检索结果-内蒙古大学图书馆

6th International Conference on Machine Learning for Cyber security, ML4CS 2024

作者： Xu, Haoyao Li, Yitong Tian, Haibo School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Province Key Laboratory of Information Security Technology Guangzhou510006 China

ISBN: (纸本)9789819645657

In recent years, Private information Retrieval (PIR) schemes capable of rapid response have gotten significant attention, with SimplePIR, for instance, achieving a throughput of approximately 10 GB/s in a single-threaded setting. However, these schemes often require users to download data related to the database, known as client hints, making them unsuitable for scenarios where the database undergoes frequent updates. This paper, building upon the Spiral scheme, incorporates the precomputation approach of SimplePIR to design a query method that leverages simulatable homomorphic ciphertexts for offline precomputation. This enhancement not only improves the efficiency of the Spiral scheme but also addresses the issue of SimplePIR’s necessity for downloading client hints. Experimental results demonstrate that, on a database with 220 entries of 256 bytes each, the proposed scheme achieves a throughput 1.87 times higher than that of the original Spiral scheme. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

DDoS Attack Detection Based on information Entropy Feature Extraction in Software Defined networks

DDoS Attack Detection Based on Information Entropy Feature E...

引用

2023 International Conference on networking and network Applications, NaNA 2023

作者： Ji, Wenjiang Yang, Yixin Zhang, Yaling Wang, Yichuan Tian, Mengjie Qiu, Yuan Xi'an University of Technology School of Computer Science and Engineering Xi'an China Shaanxi Key Laboratory for Network Computing and Security Technology China

ISBN: (纸本)9798350327380

Distributed Denial of Service(DDoS) attacks target the forwarding-control separation feature of Software-Defined networking(SDN) to launch attacks, causing network disruptions. Therefore security against DDoS attack detection for SDN controllers is the focus of current research. This paper proposes an Extreme Gradient Boosting (XGBoost) DDoS attack detection algorithm based on a combination of information gain and recursive feature elimination algorithms. We evaluated the performance of the method using the CICDDoS2019 dataset. This method works well in multi-classification model for attack detection with an accuracy of 93.41%. © 2023 IEEE.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

A divide-and-conquer reconstruction method for defending against adversarial example attacks

引用

Visual Intelligence 2024年第1期2卷 360-376页

作者： Xiyao Liu Jiaxin Hu Qingying Yang Ming Jiang Jianbiao He Hui Fang School of Computer Science and Engineering Central South UniversityChangsha410083HunanChina Guangxi Key Laboratory of Cryptography and Information Security School of Computer Science and Information SecurityGuilin University of Electronic TechnologyGuilinGuangxiChina Department of Computer Science Loughborough UniversityLoughboroughLE113TUUK

In recent years,defending against adversarial examples has gained significant importance,leading to a growing body of research in this *** these studies,pre-processing defense approaches have emerged as a prominent research ***,existing adversarial example pre-processing techniques often employ a single pre-processing model to counter different types of adversarial *** a strategy may miss the nuances between different types of attacks,limiting the comprehensiveness and effectiveness of the defense *** address this issue,we propose a divide-and-conquer reconstruction pre-processing algorithm via multi-classification and multi-network training to more effectively defend against different types of mainstream adversarial *** premise and challenge of the divide-and-conquer reconstruction defense is to distinguish between multiple types of adversarial *** method designs an adversarial attack classification module that exploits the high-frequency information differences between different types of adversarial examples for their multi-classification,which can hardly be achieved by existing adversarial example detection *** addition,we construct a divide-and-conquer reconstruction module that utilizes different trained image reconstruction models for each type of adversarial attack,ensuring optimal defense *** experiments show that our proposed divide-and-conquer defense algorithm exhibits superior performance compared to state-of-the-art pre-processing methods.

关键词： Adversarial example defense Divide-and-conquer strategy Adversarial attack multi-classification Reconstruction network

来源：评论

学校读者我要写书评

暂无评论

A Label Flipping Attack on Machine Learning Model and Its Defense Mechanism 22nd

A Label Flipping Attack on Machine Learning Model and Its De...

引用

22nd International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2022

作者： Li, Qingru Wang, Xinru Wang, Fangwei Wang, Changguang Key Laboratory of Network and Information Security of Hebei Province Hebei Normal University Shijiazhuang050024 China College of Computer and Cyberspace Security Hebei Normal University Shijiazhuang050024 China

ISBN: (纸本)9783031226762

Recently, the robustness of machine learning against data poisoning attacks is widely concerned. As a subclass of poisoning attack, the label flipping attack can poison training data resulting in reducing the classification performance of training model. This attack poses a more serious threat in complex network or high-noise environments, such as in the environment of Internet of Things. In this paper, a new label flipping attack method and its defense strategy are proposed. First, a label flipping attack based on agglomerative hierarchical clustering is proposed. The attack uses agglomerative hierarchical clustering to identify vulnerable samples in training data and then carries out label flipping on them. To defend against this attack, a TrAdaBoost-based label correction defense method is proposed. This method uses the TrAdaBoost algorithm to update the weight of the contaminated data, and then uses the updated weight value to judge and remark the contaminated training samples. The contaminated samples are cleaned and used to retrain the classifier. Compared with the state-of-the-art methods, the proposed attack strategy can reduce the accuracy of the model more effectively and the proposed defense method can better protect the classification model. © 2023, Springer Nature Switzerland AG.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Crop Classification Methods Based on Siamese CBMM-CNN Architectures Using Hyperspectral Remote Sensing Data 24th

