检索结果-内蒙古大学图书馆

20th International Conference on Information security and Cryptology, Inscrypt 2024

作者： Gao, Birou Zhang, Rui Xiao, Yuting Zou, Huan Institute of Information Engineering Chinese Academy of Sciences Beijing China Key Laboratory of Cyberspace Security Defense Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Science and Technology Dongguan University of Technology Guangdong China Information Security Center China Mobile Communication Corporation Beijing China

ISBN: (纸本)9789819647309

Blockchain wallets protect users’ assets by securely storing keys. Research has explored various aspects, including BIP32 for key derivation in cold/hot settings and PDPKS further enhancing key insulation. However, most wallets are either user-managed or exchange-hosted, creating centralized points of failure. Shared-custodial wallets allow users and service providers to collaboratively manage keys, which can lead to potential corruption while still safeguarding asset security. Nonetheless, the need for server involvement in each signature poses challenges to user privacy and efficiency. To address these limitations, we propose NEST, the first efficient wallet that simultaneously satisfies strong key insulation, shared custody and privacy. We restrict malicious users’ access to the server through password-based identity authentication and introduce blindness and unlinkability to prevent malicious servers from associating transactions with specific users. Additionally, we have designed two modes: interactive signing for large transactions with high security requirements, and non-interactive signing for small, high-frequency transactions. Our construction of NEST is based on bilinear pairing and an IND-CCA-secure public key encryption scheme, accompanied by a rigorous security analysis in the random oracle model. We implemented our scheme, and the results demonstrate its practicality. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

security and Threat Detection through Cloud-Based Wazuh Deployment 1

Security and Threat Detection through Cloud-Based Wazuh Depl...

引用

1st IEEE Karachi Section Humanitarian Technology Conference, Khi-HTC 2024

作者： Moiz, Syed Majid, Abdul Basit, Abdul Ebrahim, Mansoor Abro, Abdul Ahad Naeem, Mehwish Iqra University Dept. of Computer Science Karachi Pakistan Dept. of Cyber Security Karachi Pakistan Indus University Dept. of Computer Science Karachi Pakistan Iqra University Dept. of Software Engineering Karachi Pakistan University Libre de Bruxelles Brussels Belgium

ISBN: (纸本)9798350373042

In today's interconnected business landscape, security is the cornerstone of all organizations, irrespective of their size or industry. This research emphasizes the critical need to safeguard organizational assets from cyber threats and highlights the pivotal role that firewalls play in fortifying network and cyber systems. The challenge lies in maintaining updated firewall defenses to prevent server downtime and the circumvention of security measures. To address these concerns, this study introduces a novel approach by integrating Cloud Wazuh, a user-friendly solution tailored for non-technical personnel, providing streamlined deployment and customizable security rules. Leveraging Wazuh suite of tools, particularly the Host-Based Intrusion Detection System (HIDS), the research detects and mitigates potential threats, including patterns associated with attacks such as Port Scanning, Denial of Service (DoS), and Metasploit. Additionally, Wazuh offers a range of features, from security Analytics to File Integrity Monitoring, to comprehensively protect against cyber threats. While implementing Cloud Wazuh may entail initial costs, it proves cost-effective compared to maintaining a dedicated IT security team. This research underscores how Cloud Wazuh deployment serves as a pivotal tool for organizations looking to strengthen their security measures, safeguard their data, and ensure uninterrupted operations in an increasingly digital and interconnected world. © 2024 IEEE.

关键词： cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Cost-Effective Evaluation Metrics

Deep Learning Cost-Effective Evaluation Metrics

引用

2023 China Automation Congress, CAC 2023

作者： Zhao, Jian Zhao, Zisong Shi, Lijuan Kuang, Zhejun Wang, Runmin Li, Haixia College of Cyber Security Changchun University Changchun China College of Electronic Information Engineering Changchun University Changchun China College of Computer Science and Technology Changchun University Changchun China

