检索结果-内蒙古大学图书馆

Towards Interpretable Machine-Learning-Based DDoS Detection

SN computer science 2024年第1期5卷 115页

作者： Zhou, Qianru Li, Rongzhen Xu, Lei Nallanathan, Arumugam Yang, Jian Fu, Anmin School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China School of Electronic Engineering and Computer Science Queen Mary University of London London E1 4NS United Kingdom

The Internet is the most complex machine humankind has ever built, and thus, it is difficult to defend it from attacks. The most common attack to the Internet is DDoS attacks. With the growing popularity for QUIC protocol, DDoS detection tasks are increasingly rely on machine learning (ML), which is based on black-box model and cannot explain its decision. A interpretable and transparent ML model is the foundation of a trustworthy ML-based DDoS attack detection. Current ML interpretation methodologies in cyber intrusion detection are heuristic, which is neither accurate nor sufficient. This paper proposed a rigorous interpretable ML-driven omnipotent DDoS detection approach, based on knowledge compilation technologies. Details of rigorous interpretation calculation process for the ML model are presented, which include an accelerated prime implicant calculation method driven by knowledge compilation for the DDoS detection ML model, and a map, combine, and merge (M &M) algorithm to discretize continuous features into Boolean expression. The proposed Prime implicant reasons calculation algorithm has been tested on a DDoS LOIC and HOIC attack detection ML model with 100% accuracy, trained with real-life DDoS data. An exhaust list of explanations are given in detail as rules for the omnipotent DDoS intrusion detection learnt by the ML model used. As the ML interpretation method is an SAT problem-solving process, the explanations are rigorous and sufficient reasons for the ML model for DDoS attack detection, and are believed to shade light on DDoS detection research work in cybersecurity community. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： DDoS attack Explainable artificial intelligence Intrusion detection system Knowledge compilation Prime implicate

来源：评论

学校读者我要写书评

暂无评论

Autonomous embodied navigation task generation from natural language dialogues

引用

science China(Information sciences) 2025年第5期68卷 119-132页

作者： Haifeng XU Yongchang LI Lumeng MA Chunwen LI Yanzhi DONG Xiaohu YUAN Huaping LIU Department of Automation Tsinghua University School of Physics and Electronic Information Yantai University School of Electrical and Electronic Engineering Shanghai Institute of Technology Department of Computer Science and Technology Tsinghua University

Robots are increasingly being deployed in densely populated environments, such as homes, hotels, and office buildings, where they rely on explicit instructions from humans to perform tasks. However, complex tasks often require multiple instructions and prolonged monitoring, which can be time-consuming and demanding for users. Despite this, there is limited research on enabling robots to autonomously generate tasks based on real-life scenarios. Advanced intelligence necessitates robots to autonomously observe and analyze their environment and then generate tasks autonomously to fulfill human requirements without explicit commands. To address this gap, we propose the autonomous generation of navigation tasks using natural language dialogues. Specifically, a robot autonomously generates tasks by analyzing dialogues involving multiple persons in a real office environment to facilitate the completion of item transportation between various *** propose the leveraging of a large language model(LLM) through chain-of-thought prompting to generate a navigation sequence for a robot from dialogues. We also construct a benchmark dataset consisting of 625 multiperson dialogues using the generation capability of LLMs. Evaluation results and real-world experiments in an office building demonstrate the effectiveness of the proposed method.

关键词： proactive robot robot navigation service robot large language model

来源：评论

学校读者我要写书评

暂无评论

Preventing 51% Attack by Using Consecutive Block Limits in Bitcoin

引用

IEEE Access 2024年 12卷 77852-77869页

作者： Mahmood Babur, Sohail Ur Rehman Khan, Shafiq Yang, Jing Chen, Yen-Lin Soon Ku, Chin Yee Por, Lip Government Murray College Department of Information Technology Sialkot51010 Pakistan Capital University of Science and Technology Department of Computer Science Islamabad44730 Pakistan Universiti Malaya Department of Computer System and Technology Kuala Lumpur50603 Malaysia National Taipei University of Technology Department of Computer Science and Information Engineering Taipei106344 Taiwan Universiti Tunku Abdul Rahman Department of Computer Science Kampar31900 Malaysia

