检索结果-内蒙古大学图书馆

Multi-party privacy-preserving decision tree training with a privileged party

Science China(Information Sciences) 2024年第8期67卷 253-268页

作者： Yiwen TONG Qi FENG Min LUO Debiao HE Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology(Shandong Academy of Sciences)

Currently, a decision tree is the most commonly used data mining algorithm for classification tasks. While a significant number of studies have investigated privacy-preserving decision trees, the methods proposed in these studies often have shortcomings in terms of data privacy breach or efficiency. Additionally,these methods typically only apply to symmetric frameworks, which consist of two or more parties with equal privilege, and are not suitable for asymmetric scenarios where parties have unequal privilege. In this paper,we propose SecureCART, a three-party privacy-preserving decision tree training scheme with a privileged party. We adopt the existing pMPL framework and design novel secure interactive protocols for division,comparison, and asymmetric multiplication. Compared to similar schemes, our division protocol is 93.5–560.4× faster, with the communication overhead reduced by over 90%; further, our multiplication protocol is approximately 1.5× faster, with the communication overhead reduced by around 20%. Our comparison protocol based on function secret sharing maintains good performance when adapted to pMPL. Based on the proposed secure protocols, we implement SecureCART in C++ and analyze its performance using three real-world datasets in both LAN and WAN environments. he experimental results indicate that SecureCART is significantly faster than similar schemes proposed in past studies, and that the loss of accuracy while using SecureCART remains within an acceptable range.

关键词： privacy protection decision trees secure multi-party computation secret sharing privileged party

来源：评论

学校读者我要写书评

暂无评论

A Novel Machine Learning-Based Framework for Predicting Diabetes in Healthcare

A Novel Machine Learning-Based Framework for Predicting Diab...

引用

2025 International Conference on Intelligent Control, Computing and Communications, IC3 2025

作者： Oliver, A. Sheryl Gupta, Kimmi Singh, Jagendra Agnihotri, Atul Kumar Vasavi, M. Kaur, Gaganjot Srm Institute of Science and Technology Department of Computational Intelligence Chennai India School of Computer Science Engineering & Technology Bennett University Greater Noida India School of Engineering and Technology Chhatrapati Shahu Ji Maharaj University Electronics and Communication Engineering Kanpur India Cvr College of Engineering Department of Et -Cyber Security Hyderabad India Raj Kumar Goel Institute of Technology Department of Computer Science Ghaziabad India

ISBN: (纸本)9798331527495

The rise in diabetes is considered the greatest global health issue;thus, the call for early and accurate predictions of the disease is a dire need in the health sector. The detection of the disease in its initial stages would allow patients to undergo timely interventions and appropriate treatments. A novel approach for the prediction of stages and severity of diabetes by utilizing various models within a machine learning framework, such as Support Vector Machine (SVM), Artificial Neural Network (ANN), Decision tree learning (DT), and Random Forest (RF) is proposed in this paper. The training data would involve the history of medical conditions, age, BMI, insulin, skin thickness, glucose level, the number of pregnancies, and existence or non-existence of diabetes. The models were trained on 70% of the data and tested on the remaining 30%. The results show that SVM outperforms all other models, achieving an accuracy of 96.5%, followed by ANN with 94.5%, DT with 90.2 %, and RF with 86.7%. These results indicate that SVM, followed by ANN, is the most effective model for predicting diabetes stages. The accuracy and reduction of data loss have been constant improvements with epochs 30 to 360;therefore, models can be used in real-time applications in the clinical area. Thus, this research concludes that machine learning models, such as SVM, may be helpful in predicting and diagnosing early cases of diabetes;thus, these models could be helpful in making good decisions on healthcare and improving the patient's health. © 2025 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Comparative Evaluation of Deep Learning Models in Alzheimer’s Disease Diagnosis

引用

Procedia computer Science 2025年 258卷 2352-2361页

作者： Leena Arya Yogesh Kumar Sharma Smitha Nayak Janaki Sivakumar Assistant Professor Computing Department Muscat College Oman Associate Professor Programme leader Computer security and forensics Department of Computer Science and Creative Technologies Global College of Engineering and Technology Muscat Oman

