A Systematic Literature Review on Phishing Email Detection Using Natural Language Processing Techniques

Salloum, Said A.; Gaber, Tarek; Vadera, Sunil; Shaalan, Khaled

doi:10.1109/access.2022.3183083

Cited by 65 publications

(21 citation statements)

References 152 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[7] describes common phishing attack vectors, data sources, and identi cation methods used to mitigate phishing attacks and [8] delves into the technical and individual attributes of phishing attacks, motivations behind them, and user characteristics. Authors [9] review deep learning algorithms for phishing mitigation, while [10] presents a literature review of phishing and antiphishing techniques, [11] and [12] focus on using natural language processing (NLP) techniques for detecting phishing emails and websites, respectively.…”

Section: Literature Reviewmentioning

confidence: 99%

A Machine Learning Model for Predicting Phishing Websites

Boussi,

Gupta,

Hossain

2023

Preprint

View full text Add to dashboard Cite

There are various types of cybercrime, and hackers often target specific ones for different reasons, such as financial gain, recognition, or even revenge. Cybercrimes can occur anywhere in the world, as the location of both the victim and the criminal is not a limiting factor. Different countries may have different common types of cybercrime, influenced by factors such as the country's economic situation, level of internet activity, and overall development. Phishing is a prevalent type of cybercrime in the financial sector, regardless of the country's circumstances. While the phishing techniques used in developed countries may differ from those in developing countries, the impact remains the same, resulting in financial losses. In our work, a dataset consisting of 48 features extracted from 5,000 phishing webpages and 5,000 legitimate webpages was used to predict whether a website is phishing or not, achieving an accuracy of 98%.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

A Machine Learning Model for Predicting Phishing Websites

Boussi,

Gupta,

Hossain

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Despite this high number, it is challenging, if not impossible, to compare the results of one study with another. There are various reasons, but the main ones observed are the insufficient level of detail about the source of data (many times, the details about gathering the legitimate records are insufficient or missing) used by these studies or the lack of details related to data transformation and cleansing before using machine learning techniques [12]. Studies often overlook the importance of describing the data collection process and the adjustments performed, which are crucial to validate or compare the results between various researchers.…”

Section: Introductionmentioning

confidence: 99%

A Framework for Preparing a Balanced and Comprehensive Phishing Dataset

Skula,

Kvet

2024

IEEE Access

View full text Add to dashboard Cite

It is not uncommon for people to face phishing attempts on a daily basis, usually via email containing a malicious URL pointing towards a phishing landing page. Over recent years, numerous studies have been conducted using machine learning techniques to detect phishing webpages. These techniques require real-world data from which they extract the underlying distinctive patterns not easily visible to a human. Capturing and collating such data plays a fundamental role in the overall process. Supervised machine learning algorithms rely on accurate and balanced data for training. Despite the proliferation of research in this field, comparing different studies is a common challenge due to varying data sources, transformations and data cleansing techniques applied when preparing the training dataset. This paper presents a framework for creating a comprehensive and balanced dataset for training machine learning models detecting phishing webpages. The framework covers the process of identifying and gathering the data -phishing and legitimate, data cleansing and highlights important considerations related to the structural composition of the final dataset, like the ratio between phishing and legitimate records or optimal dataset size. Though there is no universal way of preparing a balanced and efficient dataset, the proposed framework provides comprehensive guidelines for constructing one, addressing aspects specific to phishing detection. The practical benefits of applying the framework are accurate, non-skewed, and balanced data, which lead to an accurate model and transparency of data transformation, enabling comparability of the results between different studies.

show abstract

“…Studying and comparing the current state-of-art data preprocessing methods is very important due to the disparity in the model's performance with each method. Table 1 also shows a few papers that investigate the unsupervised learning models [25], [27]. In [27], the authors only study one type of unsupervised learning, such as k-means clustering.…”

Section: Introductionmentioning

confidence: 99%

“…Table 1 also shows a few papers that investigate the unsupervised learning models [25], [27]. In [27], the authors only study one type of unsupervised learning, such as k-means clustering. The authors in [25] study multiple unsupervised learning models.…”

Section: Introductionmentioning

confidence: 99%

A Survey of Intelligent Detection Designs of HTML URL Phishing Attacks

et al. 2023

View full text Add to dashboard Cite

Phishing attacks are a type of cybercrime that has grown in recent years. It is part of social engineering attacks where an attacker deceives users by sending fake messages using social media platforms or emails. Phishing attacks steal users' information or download and install malicious software. They are hard to detect because attackers can design a phishing message that looks legitimate to a user. This message may contain a phishing URL so that even an expert can be a victim. This URL leads the victim to a fake website that steals information, such as login information, payment information, etc. Researchers and engineers work to develop methods to detect phishing attacks without the need for the eyes of experts. Even though many papers discuss HTML and URL-based phishing detection methods, there is no comprehensive survey to discuss these methods. Therefore, this paper comprehensively surveys HTML and URL phishing attacks and detection methods. We review the current state-of-art deep learning models to detect URL-based and hybrid-based phishing attacks in detail. We compare each model based on its data preprocessing, feature extraction, model design, and performance.

show abstract

A Systematic Literature Review on Phishing Email Detection Using Natural Language Processing Techniques

Cited by 65 publications

References 152 publications

A Machine Learning Model for Predicting Phishing Websites

A Machine Learning Model for Predicting Phishing Websites

A Framework for Preparing a Balanced and Comprehensive Phishing Dataset

A Survey of Intelligent Detection Designs of HTML URL Phishing Attacks

Contact Info

Product

Resources

About