Enhancing Phishing E-Mail Classifiers: A Lexical URL Analysis Approach

Khonji, Mahmoud; Iraqi, Youssef; Jones, Andrew R.

doi:10.20533/ijisr.2042.4639.2013.0029

Cited by 27 publications

(22 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Table 4 summarizes a set of seven previous related works along with the classification algorithm(s) used and the accuracy of the classification results, the results are visualized in figure 9. The study in [36] used a feature vector of 47 features extracted from the same data sets of Nazario [31]and Spam Assassin corpus [30], using Random Forest algorithm for training the classification model. Their model achieved 0.97 accuracy.…”

Section: Comparative Analysismentioning

confidence: 99%

An Intelligent Classification Model for Phishing Email Detection

Yasin¹,

Abuhasan²

2016

IJNSA

View full text Add to dashboard Cite

Phishing attacks are one of the trending cyber-attacks that apply socially engineered messages that are communicated to people from professional hackers aiming at fooling users to reveal their sensitive information, the most popular communication channel to those messages is through users' emails. This paper presents an intelligent classification model for detecting phishing emails using knowledge discovery, data mining and text processing techniques. This paper introduces the concept of phishing terms weighting which evaluates the weight of phishing terms in each email. The pre-processing phase is enhanced by applying text stemming and WordNet ontology to enrich the model with word synonyms. The model applied the knowledge discovery procedures using five popular classification algorithms and achieved a notable enhancement in classification accuracy; 99.1% accuracy was achieved using the Random Forest algorithm and 98.4% using J48, which is -to our knowledge-the highest accuracy rate for an accredited data set. This paper also presents a comparative study with similar proposed classification techniques.

show abstract

Section: Comparative Analysismentioning

confidence: 99%

An Intelligent Classification Model for Phishing Email Detection

Yasin¹,

Abuhasan²

2016

IJNSA

View full text Add to dashboard Cite

show abstract

“…(Abdelhamid, et al, 2013) (Muhammad, et al, 2013a) (Khonji, et al, 2012) (Bergholz et al, 2010), in the last few years due to its high impact on the online community. Phishing can be defined as an onlinethreat, which involves imitating a legitimate website to acquire sensitive financial information from end-users (Aburrous, et al, 2010).…”

Section: Introductionmentioning

confidence: 99%

An Experimental Study for Assessing Email Classification Attributes Using Feature Selection Methods

Qabajeh

Thabtah

2014

2014 3rd International Conference on Advanced Computer Science Applications and Technologies

View full text Add to dashboard Cite

Email phishing classification is one of the vital problems in the online security research domain that have attracted several scholars due to its impact on the users payments performed daily online. One aspect to reach a good performance by the detection algorithms in the email phishing problem is to identify the minimal set of features that significantly have an impact on raising the phishing detection rate. This paper investigate three known feature selection methods named Information Gain (IG), Chi-square and Correlation Features Set (CFS) on the email phishing problem to separate high influential features from low influential ones in phishing detection. We measure the degree of influentially by applying four data mining algorithms on a large set of features. We compare the accuracy of these algorithms on the complete features set before feature selection has been applied and after feature selection has been applied. After conducting experiments, the results show 12 common significant features have been chosen among the considered features by the feature selection methods. Further, the average detection accuracy derived by the data mining algorithms on the reduced 12features set was very slight affected when compared with the one derived from the 47-features set.

show abstract

“…Khonji et al present a modified variant of a website classification technique to detect phishing URLs in emails. Their previous work lexically analyzes URL tokens to increase prediction accuracy.…”

Section: Related Workmentioning

confidence: 99%

Sniff‐Phish: A novel framework for resource intensive computation in cloud to detect email scam

Kumar¹,

Srinivasagan²,

Ben‐Othman

2019

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Today, the growing significance of digitization across the globe has made the cybersecurity as inevitable. There are many threats in existence to induce harm and to make illegal activities in a device or a network. Email scam or phishing is a technique that most of the hackers use as baits to infiltrate into a system. After a systematic analysis of the infiltration process, a Chrome extension application named Sniff‐Phish is developed, where the resource intensive computational tasks are performed in cloud with which we could be able to detect various categories of real‐time email scams or phishing attacks like zero‐day and spear phishing. This extension application is based upon analyzing some basic criterion of the malicious URL and duly presenting the legitimacy level of the link in the form of a report. The accuracy obtains for Sniff‐Phish is 98% and covers a wide range of phishing websites, resulting in the less false positive rate of 1.2%. Considering the zero‐day and spear phishing detection rate of Sniff‐Phish, the overall experimental results prove that the proposed system outperforms the conventional phishing detection methods.

show abstract

Enhancing Phishing E-Mail Classifiers: A Lexical URL Analysis Approach

Cited by 27 publications

References 14 publications

An Intelligent Classification Model for Phishing Email Detection

An Intelligent Classification Model for Phishing Email Detection

An Experimental Study for Assessing Email Classification Attributes Using Feature Selection Methods

Sniff‐Phish: A novel framework for resource intensive computation in cloud to detect email scam

Contact Info

Product

Resources

About