检索结果-内蒙古大学图书馆

International Conference on Software engineering (ICSE)

作者： Jintao Huang Kai Yang Gaosheng Wang Zhiqiang Shi Zhiwen Pan Shichao Lv Limin Sun Beijing Key Laboratory of IOT Information Security Technology Institute of Information Engineering CAS School of Cyber Security University of Chinese Academy of Sciences Beijing China School of Computer Electronics and Information Guangxi University Nanning China

ISBN: (数字)9798331505691

ISBN: (纸本)9798331505707

As embedded devices become increasingly popular, monolithic firmware, known for its execution efficiency and simplicity, is widely used in resource-constrained devices. Different from ordinary firmware, the monolithic firmware image is packed without the file that indicates its format, which challenges the reverse engineering of monolithic firmware. Function identification is the prerequisite of monolithic firmware's analysis. Prior works on function identification are less effectiveness when applied to monolithic firmware due to their heavy reliance on file formats. In this paper, we propose Moye, a novel method to identify functions in monolithic firmware. We leverage the important insight that the use of registers must conform to some constraints. In particular, our approach segments the firmware, locate code sections and output the instructions. We use a masked language model to learn hiding relationships among the instructions to identify the function boundaries. We evaluate Moye using 1,318 monolithic firmware images, including 48 samples collected from widely used devices. The evaluation demonstrates that our approach significantly outperforms current works, achieving a precision greater than 98 % and a recall rate greater than 97 % across most datasets, showing robustness to complicated compilation options.

关键词： Image segmentation Codes Reverse engineering Robustness Registers Microprogramming Software engineering

来源：评论

学校读者我要写书评

暂无评论

TMAS:A transaction misbehavior analysis scheme for blockchain

引用

Blockchain(Research and Applications) 2024年第3期5卷 42-52页

作者： Shiyong Huang Xiaohan Hao Yani Sun Chenhuang Wu Huimin Li Wei Ren Kim-Kwang Raymond Choo School of Computer Science China University of GeosciencesWuhan430074China Artificial Intelligence Thrust Information HubHong Kong University of Science and TechnologyGuangzhou511400China Yunnan Key Laboratory of Blockchain Application Technology Yunnan Innovation Institute of Beihang UniversityKunming650233China Fujian Key Laboratory of Financial Information Processing Putian UniversityPutian351100China Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX 78249-0631USA

Blockchain-based cryptocurrencies,such as Bitcoins,are increasingly ***,the decentralized and anonymous nature of these currencies can also be(ab)used for nefarious activities such as money laundering,thus reinforcing the importance of designing tools to effectively detect malicious transaction *** this paper,we propose TMAS,a transaction misbehavior analysis scheme for blockchain-based ***,the proposed system includes ten features in the transaction graph,two heuristic money laundering models,and an analysis method for account linkage,which identifies accounts that are distinct but controlled by an identical *** evaluate the effectiveness of our proposed indicators and models,we analyze 100 million transactions and compute transaction features,and are able to identify a number of suspicious ***,the proposed methods can be applied to other cryptocurrencies,such as token-based cryptocurrencies(e.g.,Bitcoins)and account-based cryptocurrencies(e.g.,Ethereum).

关键词： Blockchain Anti-money laundering Bitcoin Cyptocurrency

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Explainable Machine Learning Framework for Alzheimer's Disease Detection

An Efficient and Explainable Machine Learning Framework for ...