Alzheimer’s Disease (AD) is an ever-evolving neurodegenerative confusion that influences the neurons of the mind in a manner that hinders the patients’ ability to solve problems and remember issues and that requires timely and proper identification to enable appropriate management and treatment. Based on MRI medical images, deep learning models have become one of the most effective approaches for analyzing the signs of the early stages of AD. This research, therefore, carries out a comparative analysis of five deep learning models such as Convolutional Neural Networks (CNNs) like AlexNet, VGGNet, and ResNet, as well as Long Short-Term Memory (LSTM) networks and 3D Convolutional Neural Networks (3D-CNNs) in the finding of Alzheimer’s Sickness from medical imaging data. Each model’s arrangement parameters, for example, layer configurations, learning rate, batch size, optimizer, number of epochs, loss function, applying techniques for regularization, activation functions, and the input dimensions, using pre-trained weights, were carefully initialized to yield a proper comparison between the models. Diagnostic performances were evaluated utilizing precision, responsiveness(recall), specificity, and region under the receiver operating characteristic curve (AUC-ROC). ResNet outperformed other profound learning models in diagnosing Alzheimer’s Disease from MRI scans with a precision of 0.91 and AUC-ROC of 0.95. At the same time, VGGNet, AlexNet, LSTM, and 3D-CNNs demonstrated varying strengths and limitations in balancing accuracy, computational efficiency, and feature extraction.

关键词： Artificial Intelligence (AI) Cognitive Impairment Data Augmentation Diagnosis Accuracy Medical Imaging

来源：评论

学校读者我要写书评

暂无评论

Research on Concurrency Control in Database Systems 12th

Research on Concurrency Control in Database Systems

引用

12th International Conference on computer engineering and Networks, CENet 2022

作者： Shen, Pengxu Qian, Hanwei Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing210031 China Engineering Research Center of Electronic Data Forensics Analysis Jiangsu Nanjing China Key Laboratory of Digital Forensics Department of Public Security of Jiangsu Province Nanjing China

ISBN: (纸本)9789811969003

In a database system, if the degree of concurrency is high, using a concurrency control algorithm alone will reduce the performance of the system, and the process of selecting a concurrency control algorithm will virtually improve the knowledge threshold of users. In order to overcome this limitation, this paper proposes a hybrid concurrency control algorithm, which is called cluster based concurrency control algorithm. It creatively puts forward the concept of transaction working set, uses the minimum hash algorithm to calculate the Jaccard similarity between different transaction working sets to measure the conflict rate between different transactions, and uses this as a standard to place transactions in different clusters, Transactions in the same cluster adopt pessimistic concurrency control algorithm, and transactions in different clusters adopt optimistic concurrency control algorithm. The clustering based concurrency control algorithm combines the traditional pessimistic concurrency control algorithm with the optimistic concurrency control algorithm to obtain the advantages of the two algorithms and alleviate the performance bottleneck of the two algorithms. Finally, through simple experiments, it is proved that the concurrency control algorithm based on clustering is indeed better than the traditional pessimistic and optimistic concurrency control algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Concurrency control

来源：评论

学校读者我要写书评

暂无评论

security Revisited: Honeytokens meet Google Authenticator 7

Security Revisited: Honeytokens meet Google Authenticator

引用

7th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2022

作者： Papaspirou, Vassilis Papathanasaki, Maria Maglaras, Leandros Kantzavelou, Ioanna Douligeris, Christos Ferrag, Mohamed Amine Janicke, Helge University of West Attica Department of Informatics and Computer Engineering Athens Greece University of Thessaly Department of Cs and Telecommunications Lamia Greece Cyber Technology Institute De Montfort University Leicester United Kingdom University of Piraeus Department of Informatics Piraeus Greece Guelma University Department of Computer Science Guelma Algeria Cyber Security CRC Edith Cowan University Perth Perth6027 Australia

ISBN: (数字)9798350398588

ISBN: (纸本)9798350398588

In contrast to the rapid advancement and evolution of technology, computer systems rely significantly on passwords to maintain their security for an unreasonably long time. Although the introduction of two or more factors improved existing authentication procedures and gave rise to new multi-factor authentication schemes, more advanced and focused assaults have revealed they are also sensitive and ineffective to assure only authorized access to systems. This study suggests a revolutionary two-factor authentication mechanism that uses QR codes and honeytokens. In the current implementation, honeywords and Google authenticator work together. In order to speed up the identification process, the honeywords technique is utilized as a second factor on a different computing device. By using a stronger and more effective authentication mechanism than a single password mechanism or a common two-factor authentication scheme, the novel and straightforward approach presented here intends to add additional layers of security and protection into a system, thereby increasing its security. © 2022 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A Community Detection Approach for Academic Social Network: The Case of the Cross-Strait Academic Conference Network 3

A Community Detection Approach for Academic Social Network: ...

