Regresar

Classification of Phishing Attack Solutions by Employing Deep Learning Techniques: A Systematic Literature Review

Abstract:

Phishing is the technique by which the attacker tries to obtain confidential information from the user, with the purpose of using it fraudulently. These days, three ways to mitigate such attacks stand out: Focus based on awareness, based on blacklists, and based on machine learning (ML). However, in the last days, Deep Learning (DL) has emerged as one of the most efficient techniques of machine learning. Thus, this systematic literature review has been aimed to offer to other researchers, readers and users, an analysis of a variety of proposals of other researchers how to face these attacks, applying Deep Learning algorithms. Some of the contributions of the current study include a synthesis of each selected work and the classification of anti-phishing solutions through its approach, obtaining that the uniform resource locator (URL)-oriented approach is the most used. Furthermore, we have been able to classify the Deep Learning algorithms selected in each solution, which yielded that the most commonly used are the deep neural network (DNN) and convolutional neural network (CNN), among other fundamental data.