ISBN: (纸本)9798350303759

Deep learning has been a driving force behind recent breakthroughs in artificial intelligence. In particular, neural networks have shown great promise in handling a wide range of tasks. With the improvement of performance, networks need computing power and space are also increasing day by day. However, in practical applications, platforms with low computing power, such as edge devices, have limited computing, it is necessary to select a high cost-effective model. Traditional methods require a lot of experience to select cost-effective models. Therefore, there is an urgent need for a deep learning cost-effective evaluation metrics to measure this performance. To address this, we propose a cost-effective evaluation metric called TALES, which takes a common approach to evaluating deep learning models in practical applications. Our metric objectively evaluates networks based on FLOPs, Params, and predicted latency, which are key factors in determining model performance. After conducting a statistical survey of nearly 300 networks, we conclude that the growth in accuracy and the growth in Euclidean distance computed by FLOPs, Params, and Latency have a very similar mathematical pattern to the Sigmoid function. We then fit the relationship curve using mathematical modeling. Our final results show that our designed cost-effective evaluation metric can effectively and objectively evaluate the relationship between accuracy and network complexity of each network. The results are consistent with objective cognition in the field of deep learning. Through the metric, we can effectively evaluate the performance of deep learning models in practical applications and reducing costs and improving efficiency. © 2023 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

The mass,fake news,and cognition security

引用

Frontiers of computer science 2021年第3期15卷 1-13页

作者： Bin GUO Yasan DING Yueheng SUN Shuai MA Ke LI Zhiwen YU School of Computer Science Northwestern Polytechnical UniversityXi'an 710072China School of Cyber Security Tianjin UniversityTianjin 300350China School of Computer Science and Engineering Beihang UniversityBeijing 100191China

The widespread fake news in social networks is posing threats to social stability,economic development,and political democracy,*** studies have explored the effective detection approaches of online fake news,while few works study the intrinsic propagation and cognition mechanisms of fake *** the development of cognitive science paves a promising way for the prevention of fake news,we present a new research area called Cognition security(CogSec),which studies the potential impacts of fake news on human cognition,ranging from misperception,untrusted knowledge acquisition,targeted opinion/attitude formation,to biased decision making,and investigates the effective ways for fake news *** is a multidisciplinary research field that leverages the knowledge from social science,psychology,cognition science,neuroscience,AI and computer *** first propose related definitions to characterize CogSec and review the literature *** further investigate the key research challenges and techniques of CogSec,including human-content cognition mechanism,social influence and opinion dif-fusion,fake news detection,and malicious bot ***,we summarize the open issues and future research directions,such as the cognition mechanism of fake news,influence maximization of fact-checking information,early detection of fake news,fast refutation of fake news,and so on.

关键词： cyberspace cognition security fake news crowd computing human-content interaction

来源：评论

学校读者我要写书评

暂无评论

ML-assisted security for Anomaly Detection in Industrial IoT (IIoT) Applications 2

ML-assisted Security for Anomaly Detection in Industrial IoT...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Konatham, Bharath Reedy Simra, Tabassum Ghimire, Ashutosh Amsaad, Fathi Ibrahem, Mohamed I. Jhanjhi, N.Z. Department of Computer Science and Engineering Wright State University DaytonOH United States Department of Cyber Security Engineering George Mason University FairfaxVA United States School of Computer Science SCS Taylor’s University Subang Jaya47500 Malaysia

ISBN: (纸本)9798350305418

The industrial Internet of Things (IIoT) uses intelligent sensors and actuators, etc., to facilitate the application of IoT in different industries. This paper presents a comparative analysis using several machine learning (ML)-assisted deep learning techniques to develop efficient cybersecurity anomaly detection within IoT applications. To accomplish that, several deep learning techniques are investigated and analyzed, including Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), their hybrid (CNN+GRU), and Long Short-Term Memory (LSTM). The performance of the developed deep learning models is evaluated in terms of accuracy, precision, recall, F1-score, and False Alarm Rate (FAR). Our experimental results show that the developed hybrid CNN+GRU model outperforms the others, achieving an accuracy of 94.94%, a recall of 92.29%, a precision of 98.49%, an F1-score of 95.24%, and a low false alarm rate of 0.001. However, it is essential to note that the hybrid model requires a longer convergence time, indicating a trade-off between performance and computational efficiency. Notably, individual CNN and GRU models also showcase strong performance as time-efficient alternatives. In conclusion, our adopted comprehensive dataset and rigorous evaluation prove that we have developed practical deep-learning approaches to obtain an accurate measure for an efficient IIoT anomaly detection framework. © 2023 IEEE.

