A framework for detection and measurement of phishing attacks

摘要: Phishing is form of identity theft that combines social engineering techniques and sophisticated attack vectors to harvest financial information from unsuspecting consumers. Often a phisher tries lure her victim into clicking URL pointing rogue page. In this paper, we focus on studying the structure URLs employed in various phishing attacks. We find it often possible tell whether or not belongs without requiring any knowledge corresponding page data. describe several features can be used distinguish benign one. These are model logistic regression filter efficient has high accuracy. use perform thorough measurements million quantify prevalence Internet today