检索结果-内蒙古大学图书馆

Imperceptible and Reliable Adversarial Attack 1

4th International Conference on Frontiers in Cyber Security, FCS 2021

作者： Zhang, Jiawei Wang, Jinwei Luo, Xiangyang Ma, Bin Xiong, Naixue School of Computer and Software Engineering Research Center of Digital Forensics Ministry of Education Nanjing University of Information Science and Technology Nanjing210044 China State Key Laboratory of Mathematical Engineering and Advanced Computing Zhenzhou450001 China Shandong Provincial Key Laboratory of Computer Networks and Qilu University of Technology Jinan250353 China Department of Computer Science and Mathematics Sul Ross State University AlpineTX79830 United States

ISBN: (数字)9789811905230

ISBN: (纸本)9789811905223

Deep neural networks are vulnerable to adversarial examples, which can fool classifiers by adding small perturbations. Various adversarial attack methods have been proposed in the past several years, and most of them add the perturbation in a "sparse" or "global" way. Since the number of pixels perturbed by the "sparse" method and the perturbation intensity of each pixel added by the "global" method are both small, the adversarial property can be destroyed easily. Finally, it makes the adversarial attack and the adversarial training based on these samples unreliable. To address this issue, we present an "pixel-wise" method which is somewhere in between the "sparse" or "global" way. First, the perception of human eyes to the error of different image regions is different. Second, image processing methods have different effects on the different areas of the image. Based on these two considerations, we propose an imperceptible and reliable adversarial attack method, which projects the perturbation to the different areas differently. Extensive experiments demonstrate our method can preserve the attack ability while maintaining good view quality. More importantly, the proposed projection can be combined with existing attack methods to generate a stronger generation algorithm which improves the robustness of adversarial examples. Based on the proposed method, the reliability of adversarial attacks can be greatly improved. © 2022, Springer Nature Singapore Pte Ltd.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

A Time-Aware Generative Network for Enhancing Transaction Security in Consumer Electronics

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xie, Yu Hong, Yang Qiao, Sibo Yao, Jiamin Liu, Guanjun Pang, Shanchen Shanghai Maritime University College of Information Engineering Shanghai201306 China Shanghai Maritime University School of Economics and Management Shanghai201306 China Tiangong University School of Software Tianjin300387 China Tongji University Department of Computer Science Shanghai201804 China College of Computer Science and Technology Qingdao266580 China

As consumer electronics increasingly rely on secure digital transactions, ensuring transaction security remains a formidable challenge, largely due to the severe class imbalance between legitimate and fraudulent transactions. Although existing methods attempt to mitigate this imbalance, their effectiveness is often compromised by the sophisticated concealment strategies employed by fraudsters, which lead to significant behavioral overlap between legitimate and fraudulent transactions. In this paper, we propose a novel Time-aware Generative Network (TaGN) that combines a Density-based Wasserstein Generative Adversarial Network (DWGAN) with a Time-aware Gated Recurrent Network (TaGRN) to enhance fraud detection in consumer electronics. The DWGAN penalizes synthetic samples that closely resemble legitimate transactions, focusing the generator on fraudulent characteristics and reducing the impact of behavioral overlap. The TaGRN leverages temporal and contextual transactional information through a gated recurrent structure, transforming original transaction features into new representations that effectively distinguish behavior patterns in overlapping regions. Extensive experiments conducted on real-world and public datasets demonstrate that TaGN significantly outperforms its competitive peers, offering a robust and effective framework for enhancing transaction security in consumer electronics. © 1975-2011 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Adaptive Memory Management for Video Object Segmentation

arXiv

引用

arXiv 2022年

作者： Pourganjalikhan, Ali Poullis, Charalambos Immersive and Creative Technologies Lab Department of Computer Science and Software Engineering Concordia University Montreal Canada

Matching-based networks have achieved state-of-the-art performance for video object segmentation (VOS) tasks by storing every-k frames in an external memory bank for future inference. Storing the intermediate frames’ predictions provides the network with richer cues for segmenting an object in the current frame. However, the size of the memory bank gradually increases with the length of the video, which slows down inference speed and makes it impractical to handle arbitrary length videos. This paper proposes an adaptive memory bank strategy for matching-based networks for semi-supervised video object segmentation (VOS) that can handle videos of arbitrary length by discarding obsolete features. Features are indexed based on their importance in the segmentation of the objects in previous frames. Based on the index, we discard unimportant features to accommodate new features. We present our experiments on DAVIS 2016, DAVIS 2017, and Youtube-VOS that demonstrate that our method outperforms state-of-the-art that employ first-and-latest strategy with fixed-sized memory banks and achieves comparable performance to the every-k strategy with increasing-sized memory banks. Furthermore, experiments show that our method increases inference speed by up to 80% over the every-k and 35% over first-and-latest strategies. Copyright © 2022, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Early Fault Detection in Rolling Element Bearings Using Signal Processing Techniques

Early Fault Detection in Rolling Element Bearings Using Sign...

