作者: Michal Piskozub , Riccardo Spolaor , Mauro Conti , Ivan Martinovic
关键词: F1 score 、 Moving target defense 、 Flow network 、 Computer security 、 Robustness (computer science) 、 Identifier 、 Computer science
摘要: Researchers propose Moving Target Defense (MTD) strategies for networking infrastructures as a countermeasure to impede attackers from identifying and exploiting vulnerable network hosts. In this paper, we investigate the weaknesses of Network-based (NMTD) against passive host profiling attacks. particular, consider periodical reactive approaches change hosts' identifiers. To evaluate capabilities attack, design Hostbuster, tool that reidentifies hosts based on flow data. We experimentally its effectiveness using real-world traffic University Oxford. show robustness learned profiles, which are valid more than two months. On average, our experiments result in 80% classification performance given by F1 score. As these analyses, provide guidelines strengthen NMTD types