引用

3rd International Conference on Electronics, Communications and Information technology, CECIT 2022

作者： Zhang, Xinxin Xu, Li Gao, Min Fan, Jianxi Sun, Hung-Min Fujian Normal University College of Computer and Cyber Security Fujian Provincial Key Laboratory of Network Security and Cryptology Fuzhou China Fudan University The School of Computer Science Shanghai China Soochow University The School of Computer Science and Technology Suzhou China National Tsing Hua University The Department of Computer Science Hsinchu Taiwan

ISBN: (纸本)9798350331974

With the fast development of information networks, academic social network analysis has attracted significant attention, we regard these researchers sharing common interests as a research community. The community has been widely used as the underlying structure of social networks. To utilize network information as much as possible, we capture the structural characteristics and attribute features to detect communities in the cross-strait academic conference network. In this paper, we first consider 2-hop neighbors with the Pareto principle to filtrate the central seed nodes in networks. Then we propose a new seed shrinkage strategy to get the initial communities and define the similarity according to the structure and attributes of social networks to merge the communities. Finally, we define a new indicator named inner average distance (IAD) to measure the aggregation density for each community. A case study of the cross-strait academic social network was developed to test the applicability of the proposed model, the experiment analysis suggests that our method can be more accurate to identify communities in most situations, which contributes to controlling the information spreading in networks. © 2022 IEEE.

关键词： Pareto principle

来源：评论

学校读者我要写书评

暂无评论

A Physical-Layer Key Generation Scheme for Non-Square Channel Matrices Based on PMI

A Physical-Layer Key Generation Scheme for Non-Square Channe...

引用

2023 IEEE/CIC International Conference on Communications in China, ICCC 2023

作者： Sun, Haixi Li, Guyue Li, Haoyu Hu, Aiqun Cheng, Yexia Tian, Ye He, Shen Southeast University School of Cyber Science and Engineering Nanjing210096 China Purple Mountain Laboratories for Network and Communication Security Nanjing210096 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Research Institute of China Mobile Communications Corporation Department of Security Technology China

ISBN: (纸本)9798350345384

Physical-layer secret key generation (PKG) is an emerging technique to address the secret key distribution problem and precoding matrix index (PMI)-based PKG approaches can thwart eavesdropping attempts. However, existing PKG schemes based on PMI only considered square channel matrices, which restricts the practical application. In this paper, we propose a new PKG scheme called NS-PMI-PKG which can yield secret keys for non-square channel matrices in time-division duplex (TDD) mode. Specifically, NS-PMI-PKG includes two vital steps, i.e., codebook generation and detection. First, the codebook generation approach ensures a unitary precoding matrix by applying singular value decomposition (SVD) to the precoding matrix. Second, we present an efficient codebook detection approach leveraging the properties of unitary matrices and the concept of template matching. Subsequently, we present a theoretical analysis of the proposed NS-PMI-PKG scheme from the aspects of key generation correctness, security, and efficiency. The simulation results demonstrate that the proposed scheme exhibits good key generation performance when the channel matrix is non-square. At the signal-to-noise ratio (SNR) of 25 dB, the bit error rate (BER) of the proposed scheme is approximately an order of magnitude lower than that of the baseline scheme. In addition, the eavesdropper struggles to obtain any keys when 2 meters away from the legitimate user, and even when sufficiently close, can acquire at most half the keys. Also, the generated key exhibits good randomness, enhancing its resistance to brute force cracking. © 2023 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Weibo Public Opinion Analysis System 12th

Design and Implementation of Weibo Public Opinion Analysis S...

