COVID-19 malicious domain names classification
作者:
Highlights:
• A method to detect cyberattacks in the context of the COVID-19 pandemic.
• An efficient feature set for the fast detection of COVID-19 malicious domain names.
• Knowledge of the entire URL is not required to prevent an attack.
• The number of subdomains as a feature can highly influence the chosen model.
• Examining the effectiveness of both batch and online learning approaches.
摘要
•A method to detect cyberattacks in the context of the COVID-19 pandemic.•An efficient feature set for the fast detection of COVID-19 malicious domain names.•Knowledge of the entire URL is not required to prevent an attack.•The number of subdomains as a feature can highly influence the chosen model.•Examining the effectiveness of both batch and online learning approaches.
论文关键词:Machine learning,Cybersecurity,Phishing attacks,Supervised learning,Hoeffding trees,Online learning
论文评审过程:Received 22 April 2021, Revised 4 May 2022, Accepted 7 May 2022, Available online 20 May 2022, Version of Record 30 May 2022.
论文官网地址:https://doi.org/10.1016/j.eswa.2022.117553