Cantina: a content-based approach to detecting phishing web sites

By Yue Zhang, Jason I. Hong, Lorrie Faith Cranor. 2007

920 citations recorded by the source corpus.

Subfields: Information Systems, Signal Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Signal Processing

Citations in the corpus

PhishEye: Live Monitoring of Sandboxed Phishing Kits (2016, background): “However, conduct live phishing experiments and evaluations inside honeypots has always been confronted with ethical considerations that have severely limited the scope of all previous research studies about phishing attacks.”
Learning to Detect Phishing Webpages (2014, methodology): “Lexical features, the textual properties of the URL itself, have widely been used to detect phishing emails and malicious websites [23, 24, 30, 43].”
Large-Scale Automatic Classification of Phishing Pages (2010, methodology): “Despite the noise in the training data, our classifier learns a robust model for identifying phishing pages which correctly classifies more than 90% of phishing pages several weeks after training concludes.”
PhishZoo: Detecting Phishing Websites by Looking at Them (2011, positive): “SpoofGuard [12] and CANTINA [17] are two such approaches.”
Predicting phishing websites based on self-structuring neural network (2013, background): “The method proposed in [10] suggested utilizing”
Malicious URL Detection using Machine Learning: A Survey (2017, methodology): “[51], [52] proposed CANTINA and its variants for detecting phishing websites using a comprehensive featurebased machine learning approach, by exploiting various fea-”
Detecting visually similar Web pages: Application to phishing detection (2010, methodology): “This compares favorably with existing anti-phishing techniques (excluding blacklist-based approaches) such as CANTINA [Zhang et al. 2007] (TPR = 97%, FPR = 6%), or SpoofGuard [Chou et al. 2004; Cranor et al. 2007; Zhang et al. 2007] (TPR = 91%, FPR = 48%), and is similar to the more recent hybrid”
PhishDef: URL names say it all (2010, methodology): “…phishing URLs; the comparative analysis of phishing and non-phishing URLs drawn from PhishTank [6] and DMOZ [5] by McGrath and Gupta [22]; CANTINA [26], which uses a weighted sum of 8 features (4 content-related, 3 lexical, and 1 WHOIS) to classify phishing URLs; the classiﬁcation of phishing…”
A Hierarchical Adaptive Probabilistic Approach for Zero Hour Phish Detection (2010, methodology): “This module, based on one heuristic in CANTINA [23], compensates for the incompleteness of domain whitelists, and is able to minimize FP even for less popular phishing target sites.”
The state of phishing attacks (2012, background): “39 Researchers have also looked at linguistic characteristics of Web pages, identifying the brand name a Web page claims to be.”
PhishNet: Predictive Blacklisting to Detect Phishing Attacks (2010, background): “CANTINA also looks at features related to content, lexical and WHOIS to classify the phishing URLs [13].”