In permissionless blockchain systems, Proof of Work (PoW) is utilized to address the issues of double-spending and transaction starvation. When an attacker acquires more than 50% of the hash power of the entire network, they gain the ability to engage in double-spending activities, posing a significant threat to the PoW consensus algorithm. This research focuses on the consensus algorithm employed in the Bitcoin system, explaining how it operates and the security challenges it faces. The proposed modification to the PoW algorithm imposes a restriction on miners: they are not allowed to accept consecutive blocks from the same miner into the final local blockchain to prevent the 51% attack problem. This modification supports transactions that require six confirmations. In the event an attacker attempts a 51% attack with a private chain that consists of fewer than 6 blocks, it becomes easier to detect a double-spending attack before accepting the attacker's private chain. The modified algorithm introduces a 'Safe Mode Detection Algorithm' that scrutinizes incoming blocks for adjustments at the top of the local blockchain. If inconsistencies are identified, the consensus algorithm proceeds cautiously by comparing the UTXO dictionaries from the attacker's chain with those from the miner's own blockchain. This meticulous comparison aims to detect instances of double-spending. If such instances are detected, the miner rejects the attacker's chain, establishing a double-spend-free environment and thwarting 51% attacks. © 2013 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

AI-Based Security Protocols for IoT Applications: A Critical Review

引用

Recent Advances in computer science and Communications 2023年第5期16卷 2-18页

作者： Chadha, Harshita Gupta, Shruti Khanna, Ashish Kumar, Neeraj Department of Computer Science and Engineering Maharaja Agrasen Institute of Technology New Delhi India Department of Computer Science and Engineering Chitkara University Institute of Engineering & Technology Punjab Chandigarh India

The Internet Of Things (IoT) is a network of heterogeneous nodes that exchange data and critical information amongst themselves with minimum human intervention. The utility of this technology is large, thus it is used today in most modern applications. With billions of nodes connected across multiple applications, the area for potential security attacks is ever increasing. In addition to this, the nature of the data being transmitted also becomes more sensitive to the latest applications and this calls for effective security provisions. Due to its unique nature, traditional security provisions are not as successfully applicable in IoT networks. This leaves these networks vulnerable to malicious intruders. In such a scenario, Artificial Intelligence (AI) comes out as a powerful solution. This article serves to provide an overview of previously proposed AI-based solutions that can be applied to IoT networks to secure them. An industry-wide overview of security provisions is provided by categorizing IoT applications into three broad sectors, namely, healthcare, smart grid, and smart city. The survey strives to give a clear industry-oriented vision of the available AI solutions and address the requirement of an application-ready security survey in the field. © 2023 Bentham science Publishers.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Adaptive Neighborhood Adjustment Strategy Based On MOHHO and NSGA-III Algorithms for Feature Selection

引用

IAENG International Journal of Applied Mathematics 2024年第5期54卷 917-935页

作者： Papasani, Anusha Durgam, Revathi Devarakonda, Nagaraju Computer Science and Engineering Department Koneru Lakshmaiah Education Foundation AndhraPradesh Vaddeswaram522502 India Computer Science and Engineering Department AVN Institute of Engineering and Technology Telangana Hyderabad501510 India Science and Engineering Department VIT-AP University AP Amaravati522237 India