关键词： Anomaly Detection CNN GRU Industrial Internet of Things (IIoT) LSTM ML-assisted security

来源：评论

学校读者我要写书评

暂无评论

Forward and Backward Private Searchable Symmetric Encryption with Efficient Updates 24

Forward and Backward Private Searchable Symmetric Encryption...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Yin, Zhiming Li, Xiong Choo, Kim-Kwang Raymond Liu, Yuzhen Liang, Wei School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Institute for Cyber Security School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China University of Texas at San Antonio Department of Information Systems and Cyber Security San AntonioTX78249-0631 United States

ISBN: (纸本)9798350319934

In dynamic searchable symmetric encryption, clients can search and update encrypted data stored on the server (assumed to be semi-honest). In such schemes, forward privacy guarantees that prior queries are not related to subsequent updated entries, while backward privacy ensures that the previously deleted files are not retrievable from the subsequent queries. However, most of the existing schemes have poor update efficiency, for example incurring significant computational and communication overheads since the use of the complex structures and cryptographic primitives used. Hence, we propose a Forward and Backward private searchable symmetric encryption scheme with Efficient uPdates, called FBEP. Specifically, FBEP achieves efficient updates based on Bloom filters and lightweight symmetric cryptographic primitives. It enables the client to remove file identifiers without interacting with the server and insert them efficiently, while maintaining high search efficiency. We precisely define the leakage of FBEP, and demonstrate that FBEP supports forward and Type-II backward privacy with formal security analysis. Besides, the experiments show that FBEP is much better than other related schemes in terms of comprehensive performance. Specially, the update efficiency of FBEP outperforms at least 1.6×, 25×, 525× than Mitra, SDd and Janus ++, respectively, while the search time is at least 2×, 702× faster than Mitra and Janus ++, respectively. © 2022 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled DNS: Enhancing security and Mitigating Attacks in Domain Name Systems 6

Blockchain-Enabled DNS: Enhancing Security and Mitigating At...

引用

6th International Conference on Signal Processing and Information security, ICSPIS 2023

作者： Shah, Kaushal Padhya, Mukti Sharma, Sachin Pandit DeenDayal Energy University School of Technology Department of Computer Science and Engineering Gandhinagar India National Forensic Sciences University School of Cyber Security and Digital Forensics Gandhinagar India

ISBN: (纸本)9798350329599

The importance of Internet security is increasing as businesses expand through digitalization. Like in the physical world, data transmitted over the Internet must be safeguarded to ensure confidentiality, integrity, and availability. Among the various security threats, Distributed Denial-of-Service (DDoS) attacks are widely recognized as they can potentially compromise all three aspects of data security. Despite several attempts to address these attacks, the traditional Domain Name System (DNS) has struggled to counter them effectively. In this research, we propose the concept of a Blockchain-based DNS as a solution to mitigate DNS-related threats, particularly DDoS attacks. The suggested architecture encompasses all levels of the DNS, including registrars, intermediaries (if any), and clients. By leveraging the decentralized nature of blockchain technology, this approach provides a fundamental defense against DDoS attacks, as it eliminates the vulnerability of a single point of failure. Furthermore, this work explores the appropriate type of blockchain to be used, estimates the cost of implementing such a service, and offers flexibility for organizations to adopt this solution at their discretion. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Climate Change Impact Assessment and Adaptation Planning 2

Machine Learning for Climate Change Impact Assessment and Ad...