Crop Classification Methods Based on Siamese CBMM-CNN Archi...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Xie, Bin Zhang, Jiahao Li, Yuling Li, Yusong Dong, Xinyu College of Computer and Cyber Security Hebei Normal University Hebei Shijiazhuang China Hebei Provincial Key Laboratory of Network and Information Security Hebei Normal University Hebei Shijiazhuang China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics and Data Security Hebei Normal University Hebei Shijiazhuang China

ISBN: (纸本)9789819615278

Amidst global population growth and escalating food demands, real-time agricultural monitoring is crucial for ensuring food security. During the initial stages of crop growth, however, it faces significant challenges in obtaining accurate ground truth data via remote sensing, thereby impeding effective crop classification. Traditional Convolutional Neural network (CNN) models, although effective in image processing and feature extraction within computer vision, are notably limited in their ability to handle the high dimensionality and complex spectral information inherent in hyperspectral non-image remote sensing data. To address this problem, we designed an enhanced CNN model, CBM-CNN. The CBM-CNN incorporates additional convolutional layers (C), batch normalization (B), and MLP(M) to convert one-dimensional data into two-dimensional data for classification, thus improving the processing efficiency of highly nonlinear data features. Building on CBM-CNN, we add multiple attention mechanisms (CBMM-CNN) to enhance feature extraction capabilities. The Siamese CBMM-CNN (SCBMM-CNN) is employed for in-depth learning of data features, with supervised learning precisely adjusting the model to improve classification performance. Experimental results on hyperspectral remote sensing datasets demonstrate that SCBMM-CNN outperforms traditional machine learning models (PCA-RF, GBDT, GMO-SVM, Random Forest, Decision Tree) and deep learning models (CNN, CNN-LSTM) in terms of accuracy, recall rate, F1 score, and kappa coefficient. These results confirm that SCBMM-CNN significantly improves crop classification accuracy and provides a novel method for early crop growth classification. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel On-Demand Service Architecture for Efficient Cloud-Edge Collaboration

A Novel On-Demand Service Architecture for Efficient Cloud-E...

引用

2023 International Conference on networking and network Applications, NaNA 2023

作者： Zhang, Yaling Chen, Jingjing Wang, Yichuan Xiao, Yeqiu Liu, Xiaoxue School of Computer Science and Engineering Xi'an University of Technology Xi'an China Shaanxi Key Laboratory for Network Computing and Security Technology China

ISBN: (纸本)9798350327380

With the advent of 5G era, the model of cloud-edge collaboration is used to handle massive data computing tasks with significant superiority. However, this architecture still uses the traditional web service model, which has problems such as single service and low resource utilization during the interaction between users and remote web servers. In this paper, we propose a novel on-demand service architecture that changes the traditional inefficient network service approach and skews the entire network service to the user. By fine- grained division of users' demands and hosting them in the corresponding functional servers for processing, the resolution of users' demands is no longer restricted by the services provided by the server, thus realizing 'information to people and services on demand'. Experiments show that the new on- demand service architecture reduces the latency by 33.3%, improves the quality and efficiency of information services, and realizes a more proactive and flexible information service model, which is more suitable for users' needs. © 2023 IEEE.

关键词： information services

来源：评论

学校读者我要写书评

暂无评论

Don’t Abandon the Primary key: A High-Synchronization and Robust Virtual Primary key Scheme for Watermarking Relational Databases 26th

Don’t Abandon the Primary Key: A High-Synchronization and...

引用

26th International Conference on information and Communications security, ICICS 2024

作者： Yang, Ke Yuan, Shuguang Yu, Jing Wang, Yuyang Yang, Tengfei Chen, Chi Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Cyberspace Security Defense Beijing China National Computer Network Emergency Response Technical Team/Coordination Center of China Beijing China

ISBN: (纸本)9789819788002

A relational database is an infrastructure that manages and shares structured data. To safeguard the copyrights of data within such databases, database watermarking is an effective technique. Most watermarking schemes rely on the primary key (PK) to locate and embed watermarks, which preserves high watermark synchronization during detection. However, these schemes become invalid once PK is erased or changed. To avoid this vulnerability, virtual primary key (VPK) schemes are proposed to replace PK. Nevertheless, duplicate values in virtual primary keys compromise synchronization. Besides, current VPK schemes fail to utilize the primary key, even when it remains unchanged. This strategy decreases detection accuracy in many cases. In addition, we find an attribute name attack. It is a common challenge of existing watermarking schemes, which distort the link between detected attributes and watermarked attributes. In this paper, we propose a high-synchronization and robust VPK scheme. It introduces a classifier to maintain the original order and number of attributes to resist attribute name attacks. To resist primary key erasure or change and mitigate synchronization problems, it generates distinct virtual primary keys. Moreover, to improve detection accuracy, our watermarking scheme integrates the primary key when it remains unchanged. Experiments demonstrate that our scheme achieves high watermark synchronization. It is robust against various attacks, even when 98% of tuples or over half of the attributes are distorted. It is also practical in terms of data distortion and overhead. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Relational databases Virtual primary key Watermarking

来源：评论

学校读者我要写书评

暂无评论

Post-quantum Dropout-Resilient Aggregation for Federated Learning via Lattice-Based PRF 1st

Post-quantum Dropout-Resilient Aggregation for Federated Le...

