Intelligent phishing detection and protection scheme for online transactions

Barraclough, Phoebe; Hossain, M. A.; Tahir, Muhammad Atif; Sexton, Graham; Aslam, Nauman

doi:10.1016/j.eswa.2013.02.009

Cited by 84 publications

(65 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Major researches have considered content-based approaches based on machine learning techniques to detect phishing websites [2], [10], [11], [12], [13 [14], [15]. Aburrous proposed a model to identify electronic banking sites [2].…”

Section: A Content-based Through Machine Learning Techniquesmentioning

confidence: 99%

“…In the attempt to improve phishing detection scheme, Barraclough proposed a novel method to detect phishing website [15]. The approach was based on machine Neurofuzzy, using five sets of inputs with 288 features, which offered accuracy results of 98.4%.…”

Section: A Content-based Through Machine Learning Techniquesmentioning

confidence: 99%

“…Data are organized in to 6 sets. In particular, set1 up to set5 which are legitimate site rules, user-behaviour, phishTank, user-specific sites and pop-up windows have been taken from our previous paper [15]. Specifically, Fig.…”

Section: Data Collection and Analysismentioning

confidence: 99%

“…During training, the learning algorithms learn data and use it to create rules. If-Then rules are used because fuzzy rules have been widely utilized successfully in controls and modeling [15]. …”

Section: F Basic Rulesmentioning

confidence: 99%

See 3 more Smart Citations

Parameter optimization for intelligent phishing detection using Adaptive Neuro-Fuzzy

Barraclough

Sexton

Aslam

2014

ijarai

Self Cite

View full text Add to dashboard Cite

Abstract-Phishing attacks has been growing rapidly in the past few years. As a result, a number of approaches have been proposed to address the problem. Despite various approaches proposed such as feature-based and blacklist-based via machine learning techniques, there is still a lack of accuracy and real-time solution. Most approaches applying machine learning techniques requires that parameters are tuned to solve a problem, but parameters are difficult to tune to a desirable output. This study presents a parameter tuning framework, using adaptive Neuronfuzzy inference system with comprehensive data to maximize systems performance. Extensive experiment was conducted. During ten-fold cross-validation, the data is split into training and testing pairs and parameters are set according to desirable output and have achieved 98.74% accuracy. Our results demonstrated higher performance compared to other results in the field. This paper contributes new comprehensive data, novel parameter tuning method and applied a new algorithm in a new field. The implication is that adaptive neuron-fuzzy system with effective data and proper parameter tuning can enhance system performance. The outcome will provide a new knowledge in the field.

show abstract

Section: A Content-based Through Machine Learning Techniquesmentioning

confidence: 99%

Section: A Content-based Through Machine Learning Techniquesmentioning

confidence: 99%

Section: Data Collection and Analysismentioning

confidence: 99%

Section: F Basic Rulesmentioning

confidence: 99%

See 2 more Smart Citations

Parameter optimization for intelligent phishing detection using Adaptive Neuro-Fuzzy

Barraclough

Sexton

Aslam

2014

ijarai

Self Cite

View full text Add to dashboard Cite

show abstract

“…Barraclough et al [7] utilized a Neuro-Fuzzy scheme with five inputs (Legitimate site rules, User-behavior profile, PhishTank, User-specific sites, Pop-Ups from emails) to detect phishing websites with high accuracy in real-time. Mohammad et al [9] suggested rule-based data mining classification techniques with 17 different features to distinguish phishing from legitimate websites.…”

Section: Introductionmentioning

confidence: 99%

Phishing Website Detection based on Supervised Machine Learning with Wrapper Features Selection

Ali¹

2017

ijacsa

View full text Add to dashboard Cite

Abstract-The problem of Web phishing attacks has grown considerably in recent years and phishing is considered as one of the most dangerous Web crimes, which may cause tremendous and negative effects on online business. In a Web phishing attack, the phisher creates a forged or phishing website to deceive Web users in order to obtain their sensitive financial and personal information. Several conventional techniques for detecting phishing website have been suggested to cope with this problem. However, detecting phishing websites is a challenging task, as most of these techniques are not able to make an accurate decision dynamically as to whether the new website is phishing or legitimate. This paper presents a methodology for phishing website detection based on machine learning classifiers with a wrapper features selection method. In this paper, some common supervised machine learning techniques are applied with effective and significant features selected using the wrapper features selection approach to accurately detect phishing websites. The experimental results demonstrated that the performance of the machine learning classifiers was improved by using the wrapper-based features selection. Moreover, the machine learning classifiers with the wrapper-based features selection outperformed the machine learning classifiers with other features selection methods.

show abstract