A comparison of machine learning techniques for phishing detection

By Saeed Abu-Nimeh, Dario Nappa, Xinlei Wang, Suku Nair. APWG Symposium on Electronic Crime Research, 2007

523 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems

View Paper: https://www.semanticscholar.org/paper/fcb926027ba5001f8f69dc0f1de5ded7d003b6af

How researchers see this paper

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

In Artificial Intelligence

In Information Systems

Citations in the corpus

Word2Vec inversion and traditional text classifiers for phenotyping lupus (2017, background): “BOWs with our dataset had the best success with random forests and text classification has proven to have great success with random forests in the past [35, 36].”
Malicious URL Detection using Machine Learning: A Survey (2017, background): “For example [160] did an empirical analysis of different machine learning techniques for Malicious URL Detection in 2007, at a time when neither features nor machine learning models for this task had been extensively explored.”
Review: machine learning techniques applied to cybersecurity (2019, methodology): “Before then, few studies can be found applied to phishing, but in 2007 two main research works were published focused on phishing e-mails detection with machine learning techniques: [25, 186].”
Machine learning for email spam filtering: review, approaches and open research problems (2019, background): “Phishing corpus 415 0 100 2005 Abu-nimeh et al [40]”
A survey of the applications of text mining in financial domain (2016, methodology): “Abu-Nimeh et al. (2007) compared the performance of CART, LR, Bayesian Additive Regression Trees (BART), SVM, Random Forest (RF), and Neural Networks for phishing emails detection.”
Teaching Johnny not to fall for phish (2010, methodology): “Both blacklist and machine learning techniques can also be used to detect phishing emails [Chandrasekaran et al. 2006; Fette et al. 2006; Abu-Nimeh et al. 2007].”
Beyond blacklists: learning to detect malicious web sites from suspicious URLs (2009, background): “compare different classifiers over a corpus of phishing emails, using as features the frequency of the 43 most-popular words in the corpus [1].”
Phishing Detection: A Literature Survey (2013, methodology): “where λ weights the importance of legitimate instances as used previously in [16].”
Clustering Potential Phishing Websites Using DeepMD5 (2012, methodology): “Other email-based approaches use features derived from the email message such as the sender email, sender IP address, and non-matching URLs between the hyperlink and anchor tag [1].”
An Empirical Analysis of Phishing Blacklists (2009, background): “Recently, some phishing-specific filters were developed as well [1, 11].”
The Case for Learned Index Structures (2017, background): “For example, significant research has worked on using ML to predict if a webpage is a phishing page [10, 15].”
A Hierarchical Adaptive Probabilistic Approach for Zero Hour Phish Detection (2010, methodology): “Abu-Nimeh et al [8] adopted the bag-of-words strategy and used a list of words frequently found on phishing sites as features to detect phish, which is not expressive and easy to defeat by attackers.”