引用

International Symposium on High Capacity Optical Networks and Enabling Technologies, HONET

作者： Ali Saeed M. Usman Akram Muazzam A. Khan M. Belal Afsar Department of Computer Science ICESCO Chair Big Data Analytics and Edge Computing Quaid-i-Azam University Islamabad Pakistan Department of Computer and Software Engineering National University of Sciences & Technology Islamabad Pakistan Faculty of Electrical Engineering and Information Technology Otto-von-Guericke University Maddeburg DE

ISBN: (数字)9798350378078

ISBN: (纸本)9798350378085

Many studies show that bearings are the most vulnerable components in low-voltage motors. While advanced bearing diagnostic systems exist, their cost can be a barrier for non-critical machinery due to the potential wait time to see a return on investment. This research explores the feasibility of using basic signal processing techniques on vibration data for bearing condition monitoring. The primary goal is to analyze benchmark data from the Case Western Reserve University (CWRU) dataset and establish a baseline performance for this data-driven approach. The results suggest that, with appropriate signal processing, it's possible to achieve early detection of bearing faults, leading to more efficient time-to-fault identification with higher detection accuracies ranging from 83 % to 100 % for each method.

关键词： Vibrations Fault diagnosis Low voltage Smart cities Rolling bearings Signal processing Motors Robots Monitoring Investment

来源：评论

学校读者我要写书评

暂无评论

Multiple Feature Selection Frameworks Based on Evolutionary Computing and Ensemble Learning for software Defect Prediction

Multiple Feature Selection Frameworks Based on Evolutionary ...

引用

International Conference on Computational Intelligence and Networks (CINE)

作者： Ruchika Malhotra Anmol Budhiraja Abhinav Kumar Singh Ishani Ghoshal Shweta Meena Department of Software Engineering Delhi Technological University Delhi India Department of Computer Science and Engineering Delhi Technological University Delhi India

ISBN: (纸本)9781665464666

software defects may cause severe crashes in the system, leading to the software's high maintenance costs. Early identification of these defects would lead to high-quality software, thus saving time and money. This study proposes five feature selection approaches based on evolutionary computing algorithms, each coupled with a majority voting ensemble for software defect prediction. The objective is to improve the existing process by targeting the metric selection stage. The study was conducted on thirty open-source defect datasets. The proposed feature selection techniques were applied on a within-project defect prediction model and a heterogeneous defect prediction model. The Friedman and the Wilcoxon Signed-rank test concluded that the proposed techniques were promising and generated results comparable to some other state-of-the-art feature selection methodologies.

关键词： Measurement Statistical analysis Computational modeling software algorithms Evolutionary computation Predictive models Maintenance engineering

来源：评论

学校读者我要写书评

暂无评论

Deep Hierarchy Quantization Compression algorithm based on Dynamic Sampling

arXiv

引用

arXiv 2022年

作者： Jiang, Wan Liu, Gang Chen, Xiaofeng Zhou, Yipeng College of Computer Science and Software Engineering ShenZhen University China Department of Computing Macquarie University Australia

Unlike traditional distributed machine learning, federated learning stores data locally for training and then aggregates the models on the server, which solves the data security problem that may arise in traditional distributed machine learning. However, during the training process, the transmission of model parameters can impose a significant load on the network bandwidth. It has been pointed out that the vast majority of model parameters are redundant during model parameter transmission. In this paper, we explore the data distribution law of selected partial model parameters on this basis, and propose a deep hierarchical quantization compression algorithm, which further compresses the model and reduces the network load brought by data transmission through the hierarchical quantization of model parameters. And we adopt a dynamic sampling strategy for the selection of clients to accelerate the convergence of the model. Experimental results on different public datasets demonstrate the effectiveness of our algorithm. Copyright © 2022, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Radiology Report Generation via Structured Knowledge-Enhanced Multi-modal Attention and Contrastive Learning

Radiology Report Generation via Structured Knowledge-Enhance...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Dexuan Xu Yanyuan Chen Jiayu Zhang Yiwei Lou Hanpin Wang Jing He Yu Huang National Engineering Research Center for S.E. School of Software & Micro. Peking University China School of Computer Science Peking University China Key Laboratory of High Confidece Software Technologies (MOE) School of Computer Science Peking University China Department of Rheumatology and Immunology Peking University People’s Hospital China National Engineering Research Center for Software Engineering Peking University China

The automated generation of radiology reports has attracted significant attention in the field of bioinformatics. Currently, the main limitations of this task include insufficient utilization of prior medical knowledge, lack of efficient knowledge fusion algorithms, and less distinctiveness between different generated reports. To address these issues, we propose a novel algorithm for radiology report generation, which includes Structured Knowledge-Enhanced Multi-modal Attention (SKEMA) and Dual-Branch Contrastive Learning (DBCL) for the first time. SKEMA aims to effectively bridge the gap between visual and prior knowledge by leveraging the high-order adjacency matrix of the knowledge graph to weightedly fuse image features and knowledge features. We enhance both features through masking, and use the original features and augmented features as positive and negative samples in the dual-branch contrastive learning (DBCL). DBCL increases the differences between positive and negative samples to avoid generating templated results, and enhances the robustness of the model. Finally, we conducted experiments to demonstrate the effectiveness of our model on two public radiology datasets, IU-Xray and MIMIC-CXR. Our model outperformed previous baseline methods on both datasets and achieved excellent evaluation scores.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Decentralized Property Registration and Management Platform

