AI-Driven Phishing Detection Systems

EasyChair Preprint 14338

Abstract

Phishing attacks, which involve fraudulent attempts to obtain sensitive information by masquerading as a trustworthy entity, have become increasingly sophisticated and prevalent. Traditional methods of phishing detection often rely on heuristic or signature-based techniques, which may struggle to keep pace with evolving phishing tactics. This paper explores the application of Artificial Intelligence (AI) in enhancing phishing detection systems. AI-driven approaches leverage machine learning algorithms, natural language processing, and pattern recognition to identify and mitigate phishing threats with greater accuracy and efficiency. By analyzing vast amounts of data, these systems can detect subtle patterns and anomalies indicative of phishing attempts that might elude conventional methods. This abstract discusses the various AI methodologies employed in phishing detection, including supervised and unsupervised learning techniques, ensemble methods, and deep learning models. Additionally, it examines the effectiveness of AI-driven systems in real-world scenarios and their potential to adapt to emerging phishing strategies. The paper concludes with an overview of current challenges and future directions for research in this domain, emphasizing the need for continuous advancement to address the dynamic nature of phishing threats.

Keyphrases: Cyber Security, learning, machine

@booklet{EasyChair:14338,
  author    = {Obaloluwa Ogundairo and Peter Broklyn},
  title     = {AI-Driven Phishing Detection Systems},
  howpublished = {EasyChair Preprint 14338},
  year      = {EasyChair, 2024}}