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Mohammad Emad Arafah Rejwan Bin Sulaiman Mohammad Ahmad Md. Simul Hasan Talukder Department of Computer Science University of Petra Amman Jordan Lecturer of AI and Cyber Security Northumbria University Newcastle upon Tyne UK Lecturer of Computer Science University of Bedfordshire Luton UK Electrical and Electronic Engineering Dhaka University of Engineering & Technology Gazipur Bangladesh

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Alzheimer's disease detection is of paramount importance as it is a global health problem in terms of early detection, interventions, and management. The study applies prominent machine learning classification to Alzheimer's disease by integrating longitudinal and cross-sectional data analysis. With careful correlation analysis, we derived the following important predictive features: ‘M/F’, ‘Age’, ‘Education’, ‘SES’, ‘CDR’, ‘MMSE’, ‘eTIV’, ‘nWBV’, ‘ASF’, and ‘Hand’. In this study, the entire dataset was divide into training (80%) and testing (20%) sets, with eight machine learning models implemented on it for classification: CatBoost-CB, Logistic Regression-LR, Extreme Gradient Boosting-XGB, Support Vector Machine-SVM, Random Forest-RF, K-Nearest Neighbors-KNN, Decision Tree-DT, and Gradient Boosting-GB. Our results demonstrated superior performance from ensemble models, with RF, XGB, GB, DT, and CB achieving 98.1% accuracy, 98.2% precision, and 98.1% recall. These models showed exceptional performance with a Kappa score of 0.95, indicating strong reliability in classification. We have also used LIME explainability to enhance model transparency, providing insight into the contribution of different features in support of the interpretability of the model. In this study, we stress the power of machine learning for early detection of Alzheimer's disease, and provide future research directions on improving the predictive accuracy and transparency of predictive models.

关键词： Training Radio frequency Accuracy Feature extraction Vectors Reliability Alzheimer's disease Stress Regression tree analysis Testing

来源：评论

学校读者我要写书评

暂无评论

Secure Cloud Computing: Mitigating Network Vulnerabilities

Secure Cloud Computing: Mitigating Network Vulnerabilities

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Santhosh Kumar Gopal Abdul Sajid Mohammed Madhusudhan Dasari Sreeramulu Dhamodharan Srinivasan Technology Lead Charlotte NC USA Dept of School of Computer and Information Sciences University of the Cumberlands Kentucky USA Dept of Cyber Security American Express Department of Computer and Communication Engineering Sri Eshwar College of Engineering Coimbatore Tamil Nadu India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

As businesses increasingly depend on these cloud-based services, secure cloud computing is vital. There is no free way with the cloud network, and our information is susceptible to vulnerability. Mitigation strategies to address these network vulnerabilities in cloud computing and analysis of the man-in-the-middle attack and Distributed Denial of Service (DDoS) attack are discussed in this paper. For instance: enhance network architecture, encryption, and security mechanisms like intrusion detection systems and firewalls. With these steps, organizations can further increase their cloud network security and protect data with zero breaches.

关键词： Access control Cloud computing Protocols Prevention and mitigation Authentication Telecommunication traffic Software Encryption Web sites Protection

来源：评论

学校读者我要写书评

暂无评论

An Efficient Post-quantum Identity-Based Signature

引用

Chinese Journal of Electronics 2021年第2期30卷 238-248页

作者： YANG Zhichao DUNG H.Duong WILLY Susilo YANG Guomin LI Chao CHEN Rongmao College of Liberal Arts and Sciences National University of Defence Technology Department of Information Security Naval University of Engineering School of Computing and Information Technology University of Wollongong College of Computer National University of Defence Technology

Digital signature is one of the most important cryptography primitives. Recently, more and more works have been done to construct signatures over lattice problems to keep them secure in the quantum age. Among them, a ring-based signature scheme named Dilithium is the most efficient one and a candidate in the third round of the National Institute of Standards and technology's post-quantum cryptography project. To make those schemes work well in large network, we constructed the first ring-based Identity-based signature(IBS) scheme for light-weight authentication. The construction in this paper relies on the transformations introduced by Bellare et al. in Journal of Cryptology(Vol.22, No.1, pp.1–61, 2009)and its security can be proved under the hardness of ringlearning with errors problem in the random oracle *** to better trapdoor and polynomial ring setting,our proposed scheme are much better than the previous ones in terms of both computation and communication complexities.

