The AI Impact in Defense Mechanism of Social Engineering Attacks


DOI: https://doi.org/10.15308/Sinteza-2024-18-24
Authors:
Ivan Prole
Mladen Veinović

Download full paper

Keywords:
Social engineering, AI/ML, Supervised learning, Emotion detection


Abstract:
This research paper explores the use of artificial intelligence in preventing social engineering attacks. Social engineering attacks are a significant cybersecurity threat that exploits individuals' emotions and psychological vulnerabilities. The paper examines various types of social engineering attacks and how AI can assist in thwarting the malicious intentions of attackers. It proposes a method for detecting the emotional state of potential attackers using AI technology. The research aims to identify the emotional state of potential attackers by analyzing their written communication. Identifying a person's emotional state is essential because it can help classify bad intentions and potential attackers, ultimately helping to prevent social engineering attacks. The methods used in this paper employ machine learning algorithms such as XGBoost, Naïve Bayes, KNN, and Random Forest to train the data. The experiment indicates that XGBoost, Naïve Bayes, and Random Forest have better accuracy rates, while KNN has a lower accuracy rate. The research results are based on a dataset. The paper demonstrates how identifying the emotional states of potential attackers can improve social engineering defense.

CITATION:

IEEE format

I. Prole, M. Veinović, “The AI Impact in Defense Mechanism of Social Engineering Attacks,” in Sinteza 2024 - International Scientific Conference on Information Technology, Computer Science, and Data Science, Belgrade, Singidunum University, Serbia, 2024, pp. 18-24. doi:10.15308/Sinteza-2024-18-24

APA format

Prole, I., Veinović, M. (2024). The AI Impact in Defense Mechanism of Social Engineering Attacks. Paper presented at Sinteza 2024 - International Scientific Conference on Information Technology, Computer Science, and Data Science. doi:10.15308/Sinteza-2024-18-24

BibTeX format
Download

RefWorks Tagged format
Download