The efficiency of multi-objective evolutionary algorithms (MOEAs) in tackling issues with multiple objectives is examined. However, it is noted that current MOEA-based feature selection techniques often converge towards the center of the Pareto front due to inadequate selection forces. The study proposes the utilization of a novel approach known as MOEA/D, which partitions complex multi-objective problems into smaller, more feasible single-objective sub-problems. Each sub-problem may then be addressed using an equal amount of computational resources. The predetermined size of the neighborhood used by MOEA/D may lead to a delay in the algorithm's merging and reduce the effectiveness of the failure. The paper proposes the Adaptive Neighbourhood Adjustment Strategy (ANAS) as a novel approach to improve the efficiency of multi-objective optimisation algorithms in order to tackle this issue. The ANAS algorithm allows for adaptive adjustment of the subproblem neighborhood size, hence enhancing the trade-off between merging and variety. In the following section of the study, a novel feature selection technique called MOGHHNS3/D-ANA is introduced. This technique utilizes ANAS to expand the potential solutions for a particular subproblem. The approach evaluates the chosen features using the Regulated Extreme Learning Machine (RELM) classifier on sixteen benchmark datasets. The experimental results demonstrate that MOGHHNS3/D-ANA outperforms four commonly employed multi-objective techniques in terms of accuracy, precision, recall, F1 score, coverage, hamming loss, ranking loss, and training time, error. The APBI approach in decomposition-based multi-objective optimization focuses on handling constraints by adjusting penalty parameters to guide the search towards feasible solutions. On the other hand, the ANA approach focuses on dynamically adjusting the neighborhood size or search direction based on the proximity of solutions in the detached space to adapt the search process.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 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 Method for Suppressing ISRJ based on Noise Frequency Modulated Signal and Multi-channel Matched Filtering 16

A Method for Suppressing ISRJ based on Noise Frequency Modul...

引用

16th International Conference on Signal Processing Systems, ICSPS 2024

作者： Li, Wangyang Yang, Jianchao Lu, Xinyu Dai, Zheng Yu, Wenchao Tan, Ke Gu, Hong Department of Electronic Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9781510689251

This paper introduces a method for suppressing interrupted sampling repeater jamming (ISRJ) based on noise frequency modulation (NFM) signals and multi-channel matched filtering. By taking advantage of the relevant characteristics of the NFM signal and the interval sampling characteristic of interference signals, a group of matched filters is constructed to judge the peak fluctuation of the pulse compression peak, distinguish interference signals from target echoes, and finally eliminate interference components. Compared with traditional ISRJ suppression methods, this method eliminates the influence of intra-pulse time-frequency coupling in the transmitted signal, significantly reduces the number of interference peaks, making the identification and suppression of interference segments precise. Simulation results demonstrate the effectiveness of the proposed method. © 2025 SPIE.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

An integrated land change modeler and distributed hydrological model approach for quantifying future urban runoff dynamics

引用

science China Earth sciences 2024年第10期67卷 3288-3301页

作者： Asad Hussain MUHAMMAD Waseem MUHAMMAD Ajmal MUHAMMAD Atiq Ur Rehman Tariq MUHAMMAD Jiaqing XIAO Tao YANG Pengfei SHI Institute for Disaster Risk Management School of Geographical ScienceNanjing University of Information Science and TechnologyNanjing 210044China The National Key Laboratory of Water Disaster Prevention Hohai UniversityNanjing 210098China Yangtze Institute for Conservation and Development Hohai UniversityNanjing 210098China College of Hydrology and Water Resources Hohai UniversityNanjing 210098China Centre of Excellence in Water Resources Engineering University of Engineering and TechnologyLahore 54890Pakistan Department of Agricultural Engineering Faculty of CivilAgricultural and Mining EngineeringUniversity of Engineering and TechnologyPeshawar 25120Pakistan

Climate and land use changes have a significant impact on the runoff generation process in urban environments, and these effects could get worse in the future. The combined contributions of these changes have increased the risk of ***, there is a need for integrated modeling to better understand the runoff variability, especially in small urban catchments. To quantify and separate the effects of land-use changes and climate change on the hydrological response of urban catchments with a distributed hydrological model(Storm Water Management Model, SWMM), this study introduces a new integrated approach based on the Machine Learning based land use change modeler and climate change scenarios under *** on supervised classification and land use change model analysis, accumulated impervious area increase from 22%(in2023) to 33%(in 2060) was observed in the study area. Furthermore, integrating this projected increase in imperviousness with future climate change into SWMM by considering three different scenarios i.e., S1(Climate Change), S2(Combined Land Use and Climate Change), and S3(Land use Change) resulted that climate change could cause an increase in runoff from 13.2% to18.3% in peak runoff and the contribution of land use could range from 9.1% to 18.6%. Similarly, in response to the coupled effects of climate and land-use change, the runoff would likely change from 24.53% to 39.66%. Conclusively, the study showed that despite climate change, intensive urban development by the substitution of impervious surfaces could also have a severe impact on the microclimate and hydrology of small catchments. Lastly, this study could provide a way forward for the future planning and management of water resources in small catchments which could be extended to larger catchments.

