Figure - uploaded by Michael Koddebusch
Content may be subject to copyright.
![Click rates by Phase and Persuasion Technique [Phase 1]](profile/Michael-Koddebusch/publication/363570852/figure/tbl1/AS:11431281233844231@1712148718462/Click-rates-by-Phase-and-Persuasion-Technique-Phase-1_Q320.jpg)
Similar publications
Przedmiot badań: W artykule przybliżono najbardziej doniosłe zagadnienia związane z pełnym stosowaniem pakietu regulacyjnego PSD2 w obrębie rynku usług płatniczych. Zobrazowano zarówno obecny stan krajowego rynku, jak i perspektywy jego rozwoju. Całość zestawiono z nadchodzącymi zmianami w sektorze bankowym oraz podjęto próbę oszacowania kluczowy...
In recent years, customer churn has been one of the most prominent topics, especially in the telecom industry. The telecommunications industry is producing massive amounts of data every minute. Thus, the telecom industry is seeking more ways to analyze and predict their potential and churn customers. According to telecom analysis, acquiring a new c...
The rapid evolution of artificial intelligence (AI) has introduced new challenges in the realm of financial security, particularly with the advent of deepfake technology. AI-generated content, such as hyper-realistic fake videos, images, and audio, has emerged as a potent tool for facilitating financial crimes, identity theft, and fraud. This paper...
Phishing is the most prevalent cybercrime that
involves deceptive email. It is how fraudsters get
victims to reveal their personal information by
pretending to be a bank or government organisation.
Modern business and personal communication use
email. Emails often contain sensitive information from
identifying documents, including bank accoun...
Citations
Persuasion is a human activity of influence. In marketing, persuasion can help customers find solutions to their problems, make informed choices, or convince someone to buy a useful (or useless) product or service. In computer crimes, persuasion can trick users into revealing sensitive information, or even performing actions that benefit attackers. Phishing is one of the most common and dangerous forms of persuasion-based attacks, as it exploits human vulnerabilities rather than technical ones. Therefore, an intelligent system capable of detecting and classifying persuasion attempts might be useful in protecting users. In this work, an approach that uses Machine Learning to analyze messages based on principles of persuasion and different data representations is presented. The aim of this research is to detect which data representation and which classification algorithm obtain the best results in detecting each principle of persuasion as a prior step to detecting phishing attacks. The results obtained indicate that among the combinations tested, there is one combination of data representation and classification algorithm that performs best. The related classification models obtained can detect the principles of persuasion at a rate that varies between 0.78 and 0.86 of AUC-ROC.
Social Engineering (SE) is a major threat to cybersecurity and seeks to manipulate a target to divulge information or take an action that may or may not be in their best interest. One of the ways social engineers manipulate their targets to perform an action is by utilizing persuasion techniques that prey on qualities of human nature. In this paper, a comprehensive literature review was conducted to analyze current computational approaches to persuasion detection and identify what approaches may address their limitations in the SE context. We found that persuasion detection has so far been studied in different contexts: argumentative discourse, recommendation systems, propaganda, and SE. We review a total of thirteen approaches, discuss their advantages and disadvantages and surmise approaches that may be feasible to address the gaps identified based on current advancements in the field. We also observe that currently, only a few approaches to persuasion detection in SE exist and typically rely on basic feature engineering. The reviewed approaches in other domains, however, demonstrate the potential of deep learning to capture the essence of persuasion.