Decentralized Property Registration and Management Platform

引用

Advancements in Computing (ICAC), International Conference on

作者： R. M Yasas M. H. M. N. D. Bandara T. Praveena K. Abeywardena D. Kasthurirathna Department of Computer Science & Software Engineering Sri Lanka Institute of Information Technology Malabe Sri Lanka

ISBN: (纸本)9798350398106

The existing property registry management does not have a well-defined protocol for verifying and validating transactions that occur within the domain. These transactions rely on handwritten signatures, an unreliable methodology for determining an asset’s ownership. The legal system governs this process. However, several disputes have occurred due to improper validation and verification when registering properties, changing custody, and maintaining the chain of ownership. Trades have been made by including a lower value than the actual asset value, which will reduce the tax owed to the government and will lead to the failure of these departments. There are no appropriate mechanisms to resolve common disputes that arise within the domain. The courts must resolve these disputes using the same recurring traditional procedure, which will take years or decades to conclude. The main objective of this research is to develop a secure property registration mechanism by creating a digital protocol using a decentralized blockchain network. In addition, the research will focus on developing a minimum asset value calculator using machine learning and geographic information system, verifying the authenticity of the generated digital documents, and creating digital deeds for new and old paper-based records.

关键词： Protocols Calculators Law Government Finance Machine learning Blockchains

来源：评论

学校读者我要写书评

暂无评论

Combinatorial optimization and reasoning with graph neural networks

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2023年第1期24卷 5922-5982页

作者： Quentin Cappart Didier Chételat Elias B. Khalil Andrea Lodi Christopher Morris Petar Veličković Department of Computer Engineering and Software Engineering Polytechnique Montréal Montréal Canada CERC in Data Science for Real-Time Decision-Making Polytechnique Montréal Montréal Canada Department of Mechanical & Industrial Engineering University of Toronto Toronto Canada Jacobs Technion-Cornell Institute Cornell Tech and Technion - IIT New York Department of Computer Science RWTH Aachen University Aachen Germany DeepMind London UK

Combinatorial optimization is a well-established area in operations research and computer science. Until recently, its methods have focused on solving problem instances in isolation, ignoring that they often stem from related data distributions in practice. However, recent years have seen a surge of interest in using machine learning, especially graph neural networks (GNNs), as a key building block for combinatorial tasks, either directly as solvers or by enhancing exact solvers. The inductive bias of GNNs effectively encodes combinatorial and relational input due to their invariance to permutations and awareness of input sparsity. This paper presents a conceptual review of recent key advancements in this emerging field, aiming at optimization and machine learning researchers.

关键词： combinatorial optimization graph neural networks reasoning

来源：评论

学校读者我要写书评

暂无评论

Detection and Replay of Distributed Denial of Service Attacks In Smart Cities Using a Hybrid Deep Learning Approach

Detection and Replay of Distributed Denial of Service Attack...

引用

Business Analytics for Technology and Security (ICBATS), International Conference on

作者： Muhammad Waseem Iqbal Ghassan F. Issa Muhammad Yousif Muhammad Atif Department of Software Engineering Superior University Lahore Pakistan School of Information Technology Skyline University College Sharjah UAE Department of Computer Science NCBAE Lahore. Pakistan Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science NCBAE Lahore Pakistan

Infrastructure for smart cities is presently being built, mostly because of the (IoT) platform, which connects a wide variety of things by using the website's underlying infrastructure. As a result, it is possible to employ a uniform platform to automate the services that are delivered. Smart city infrastructure, on the other hand, is susceptible to cyberattacks owing to security flaws in IoT networks. Distributing denial of service (DDoS) and replay assaults, for example, violate the requirements for certification in smart cities. The lack of citations in this part backs up many of the statements it makes. Who needs a citation? Both assaults have the potential to substantially damage smart city infrastructure, which might also cost money and even result in human fatalities. This paper covers the creation of a blended deep- learning algorithm for replay and DDoS intrusion prevention on a growth-oriented smart city platform. This is made possible by combining proven machine-learning approaches with more recent advances in artificial intelligence. We simulate scattered denial of service and replay attacks on three datasets acquired from real-world smart cities to assess the efficacy of the proposed hybrid strategy on environmental, smart river, and smart soil dataset. The suggested model has shown excellent rates of accuracy. The ecosystem collection has an accuracy level of 98.37%, the smart riverbed dataset must have an accuracy of 98.13%, and the smart mud dataset must have an accuracy of 99.51%. The findings demonstrated that the proposed model outperformed past instances of evolutionary computation and machine learning techniques employed in the corpus of academic literature.

关键词： Analytical models Machine learning algorithms Smart cities Computational modeling Soil Probability distribution Real-time systems

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：