关键词： Climate change Land-use modeling Runoff simulation Percent Imperviousness TerrSet

来源：评论

学校读者我要写书评

暂无评论

Pyram: a robust and attack-resistant perceptual image hashing using pyramid histogram of gradients

引用

International Journal of Information technology (Singapore) 2024年第8期16卷 5331-5349页

作者： Neog, Prabhakar Sharma Roy, Moumita Sangale, Tejas Jain, Nandita Dahal, Aditi Patgiri, Ripon Thounaojam, Dalton Meitei Department of Computer Science and Engineering National Institute of Technology Silchar Department of Computer Science and Information Technology Siksha ‘O’ Anusandhan University

Perceptual image hashing is a significant and time-effective method for recognizing images within extensive databases, focusing on achieving two key objectives: robustness and discrimination. The right balance between these two aspects remains a significant challenge in contemporary hashing research. Moreover, many image hashing algorithms face limitations when performing satisfactorily against specific image processing attacks, such as rotation. With this in mind, a rotation correction based perceptual image hashing system is designed called as Pyram using a pyramid histogram of gradients (PHOG). The system exploits the properties of log polar transform for invariance to geometric distortions and then the PHOG in blocks for generating the final hash vector. In computing hash similarity, the correlation is employed as the metric of choice. The trade-off between robustness and discrimination is evaluated on benchmark databases against single and double attacks. Furthermore, the comprehensive experiments further confirm that the PHOG method consistently delivers better accuracy than its state-of-the-art methods. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Log-Polar Transform Perceptual image hashing PHOG

来源：评论

学校读者我要写书评

暂无评论

Fine-Tuning Cyber Security Defenses: Evaluating Supervised Machine Learning Classifiers for Windows Malware Detection

引用

computers, Materials & Continua 2024年第8期80卷 2917-2939页

作者： Islam Zada Mohammed Naif Alatawi Syed Muhammad Saqlain Abdullah Alshahrani Adel Alshamran Kanwal Imran Hessa Alfraihi Department of Software Engineering International Islamic UniversityIslamabad25000Pakistan Information Technology Department Faculty of Computers and Information TechnologyUniversity of TabukTabuk71491Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia Department of Cybersecurity College of Computer Science and EngineeringUniversity of JeddahJeddah21493Saudi Arabia Department of Computer Science University of PeshawarPeshawar25121Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia

Malware attacks on Windows machines pose significant cybersecurity threats,necessitating effective detection and prevention *** machine learning classifiers have emerged as promising tools for malware ***,there remains a need for comprehensive studies that compare the performance of different classifiers specifically for Windows malware *** this gap can provide valuable insights for enhancing cybersecurity *** numerous studies have explored malware detection using machine learning techniques,there is a lack of systematic comparison of supervised classifiers for Windows malware *** the relative effectiveness of these classifiers can inform the selection of optimal detection methods and improve overall security *** study aims to bridge the research gap by conducting a comparative analysis of supervised machine learning classifiers for detecting malware on Windows *** objectives include Investigating the performance of various classifiers,such as Gaussian Naïve Bayes,K Nearest Neighbors(KNN),Stochastic Gradient Descent Classifier(SGDC),and Decision Tree,in detecting Windows *** the accuracy,efficiency,and suitability of each classifier for real-world malware detection *** the strengths and limitations of different classifiers to provide insights for cybersecurity practitioners and *** recommendations for selecting the most effective classifier for Windows malware detection based on empirical *** study employs a structured methodology consisting of several phases:exploratory data analysis,data preprocessing,model training,and *** data analysis involves understanding the dataset’s characteristics and identifying preprocessing *** preprocessing includes cleaning,feature encoding,dimensionality reduction,and optimization to prepare the data for *** training utilizes various

关键词： Security and privacy challenges in the context of requirements engineering supervisedmachine learning malware detection windows systems comparative analysis Gaussian Naive Bayes K Nearest Neighbors Stochastic Gradient Descent Classifier Decision Tree

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：