引用

2nd IEEE International Conference on Trends in Quantum Computing and Emerging Business Technologies, TQCEBT 2024

作者： Balakrishnan, T. Suresh Krishnan, Prabhakar Ebenezar, U. Samson Mohammed Nizarudeen, M. Kamal, N. Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Chennai India Amrita Vishwa Vidyapeetham Center for Cyber Security Systems and Networks Amritapuri-Campus India Saveetha Institute of Medical and Technical Sciences Saveetha University Saveetha School of Engineering Department of Computer Science and Engineering Tamil Nadu Chennai India Care College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy India Grt Institute of Engineering and Technology Dept. of Computer Science and Engineering Tamil Nadu Tiruttani India

ISBN: (纸本)9798350384277

The presented research introduces a new advanced data analytics methodology for climate change impact assessment and adaptive planning that utilizes machine learning and deep-learning techniques. Quantitative analysis was performed over several databases such as GHCN, ERA5, National Centers for Environmental Prediction (NCEP) and JRA-55 in addition to CRU for a thorough assessment of the proposed methodology. In climate modeling, the Convolutional Neural Networks (CNN) showed better accuracy than ERA5 and JRA-55 which outperformed Global Historical Climatology Network (GHCN) with lower Mean Absolute Error (MAE), Root Mean Squared Error values. The Early Warning System, which was built using the LSTM network algorithm, had a higher accuracy of 0.90 and recall rate of 0.88 especially with JRA-55 proving its effectiveness in early detection for extreme weather events before they occur. The RL-based adaptive planning component performed well across all datasets, with ERA5 reaching the best feedback loop performance score of 94%. The precision agriculture optimization, which was enabled by Random Forest revealed different accuracy and AUC-ROC values across various datasets showing flexibility. Against international climate agreements, the overall alignment score was 0.78 with ERA5 being slightly better at 0.80 using Support Vector Machines (SVM). These quantitative assessments accentuate the practicality, efficacy, and applicability of this methodology in various datasets making it an apt tool for evidence-based decisions on climate resilience strategies at the global level. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Guarding Voices, Protecting Homes: A Comprehensive Case Study on Voice Assistant security in Smart Living 12

Guarding Voices, Protecting Homes: A Comprehensive Case Stud...

引用

12th International Symposium on Digital Forensics and security, ISDFS 2024

作者： Rehman, Fazalur Hashmi, Joudat Abdullah, Moiz Zaman, Hafsah School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad Pakistan College of Engineering Georgia Tech University Department of Analytics United States Air University Faculty of Computing and Artificial Intelligence Department of Cyber Security Islamabad Pakistan

ISBN: (纸本)9798350330366

The evolution of technologies in the last decades has transformed the whole human interaction experience with the digital world. Integrated into users' home voice assistant devices has rationalized personal interaction with the technology however convenience of intelligent voice assistant presents security and privacy risks. This paper investigates the security vulnerabilities of smart voice assistant devices specifically focusing on Google Home Mini. Through a series of simulated attacks and comprehensive analysis, this study uncovers potential risks ranging from unauthorized access to user data privacy compromise within home networks. The objective is to raise awareness about these vulnerabilities and their implication urging the need for robust security measures and providing valuable observation for future research. As voice devices are becoming an integral part of daily life addressing these challenges is paramount to ensuring user privacy data integrity and overall security of the smart home ecosystem. © 2024 IEEE.

关键词： Risk assessment

来源：评论

学校读者我要写书评

暂无评论

Predicting the Prices of the Used Cars using Machine Learning for Resale

Predicting the Prices of the Used Cars using Machine Learnin...

引用

IEEE Students' Conference on Electrical, Electronics and computer science (SCEECS)

作者： B Hemendiran P N Renjith Department of Computer Science and Engineering specialization in Cyber physical Systems VIT University Chennai Department of Computer Science and Engineering VIT University Chennai India

In this paper, we discuss the use of machine learning models that can accurately forecast the price of a used car based on its attributes and features. In this study, we look at applying supervised machine learning models to forecast second-hand car prices in India. The forecasts are based on historical information gathered from daily news articles, magazines and from various standard websites. The predictions were made using a variety of models, including Random Forest Regressor, Extra Tree Regressor, Bagging Regressor, Decision Tree and the XG Boost method. The most accurate predictions are then selected after comparing the predictions of the models applied. The five strategies all delivered performance that was almost equivalent but not equal and the results obtained are comparable. There are many distinct properties that can be measured, and it has taken a lot of effort to forecast the outcome with increased reliability and accuracy. These models are compared based on their prediction accuracy to determine which is more accurate. Our findings demonstrate that the Random Forest model produces the greatest outcomes.

关键词： Machine learning algorithms Pricing Predictive models Automobiles Reliability Task analysis Regression tree analysis

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：