A hybrid phish detection approach by identity discovery and keywords retrieval

By Guang Xiang, Jason I. Hong. 2009

145 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): “Our study presents accurate measurements of the duration and effectiveness of this popular threat, and discusses many new and interesting aspects we observed by monitoring hundreds of phishing campaigns.”
Antiphishing through Phishing Target Discovery (2012, background): “(1 ) I f P fo un d i n G (2) If itations end (3) If A doesn’t change after reinforcement”
Proactive Discovery of Phishing Related Domain Names (2012, background): “However for phishing detection purposes, it can be either host-based features (WHOIS info, IP preﬁx, AS number) in [15] or web page content-based features in [25].”
Clustering Potential Phishing Websites Using DeepMD5 (2012, background): “Therefore, there have been a number of researchers that use combinations of all three categories [16][17][18].”
A Hierarchical Adaptive Probabilistic Approach for Zero Hour Phish Detection (2010, methodology): “More recently, Xiang et al [22] proposed a hybrid detection model that recognizes phish by discovering the inconsistency between a webpage’s true identity and its claimed identity via search engine and information extraction techniques.”
High-performance content-based phishing attack detection (2011, background): “proposed a similar identity extraction algorithm that employs information extraction and retrieval algorithms to differentiate websites that are claiming to be a particular website versus legitimate websites [18].”
An Anti-Phishing System Employing Diffused Information (2014, methodology): “…reported TPR and FPR for Spoof-Guard [Chou et al. 2004], the Earth Mover s Distance [Fu et al. 2006], CANTINA [Zhang et al. 2007], a hybrid method [Xiang and Hong 2009], Phishing Target Discovery [Wenyin et al. 2012], and CANTINA+ [Xiang et al. 2011] (note: this latter is the randomized…”
An Empirical Analysis of Phishing Blacklists (2009, methodology): “Finally, Xiang and Hong described a hybrid phish detection method with an identity-based detection component and a keyword-retrieval detection component [35].”
Malicious URL Detection using Machine Learning: A Survey (2017, background): “[65] try to find the identity and keywords in the DOM text and evaluate the consistency between the identity observed and the identity it is potentially trying to mimic which is found by searching.”