关键词： construct signatures important cryptography primitives ring-based Identity-based signature scheme communication complexity efficient post-quantum Identity-based signature polynomial ring setting ring-based signature scheme polynomials quantum age digital signatures quantum cryptography lattice problems digital signature public key cryptography technology's post ring-learning

来源：评论

学校读者我要写书评

暂无评论

Malware analysis and multi-label category detection issues: Ensemble-based approaches 3

Malware analysis and multi-label category detection issues: ...

引用

3rd International Conference on Intelligent Data Science Technologies and Applications, IDSTA 2022

作者： Alsmadi, Izzat Al-Ahmad, Bilal Alsmadi, Mohammad Department of Computing and Cyber Security Texas A&m San Antonio United States The University of Jordan Computer Information Systems Department Aqaba Jordan Applied Science University Information Technology Amman Jordan

ISBN: (数字)9781665499606

ISBN: (纸本)9781665499606

Detection of malware and security attacks is a complex process that can vary in its details and analysis activities. As part of the detection process, malware scanners try to categorize a malware once it is detected under one of the known malware categories (e.g. worms, spywares, viruses, etc.). However, many studies and researches indicate problems with scanners categorizing or identifying a particular malware under more than one malware category. This paper, and several others, show that machine learning can be used for malware detection especially with ensemble base prediction methods. In this paper, we evaluated several custom-built ensemble models. We focused on multi-label malware classification as individual or classical classifiers showed low accuracy in such *** paper showed that recent machine models such as ensemble and deep learning can be used for malware detection with better performance in comparison with classical models. This is very critical in such a dynamic and yet important detection systems where challenges such as the detection of unknown or zero-day malware will continue to exist and evolve. © 2022 IEEE.

关键词： Scanning

来源：评论

学校读者我要写书评

暂无评论

Differential privacy protection method for trip-oriented shared data

Differential privacy protection method for trip-oriented sha...

引用

作者： Du, Danlei Luo, Entao Yi, Yang Peng, Tao Li, Xubin Zhang, Shaobo Jiang, Xu Wang, Tian School of Information Engineering Hunan University of Science and Engineering YongZhou China Guangxi Key Laboratory of Cryptography and Information Security Guilin University of Electronic Technology Guilin China Department of Computer Science Northeastern Illinois University ChicagoIL United States School of Computer Science and Engineering Guangzhou University Guangzhou China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China School of Computer Science and Engineering Nanjing University of Science and Technology NanJing China Zhuhai China Zhuhai China

While location information sharing technology provides convenience for unmanned driving and journey navigation, user journey information sharing has also become a disaster for privacy information leakage. The traditional differential privacy method can only perturb the data entirely and cannot consider the design of data availability. In this paper, the difference privacy algorithm is improved by combining it with the Apriori algorithm, and the relevant perturbation is carried out after mining the associated data of the user's trip. In the face of possible data attacks, the privacy protection of the sensitive information of the user's actual data is ensured while the availability of the data is ensured. By testing 3000 trip data generated by experimental simulation, the results show that the correlation information between the original datasets is destroyed. However good availability is maintained after the Laplace data perturbation of the proposed algorithm for both simultaneous and multi-person trips. © 2022 John Wiley & Sons, Ltd.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

New Constructions for Linear Maximum Sum-Rank Distance Codes

New Constructions for Linear Maximum Sum-Rank Distance Codes

引用

IEEE International Symposium on Information Theory

作者： Huimin Lao Yeow Meng Chee Hao Chen Van Khu Vu Department of Industrial Systems Engineering and Management National University of Singapore Singapore College of Information Science and Technology/Cyber Security Jinan University China

ISBN: (数字)9798350382846

ISBN: (纸本)9798350382853

Sum-rank-metric codes have attracted lots of attention due to their numerous applications, including muti-shot linear network coding, space-time coding, and distributed storage systems. In this paper, we focus on constructing linear sum-rank-metric codes achieving Singleton bound, which are called maximum sum-rank distance (MSRD) codes. This family of codes is the analogue of maximum distance separable (MDS) codes in Hamming metric. We propose two constructions of linear MSRD codes with various matrix sizes. Each of them yields new MSRD codes with different parameter regimes, and one of them generalizes some recent results of Byrne et al. (2021) and Chen (2023). The block lengths and the matrix block sizes of our codes are not restricted to the sizes of the finite field. Our technique is mainly based on rank metric codes and their sub-codes of different minimum rank distances.

