{"title":"鲁棒和安全5G网络的机器学习方法分析","authors":"Piyush Kulshreshtha, A. Garg","doi":"10.1109/ICEEICT53079.2022.9768557","DOIUrl":null,"url":null,"abstract":"The 5G Network provides higher bandwidth, low latency, low TCO and an ultra density network through use of several new technologies. However, these technologies also lead to a lot of vulnerabilities in the network and make it susceptible to security attacks by hackers. Detection of these attacks requires anomaly detection in network traffic which can be done quickly and efficiently through machine learning techniques. This review paper explores the use of several such supervised learning techniques for Intrusion Detection. A popular dataset _ KDD99, has been utilized to model and compare Intrusion Detection through a set of multi class classifiers. The dataset was cleaned and processed to remove the features that showed very high correlation with each other, The classifier used are Naïve Bayes, Decision Tree, Logistic Regression, Random Forest, Support Vector Machine and Gradient Boost. The paper also compares the performance of these classifiers for detecting abnormal traffic patterns in KDD99 dataset.","PeriodicalId":201910,"journal":{"name":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Analysis of Machine Learning Approaches for Robust and Secure 5G Networks\",\"authors\":\"Piyush Kulshreshtha, A. Garg\",\"doi\":\"10.1109/ICEEICT53079.2022.9768557\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The 5G Network provides higher bandwidth, low latency, low TCO and an ultra density network through use of several new technologies. However, these technologies also lead to a lot of vulnerabilities in the network and make it susceptible to security attacks by hackers. Detection of these attacks requires anomaly detection in network traffic which can be done quickly and efficiently through machine learning techniques. This review paper explores the use of several such supervised learning techniques for Intrusion Detection. A popular dataset _ KDD99, has been utilized to model and compare Intrusion Detection through a set of multi class classifiers. The dataset was cleaned and processed to remove the features that showed very high correlation with each other, The classifier used are Naïve Bayes, Decision Tree, Logistic Regression, Random Forest, Support Vector Machine and Gradient Boost. The paper also compares the performance of these classifiers for detecting abnormal traffic patterns in KDD99 dataset.\",\"PeriodicalId\":201910,\"journal\":{\"name\":\"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)\",\"volume\":\"11 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2022-02-16\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICEEICT53079.2022.9768557\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 First International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICEEICT53079.2022.9768557","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Analysis of Machine Learning Approaches for Robust and Secure 5G Networks
The 5G Network provides higher bandwidth, low latency, low TCO and an ultra density network through use of several new technologies. However, these technologies also lead to a lot of vulnerabilities in the network and make it susceptible to security attacks by hackers. Detection of these attacks requires anomaly detection in network traffic which can be done quickly and efficiently through machine learning techniques. This review paper explores the use of several such supervised learning techniques for Intrusion Detection. A popular dataset _ KDD99, has been utilized to model and compare Intrusion Detection through a set of multi class classifiers. The dataset was cleaned and processed to remove the features that showed very high correlation with each other, The classifier used are Naïve Bayes, Decision Tree, Logistic Regression, Random Forest, Support Vector Machine and Gradient Boost. The paper also compares the performance of these classifiers for detecting abnormal traffic patterns in KDD99 dataset.