引用

12th International Conference on computer engineering and Networks, CENet 2022

作者： Qi, Jiacheng Liu, Xiaoqian Yuan, Ming Gu, Haiyan Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing210031 China Engineering Research Center of Electronic Data Forensics Analysis Jiangsu Nanjing China Key Laboratory of Digital Forensics Department of Public Security of Jiangsu Province Nanjing China

ISBN: (纸本)9789811969003

Public opinion refers to the public attitudes and emotions of the masses on social phenomena. As one of the most popular micro-blogging platforms, Sina Weibo serves as an important public opinion carrier. Understanding the public opinion helps the government departments such as contingency management, public security, and other decision makers to timely understand the social situation, and actively resolve social conflicts and promote social harmony. On the other hand, related departments can also identify criminals from online public opinions and effectively crack down on them. In this work, we design and implement a Weibo public opinion analysis system, which consists of data collecting subsystem, data pre-processing subsystem, and text analysis subsystem and demonstrate our discovery mainly in public security. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Web crawler

来源：评论

学校读者我要写书评

暂无评论

Highly Efficient Actively Secure Two-Party Computation with One-Bit Advantage Bound

Highly Efficient Actively Secure Two-Party Computation with ...

引用

IEEE Symposium on security and Privacy

作者： Yi Liu Junzuo Lai Peng Yang Qi Wang Anjia Yang Siu-Ming Yiu Jian Weng College of Cyber Security Jinan University Guangzhou China Department of Computer Science The University of Hong Kong Hong Kong SAR China Department of Computer Science and Engineering National Center for Applied Mathematics Shenzhen Southern University of Science and Technology Shenzhen China

ISBN: (数字)9798331522360

ISBN: (纸本)9798331522377

Secure two-party computation (2PC) enables two parties to jointly evaluate a function while maintaining input privacy. Despite recent significant progress, a notable efficiency gap remains between actively secure and passively secure protocols. In S&P'12, Huang, Katz, and Evans formalized the notion of active security with one-bit leakage, providing a promising approach to bridging this gap. Protocols derived from this notion have become foundational in designing highly efficient actively secure 2PC protocols. However, a critical challenge identified by Huang, Katz, and Evans remains unexplored: these protocols face significant weaknesses in ensuring fairness for honest parties when employed in standalone settings rather than as components within larger protocols. While the authors proposed two potential solutions to mitigate this issue, both approaches are prohibitively expensive and lack formalization of security guarantees. In this paper, we first formally define an enhanced notion called active security with one-bit-advantage bound, in which the adversaries' advantages are strictly bounded to at most one bit beyond what honest parties obtain. This bound is enforced through a progressive revelation mechanism, where the evaluation result is disclosed incrementally bit by bit. In addition, we propose a novel approach leveraging label structures within garbled circuits to design a highly efficient constant-round 2PC protocol that achieves active security with one-bit advantage bound. Our protocol demonstrates runtime performance nearly identical to that of passively secure garbled-circuit counterparts in duplex networks (e.g., 1.033 × for the SHA256 circuit in LAN), with low overhead for output progressive revelation (only 80 communicated bytes per bit release). With its strengthened security guarantees and minimal overhead, our protocol is highly suitable for practical 2PC applications.

关键词： Privacy Protocols Runtime Circuits Computational efficiency security Local area networks Faces

来源：评论

学校读者我要写书评

暂无评论

Digital Forensics Study on Smart Watch and Wristband: Data Sniffing, Backup and Database Analyzing 8th

Digital Forensics Study on Smart Watch and Wristband: Data S...

引用

8th International Conference on Artificial Intelligence and security , ICAIS 2022

作者： Chen, Pu Liang, GuangJun Ding, Ziqi Xu, Zixiang Zhang, Mochi Department of Computer Information and Cyber Security Jiangsu Police Institute Nanjing China Jiangsu Province Electronic Data Forensics and Analysis Engineering Research Center Nanjing China Key Laboratory of Digital Forensics of Jiangsu Provincial Public Security Department Nanjing China

ISBN: (纸本)9783031067600

With the technology advancing rapidly, it has become apparent that it is nearly impossible to go without a digital trace when committing a crime. Device such as Xiaomi wristband, keeps the record of a user’s daily activities, heart rate, pressure value, step count, and sleep quality. Due to daily use, these messages are valuable for digital forensic investigators as it may serve as evidence and proofs to a crime, as well as revealing the motives of crime. This paper will demonstrate some useful examples to investigators about the methods to extract and analyze smart watch using Bluetooth tools like Ubertooth One. Experiments about wireless sniffing and wired transmission are given in this paper. We are making a tentative exploration and hoping to provide some useful experience and practice to investigators in the field of forensics. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Crime

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：