An anti-phishing method based on feature analysis

Rajab, Majed

doi:10.1145/3184066.3184082

Cited by 11 publications

(19 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…CFS sorts features based on their correlation with the target class. The first-ranked feature has highest correlation with the target class and lowest correlation with the others [13]. DW utilizes a combination of decision tree and Wrapper to select an optimal feature set [14].…”

Section: Methodsmentioning

confidence: 99%

“…Furthermore, DW is dependent on the expert opinion to decide what decreasing in the accuracy should be considered as significant to stop the method. In this work, the thresholds and other settings are set based on the values suggested in [13] and [14]. Figure 2 presents the F-measure values for classifiers using four feature selection algorithms over each data set.…”

Section: Methodsmentioning

confidence: 99%

“…Although all the above-mentioned studies have suggested different features to detect phishing websites, some features may not be sufficiently discerning to highlight phishing instances [13]. Only a limited number of work has focused on selecting the most effective features to detect phishing websites.…”

Section: Related Workmentioning

confidence: 99%

“…This training set which is composed by random extraction of websites from an online repository [16] contains 7,000 legitimate and 7,000 phishing website samples. The benefit of using FRS for feature selection is realized by comparing our results against three recently proposed algorithms [13], [14].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection

Zabihimayvan

Doran

2019

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

Phishing as one of the most well-known cybercrime activities is a deception of online users to steal their personal or confidential information by impersonating a legitimate website. Several machine learning-based strategies have been proposed to detect phishing websites. These techniques are dependent on the features extracted from the website samples. However, few studies have actually considered efficient feature selection for detecting phishing attacks. In this work, we investigate an agreement on the definitive features which should be used in phishing detection. We apply Fuzzy Rough Set (FRS) theory as a tool to select most effective features from three benchmarked data sets. The selected features are fed into three often used classifiers for phishing detection. To evaluate the FRS feature selection in developing a generalizable phishing detection, the classifiers are trained by a separate out-of-sample data set of 14,000 website samples. The maximum F-measure gained by FRS feature selection is 95% using Random Forest classification. Also, there are 9 universal features selected by FRS over all the three data sets. The F-measure value using this universal feature set is approximately 93% which is a comparable result in contrast to the FRS performance. Since the universal feature set contains no features from third-part services, this finding implies that with no inquiry from external sources, we can gain a faster phishing detection which is also robust toward zero-day attacks.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection

Zabihimayvan

Doran

2019

2019 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

show abstract

“…The best way to solve phishing is design strict user education programs that not only assist users recognize fraudulent email, but also provide particular advice on how to manage suspicious communication (Rajab, 2018). In the parts below, it will concentrate on safe handling of email that violate the software layer's safety.…”

Section: Prevention Techniques From Phishing Attackmentioning

confidence: 99%

Anti-Phishing With Google Extension 3h1m Using Blacklist Algorithm

Ramli

Faugi

Faizal³

et al. 2020

MJoC

View full text Add to dashboard Cite

The advancement of technologies has rapidly risen for the past few years, which brings a lot of benefits especially to the users. However, the developments have also contributed many security issues, where security attacks have also become more advanced. Phishing is one of the security attacks that describe spoof emails or websites to trick users into exposing their personal or any confidential information. Hence, this project develops a solution, 3H1M extension, to help in mitigating the phishing issues when browsing the Internet. This extension will compare the visited website URL with the blacklisted website lists in the database to identify the validity of the website. If the user is visiting a malicious website, a pop-up message will be displayed on the screen and the user will be directed to the search engine page. A comparison is made between a web browser implemented with and without the 3H1M extension. It can be observed that the extension is able to help the users to distinguish between the real and malicious websites.

show abstract

A Comparison of Performance of Rough Set Theory with Machine Learning Techniques in Detecting Phishing Attack

Singh

Misra²

2022

Advances in Computing, Informatics, Networking and Cybersecurity

View full text Add to dashboard Cite

An anti-phishing method based on feature analysis

Cited by 11 publications

References 17 publications

Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection

Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection

Anti-Phishing With Google Extension 3h1m Using Blacklist Algorithm

A Comparison of Performance of Rough Set Theory with Machine Learning Techniques in Detecting Phishing Attack

Contact Info

Product

Resources

About