Hybrid intelligent phishing website prediction using deep neural networks with genetic algorithm‐based feature selection and weighting

Ali, Waleed; Ahmed, Adel Ali

doi:10.1049/iet-ifs.2019.0006

Cited by 78 publications

(48 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most common methods for efficient processing of voluminous datasets are feature weighting and feature selection techniques. While feature selection algorithms refer to algorithms that select the best subset which retain the interpretation of the large original data, feature weighting models operate based on the ideology that data features vary in their importance and each feature's contribution to the classification task should be different [ 33 , 34 ]. Thus, higher weights are allocated to relevant features and lesser weights are allocated to the less relevant ones [ 35 ].…”

Section: Methodsmentioning

confidence: 99%

“…Inspired by Charles Darwin's theory of genetics, GA are powerful tools that are well known for their strong global search ability in finding solutions to non-deterministic polynomial-time hardness problems. They have been extensively combined with various ML models as a feature weighting tool and parameter optimization technique in several classification tasks [ 33 , 35 , 36 ]. The basic step of a GA process is stated briefly as follows: Creating population chromosome.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Power system events classification using genetic algorithm based feature weighting technique for support vector machine

Alimi

Ouahada

Abu‐Mahfouz

et al. 2021

Heliyon

View full text Add to dashboard Cite

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Power system events classification using genetic algorithm based feature weighting technique for support vector machine

Alimi

Ouahada

Abu‐Mahfouz

et al. 2021

Heliyon

View full text Add to dashboard Cite

“…However, the wrapper-based feature selection depends on the machine learning algorithm itself and may be computationally expensive. Recently, genetic algorithm-based feature selection was used in [29] to find more relevant features in order to enhance the detection accuracy of the machine learning model in phishing websites detection. Although the machine learning techniques with applying GA-based feature selection performed better detection accuracy compared to the same machine learning techniques with other feature selection methods, GA-based feature selection required a longer time for some machine learning algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…In this section, we compare the performances of machine learning models improved by the proposed PSO-based feature weighting against these models that applied other feature selection methods used in the phishing website detection such as Chi-square and Information Gain (IG) [7], [8], [30], Wrapper-based feature selection [10], GA-based features selection [29], and GA-based features weighting [29].…”

Section: E Comparison Of the Proposed Pso-based Feature Weighting Agmentioning

confidence: 99%

“…Thus, some machine learning algorithms with considering filter-based feature selection methods achieved better detection accuracy, while others produced similar or slightly worse detection accuracy of phishing websites. In recent years, feature selection methods based on wrapper approach [10] and genetic algorithm (GA) [29] have been used to obtain the most influential website features to achieve higher detection accuracy of the phishing websites. Although the wrapper and GA based feature selection methods achieved better detection accuracy and outperformed other feature selection methods, they were time-consuming for some machine learning algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Particle Swarm Optimization-Based Feature Weighting for Improving Intelligent Phishing Website Detection

Ali

Malebary

2020

IEEE Access

Self Cite

View full text Add to dashboard Cite

Over the last few years, web phishing attacks have been constantly evolving causing customers to lose trust in e-commerce and online services. Various tools and systems based on a blacklist of phishing websites are applied to detect the phishing websites. Unfortunately, the fast evolution of technology has led to the born of more sophisticated methods when building websites to attract users. Thus, the latest and newly deployed phishing websites; for example, zero-day phishing websites, cannot be detected by using these blacklist-based approaches. Several recent research studies have been adopting machine learning techniques to identify phishing websites and utilizing them as an early alarm method to identify such threats. However, the important website features have been selected based on human experience or frequency analysis of website features in most of these approaches. In this paper, intelligent phishing website detection using particle swarm optimization-based feature weighting is proposed to enhance the detection of phishing websites. The proposed approach suggests utilizing particle swarm optimization (PSO) to weight various website features effectively to achieve higher accuracy when detecting phishing websites. In particular, the proposed PSO-based website feature weighting is used to differentiate between the various features in websites, based on how important they contribute towards recognizing the phishing from legitimate websites. The experimental results indicated that the proposed PSO-based feature weighting achieved outstanding improvements in terms of classification accuracy, true positive and negative rates, and false positive and negative rates of the machine learning models using only fewer websites features utilized in the detection of phishing websites.

show abstract

Phishing website detection: How effective are deep learning‐based models and hyperparameter optimization?

Almousa

Zhang

Sarrafzadeh

et al. 2022

Security and Privacy

View full text Add to dashboard Cite

Phishing websites are fraudulent websites that appear legitimate and trick unsuspecting users into interacting with them, stealing their valuable information. Because phishing attacks are a leading cause of data breach, different anti-phishing solutions have been explored for cybersecurity management including machine learning-based technical approaches. However, there is a gap in understanding how robust deep learning-based models together with hyperparameter optimization are for phishing website detection. In this vein, this study pursues the tasks of developing parsimonious deep learning models and hyperparameter optimization to achieve high accuracy and reproducible results for phishing website detection. This paper demonstrates a systematic process of building detection models based on three deep learning algorithm architectures (Long Short-Term Memory-based detection models, Fully Connected Deep Neural Network-based detection models, and convolutional neural network-based detection models) that are built and evaluated using four publicly available phishing website datasets, achieving the best accuracy of 97.37%. We also compared two different optimization algorithms for hyperparameter optimization:

show abstract

Hybrid intelligent phishing website prediction using deep neural networks with genetic algorithm‐based feature selection and weighting

Cited by 78 publications

References 42 publications

Power system events classification using genetic algorithm based feature weighting technique for support vector machine

Power system events classification using genetic algorithm based feature weighting technique for support vector machine

Particle Swarm Optimization-Based Feature Weighting for Improving Intelligent Phishing Website Detection

Phishing website detection: How effective are deep learning‐based models and hyperparameter optimization?

Contact Info

Product

Resources

About