Phishing Attacks and Websites Classification Using Machine Learning and Multiple Datasets (A Comparative Analysis)

Khan, Sohail Ahmed; Khan, Wasiq; Hussain, Abir Jaafar

doi:10.1007/978-3-030-60796-8_26

Cited by 21 publications

(11 citation statements)

References 23 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The evaluation metrics were accuracy, precision, and recall. The results show that the proposed optimized stacking ensemble method outperformed the other recent and related works [7,10] in using the accuracy and recall performance measures for Dataset 1, and outperformed [35] in using the accuracy, precision and recall measures for for Dataset 2.…”

Section: Statistical Analysis and Comparison With Previous Studiesmentioning

confidence: 76%

An Optimized Stacking Ensemble Model for Phishing Websites Detection

et al. 2021

View full text Add to dashboard Cite

Security attacks on legitimate websites to steal users’ information, known as phishing attacks, have been increasing. This kind of attack does not just affect individuals’ or organisations’ websites. Although several detection methods for phishing websites have been proposed using machine learning, deep learning, and other approaches, their detection accuracy still needs to be enhanced. This paper proposes an optimized stacking ensemble method for phishing website detection. The optimisation was carried out using a genetic algorithm (GA) to tune the parameters of several ensemble machine learning methods, including random forests, AdaBoost, XGBoost, Bagging, GradientBoost, and LightGBM. The optimized classifiers were then ranked, and the best three models were chosen as base classifiers of a stacking ensemble method. The experiments were conducted on three phishing website datasets that consisted of both phishing websites and legitimate websites—the Phishing Websites Data Set from UCI (Dataset 1); Phishing Dataset for Machine Learning from Mendeley (Dataset 2, and Datasets for Phishing Websites Detection from Mendeley (Dataset 3). The experimental results showed an improvement using the optimized stacking ensemble method, where the detection accuracy reached 97.16%, 98.58%, and 97.39% for Dataset 1, Dataset 2, and Dataset 3, respectively.

show abstract

Section: Statistical Analysis and Comparison With Previous Studiesmentioning

confidence: 76%

An Optimized Stacking Ensemble Model for Phishing Websites Detection

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Refs. [8,17] utilize the Tan's dataset [15] with similar proportion of training and testing at 70% and 30%.…”

Section: Discussionmentioning

confidence: 99%

“…This study utilized two public datasets; Tan's [15] for the first dataset and Hannousse and Yahiouche [16] for the second dataset. We use this dataset because some studies on similar topics use it, such as Chiew et al [8] on 2019, Khan et al [17] on 2020, Dangwal and Moldova [18] on 2021, Al-Sareem et al [19] on 2021, and Haynes et al [20] on 2021.The first dataset selected phishing websites with the PhishTank and OpenPhish URLs and legitimate websites with the Alexa and General Archives URLs. For building the dataset, Tan gathered webpages in two different sessions between January and May and the other session in May and June for two years.…”

Section: Datamentioning

confidence: 99%

CCrFS: Combine Correlation Features Selection for Detecting Phishing Websites Using Machine Learning

Moedjahedy

Setyanto²,

Alarfaj

et al. 2022

Future Internet

View full text Add to dashboard Cite

Internet users are continually exposed to phishing as cybercrime in the 21st century. The objective of phishing is to obtain sensitive information by deceiving a target and using the information for financial gain. The information may include a login detail, password, date of birth, credit card number, bank account number, and family-related information. To acquire these details, users will be directed to fill out the information on false websites based on information from emails, adverts, text messages, or website pop-ups. Examining the website’s URL address is one method for avoiding this type of deception. Identifying the features of a phishing website URL takes specialized knowledge and investigation. Machine learning is one method that uses existing data to teach machines to distinguish between legal and phishing website URLs. In this work, we proposed a method that combines correlation and recursive feature elimination to determine which URL characteristics are useful for identifying phishing websites by gradually decreasing the number of features while maintaining accuracy value. In this paper, we use two datasets that contain 48 and 87 features. The first scenario combines power predictive score correlation and recursive feature elimination; the second scenario is the maximal information coefficient correlation and recursive feature elimination. The third scenario combines spearman correlation and recursive feature elimination. All three scenarios from the combined findings of the proposed methodologies achieve a high level of accuracy even with the smallest feature subset. For dataset 1, the accuracy value for the 10 features result is 97.06%, and for dataset 2 the accuracy value is 95.88% for 10 features.

show abstract

“…Phishing, and its variations such as vishing and smishing, are fraud attacks in which the target is contacted by the conman via some means of communication, such as email, voice phone calls, or SMS. The attackers represent themselves as a reputable entity in order to gain trust or induce some sort of reaction in the target to make them give up sensitive information, such as passwords or banking information about themselves [45]. Phishing is a common way to gain access to a target system, and protecting against it can be so resource-heavy that affects day-to-day proceedings.…”

Section: Reconnaissancementioning

confidence: 99%

“…Attackers can benefit from defensive research as well, because ML for detection avoidance is one of the key features of a good and successful phishing campaign. Some efforts, such as that of Khan et al [45], experiment with a variety of algorithms and datasets, exposing strengths and weaknesses in them. Thus, this information can be used to further evolve and improve the phishing campaigns as well as the detection algorithms.…”

Section: Reconnaissancementioning

confidence: 99%

Offensive Machine Learning Methods and the Cyber Kill Chain

Turtiainen

Costin

Polyakov³

et al. 2022

Artificial Intelligence and Cybersecurity

View full text Add to dashboard Cite

Cyberattacks are the "new normal" in the hyper-connected and all-digitized modern world, as breaches, denial-of-service, ransomware, and a myriad of other attacks occur every single day. As the attacks and breaches increase in complexity, diversity, and frequency, cybersecurity actors (both ethical and cybercrime) turn to automating these attacks in various ways and for a variety of reasons, including the development of effective and superior cybersecurity defenses. In this chapter, we address innovations in machine learning, deep learning, and artificial intelligence within the offensive cybersecurity fields. We structure this chapter inline with the Lockheed Martin's Cyber Kill Chain taxonomy in order to cover adequate grounds on this broad topic, and occasionally refer to the more granular MITRE ATT&CK taxonomy whenever relevant.

show abstract

Phishing Attacks and Websites Classification Using Machine Learning and Multiple Datasets (A Comparative Analysis)

Cited by 21 publications

References 23 publications

An Optimized Stacking Ensemble Model for Phishing Websites Detection

An Optimized Stacking Ensemble Model for Phishing Websites Detection

CCrFS: Combine Correlation Features Selection for Detecting Phishing Websites Using Machine Learning

Offensive Machine Learning Methods and the Cyber Kill Chain

Contact Info

Product

Resources

About