{"title":"Performance of Machine Learning and Big Data Analytics Paradigms in Cyber-security and Cloud Computing Platforms","authors":"G. Kabanda","doi":"10.5220/0010789900003167","DOIUrl":null,"url":null,"abstract":"The purpose of the research is to evaluate Machine Learning and Big Data Analytics 7 paradigms for use in Cybersecurity. Cybersecurity refers to a combination of technologies, 8 processes and operations that are framed to protect information systems, computers, devices, 9 programs, data and networks from internal or external threats, harm, damage, attacks or 10 unauthorized access. The main characteristic of Machine Learning (ML) is the automatic data 11 analysis of large data sets and production of models for the general relationships found among 12 data. ML algorithms, as part of Artificial Intelligence, can be clustered into supervised, 13 unsupervised, semi-supervised, and reinforcement learning algorithms. collected of opportunity 30 for cyber crimes and other forms cybersecurity risks, especially among interconnected devices now at household 31 level. 32 The research paper is focused on the Performance of Machine Learning and Big Data Analytics paradigms in 33 Cybersecurity and Cloud Computing platforms. The purpose of the research is to evaluate Machine Learning 34 and Big Data Analytics paradigms for use in Cybersecurity. This is relevant due to the rapid advances in 35 machine learning (ML) and deep learning (DL) as we explore the potency of efficient and cost-effective cloud 36 computing platforms and services. Evaluation of the attacks and defenses using ML and Big Data paradigms 37 is the key subject of this research paper. However, ML and DL techniques are resource intensive and require 38 huge volumes of training data with excellent performance, as is often provided by computational resources such 39 as high-performance graphics processing units (GPUs) and tensor processing units. Security issues related to 40 virtualisation, containerization, network monitoring, data protection and attack detection are interrogated whilst 41 strengthening AI/ML/DL security solutions that involve encryption, access control, firewall, authentication and 42 intrusion detection and prevention systems at the appropriate Fog/Cloud level. 43 Cybersecurity consolidates the confidentiality, integrity, and availability of computing resources, networks, 44 software programs, and data into a coherent collection of policies, technologies, processes, and techniques 45","PeriodicalId":346698,"journal":{"name":"Proceedings of the 1st International Conference on Innovation in Computer and Information Science","volume":"30 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 1st International Conference on Innovation in Computer and Information Science","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.5220/0010789900003167","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
The purpose of the research is to evaluate Machine Learning and Big Data Analytics 7 paradigms for use in Cybersecurity. Cybersecurity refers to a combination of technologies, 8 processes and operations that are framed to protect information systems, computers, devices, 9 programs, data and networks from internal or external threats, harm, damage, attacks or 10 unauthorized access. The main characteristic of Machine Learning (ML) is the automatic data 11 analysis of large data sets and production of models for the general relationships found among 12 data. ML algorithms, as part of Artificial Intelligence, can be clustered into supervised, 13 unsupervised, semi-supervised, and reinforcement learning algorithms. collected of opportunity 30 for cyber crimes and other forms cybersecurity risks, especially among interconnected devices now at household 31 level. 32 The research paper is focused on the Performance of Machine Learning and Big Data Analytics paradigms in 33 Cybersecurity and Cloud Computing platforms. The purpose of the research is to evaluate Machine Learning 34 and Big Data Analytics paradigms for use in Cybersecurity. This is relevant due to the rapid advances in 35 machine learning (ML) and deep learning (DL) as we explore the potency of efficient and cost-effective cloud 36 computing platforms and services. Evaluation of the attacks and defenses using ML and Big Data paradigms 37 is the key subject of this research paper. However, ML and DL techniques are resource intensive and require 38 huge volumes of training data with excellent performance, as is often provided by computational resources such 39 as high-performance graphics processing units (GPUs) and tensor processing units. Security issues related to 40 virtualisation, containerization, network monitoring, data protection and attack detection are interrogated whilst 41 strengthening AI/ML/DL security solutions that involve encryption, access control, firewall, authentication and 42 intrusion detection and prevention systems at the appropriate Fog/Cloud level. 43 Cybersecurity consolidates the confidentiality, integrity, and availability of computing resources, networks, 44 software programs, and data into a coherent collection of policies, technologies, processes, and techniques 45