引用

1st International Conference on Artificial Intelligence security and Privacy, AIS and P 2023

作者： Zuo, Ruozhou Tian, Haibo Zhang, Fangguo School of Computer Science and Engineering Sun Yat-sen University Guangzhou510006 China Guangdong Key Laboratory of Information Security Technology Guangzhou510006 China

ISBN: (纸本)9789819997848

Machine learning has greatly improved the convenience of modern life. As the deployment scale of machine learning grows larger, the corresponding data scale also increases, leading to a large number of small and medium-sized organizations wishing to use their respective data to train models together, even though this may bring risks of violating data privacy regulations and privacy leakage. To meet this demand, federated learning was proposed, which can satisfy the needs of various organizations to expand the training data scale without directly sharing data, while avoiding violations of data privacy regulations and privacy leakage. General federated learning usually allows clients to train local models independently, and then aggregate them on a central server to build a global model in a privacy-preserving manner. There are various ways to protect privacy, such as homomorphic encryption, differential privacy, etc. Among these methods, one type of federated learning scheme is based on homomorphic pseudorandom functions. This type of scheme is relatively simple to construct, has a smaller communication scale, is more resilient to disconnections, and has high scalability. However, the security aggregation with cryptographic primitives based on classic assumptions such as DDH cannot resist quantum attacks, and since the protected gradient vectors are usually tens of thousands of dimensions, obtaining the aggregation results requires solving tens of thousands of discrete logarithms, which leads to some loss of efficiency. In this paper, we proposed a secure aggregation scheme based on HPRG over lattice, which has practical efficiency and resilience to dropout and can resist quantum attacks due to the hardness of the RLWE assumption. Moreover, our scheme only requires polynomial multiplication and addition (usually treated as vectors in implements), thus significantly improving computational efficiency. © The Author(s), under exclusive license to Springer Nature Singapo

关键词： Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Some Classes of Cryptographic Power Functions and Permutation Polynomials with Low (-1)-Differential Uniformity in Cyber security

Some Classes of Cryptographic Power Functions and Permutatio...

引用

2023 IEEE International Conference on Dependable, Autonomic and Secure Computing, 2023 International Conference on Pervasive Intelligence and Computing, 2023 International Conference on Cloud and Big Data Computing, 2023 International Conference on Cyber Science and Technology Congress, DASC/PiCom/CBDCom/CyberSciTech 2023

作者： Liu, Qian Dong, Xiaobei Chen, Zhixiong Liu, Ximeng Xu, Li College of Computer and Data Science Fuzhou University Fuzhou China Putian University Fujian Key Laboratory of Financial Information Processing Putian China College of Computer and Data Science Fuzhou University Key Laboratory of Information Security of Network Systems Fuzhou China College of Computer and Cyber Security Fujian Normal University Fuzhou China

ISBN: (纸本)9798350304602

Cryptographic functions with low differential uniformity have wide applications in cryptography and cyber security. In this paper, we further investigate c-differential uniformity proposed by Ellingsen et al. (IEEE Transactions on information Theory. 2020, 66(9): 5781-5789). Specifically, two classes of power functions with low (1)-differential uniformity over finite fields with odd characteristic are obtained. In addition, a class of permutation polynomials and P1N or AP1N functions over F3n are proposed. These functions with low c-differential uniformity are utilized to resist against c-differential attacks in cyberspace from those with the usual low differential uniformity. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Automated object recognition in high-resolution optical remote sensing imagery

引用

National Science Review 2023年第6期10卷 38-41页

作者： Yazhou Yao Tao Chen Hanbo Bi Xinhao Cai Gensheng Pei Guoye Yang Zhiyuan Yan Xian Sun Xing Xu Hai Zhang School of Computer Science and Engineering Nanjing University of Science and Technology Aerospace Information Research Institute Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Key Laboratory of Network Information System Technology (NIST) Aerospace Information Research Institute Chinese Academy of Sciences Department of Computer Science and Technology Tsinghua University School of Computer Science and Engineering University of Electronic Science and Technology of China Pazhou Laboratory (Huangpu) School of Mathematics Northwest University

INTRODUCTION With the rapid development of remote sensing technology,high-quality remote sensing images have become widely *** automated object detection and recognition of these images,which aims to automatically locate objects of interest in remote sensing images and distinguish their specific categories,is an important fundamental task in the *** provides an effective means for geospatial object monitoring in many social applications,such as intelligent transportation,urban planning,environmental monitoring and homeland security.

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：