关键词： Measurement Codes Network coding Generators Encoding Decoding Galois fields

来源：评论

学校读者我要写书评

暂无评论

Enhanced Reinforcement of Filler in Polyurethane Foam - Mechanical and Thermal Properties 2

Enhanced Reinforcement of Filler in Polyurethane Foam - Mech...

引用

2nd IEEE International Conference on Emerging Trends in engineering and Medical Sciences, ICETEMS 2024

作者： Sathish, T. Giri, Jayant Al Sherideh, Ala'a Saveetha School of Engineering SIMATS Saveetha University Thandalam Department of Mechanical Engineering Chennai India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India College of Information Technology Zarga University Department of Cyber Security Zarqa Jordan University of Business and Technology Jeddah 21448 Saudi Arabia

ISBN: (纸本)9798331529352

Al2O3 synthetic filler represents one of the most readily accessible supplies for applications evaluating performance, cost, and benefit. In the present research, pure polyurethane foam was mixed with the previously described filler, and the properties were examined using thermal (thermogravimetric) and mechanical (tensile, elongation, resilience, and hardness) analysis. Employing high shear mixing rates, these synthetic fillers have been added in weight percentages of 1%, 2%, and 3%. The process for manufacturing closed-moulded polyurethane foam required an addition reaction between isocyanate and polyol. The homogeneous colour distribution of the foam composites embedded with synthetic filler indicates effective filler dispersion. Tensile and resilience improvements were observed at 2 % filler loading. Through the replacement of alternative fibres an application of industrial, such as construction, locomotive, fabric, and other prominent industries depends on purchaser, this study strengthens potential of a more sustainable future. © 2024 IEEE.

关键词： Applications Filler Mechanical Polymer Thermal

来源：评论

学校读者我要写书评

暂无评论

AdaSin: Enhancing Hard Sample Metrics with Dual Adaptive Penalty for Face Recognition

arXiv

引用

arXiv 2025年

作者： Guo, Qiqi Zheng, Zhuowen Yang, Guanghua Liu, Zhiquan Li, Xiaofan Li, Jianqing Tian, Jinyu Gong, Xueyuan School of Intelligent Systems Science and Engineering Jinan University Guangdong China College of Cyber Security Jinan University Guangdong China School of Computer Science and Engineering Macau University of Science and Technology China

In recent years, the emergence of deep convolutional neural networks has positioned face recognition as a prominent research focus in computer vision. Traditional loss functions, such as margin-based, hard-sample mining-based, and hybrid approaches, have achieved notable performance improvements, with some leveraging curriculum learning to optimize training. However, these methods often fall short in effectively quantifying the difficulty of hard samples. To address this, we propose Adaptive Sine (AdaSin) loss function, which introduces the sine of the angle between a sample’s embedding feature and its ground-truth class center as a novel difficulty metric. This metric enables precise and effective penalization of hard samples. By incorporating curriculum learning, the model dynamically adjusts classification boundaries across different training stages. Unlike previous adaptive-margin loss functions, AdaSin introduce a dual adaptive penalty, applied to both the positive and negative cosine similarities of hard samples. This design imposes stronger constraints, enhancing intra-class compactness and inter-class separability. The combination of the dual adaptive penalty and curriculum learning is guided by a well-designed difficulty metric. It enables the model to focus more effectively on hard samples in later training stages, and lead to the extraction of highly discriminative face features. Extensive experiments across eight benchmarks demonstrate that AdaSin achieves superior accuracy compared to other state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

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：