69.1% on the S3DIS Area5, NuScenes, and SemanticKITTI validation benchmarks, respectively, while speeding up almost 10x times over PointNeXt. Our work further reveals both the efficacy and efficiency potential of the vanilla point-based models in large-scale representation learning. Our code will be available at https://***/DengH293/LinNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Object Detection Based on Dynamic Semantic Vectors

Zero-shot Object Detection Based on Dynamic Semantic Vectors

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Haoyu Li Jilin Mei Jiancong Zhou Yu Hu Research Center for Advanced Computing Systems Zhejiang Laboratory Hangzhou China UCAS Hangzhou Institute for Advanced Study Hangzhou China Research Center for Intelligent Computing Systems Chinese Academy of Sciences Institute of Computing Technology Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Zero-shot object detection has shown its ability to overcome the problems of data scarcity and novel classes. Existing methods generally utilize static semantic vectors to classify objects and guide the network to map visual features to semantic vectors. However, the distribution of semantic vectors cannot adequately represent visual features, which makes migration from seen to unseen classes difficult. This work explores the dynamic semantic vector method to align the distributions of semantic vectors and visual features. The main challenge is to get a more reasonable distribution of semantic vectors. To address this issue, we proposed a two-way classification branch network and introduce N-pair loss into the dynamic semantic vector optimization process. Experiments on the MS-COCO dataset and SiTi (a real-world autonomous driving dataset collected by us) demonstrate the effectiveness and generalization of our method. Our code is available at https://***/HaoyuLizju/ZSD_tcb

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：