Machine learning and watermarking for accurate detection of AI generated phishing emails.

Brissett, Adrian and Wall, Julie ORCID logoORCID: https://orcid.org/0000-0001-6714-4867 (2025) Machine learning and watermarking for accurate detection of AI generated phishing emails. Electronics, 14 (13). pp. 1-21.

[thumbnail of PDF/A]
Preview
PDF (PDF/A)
Machine Learning and Watermarking for Accurate Detection_WallJ_accessible.pdf - Published Version
Available under License Creative Commons Attribution.

Download (681kB) | Preview

Abstract

Large Language Models offer transformative capabilities but also introduce growing cybersecurity
risks, particularly through their use in generating realistic phishing emails. Detecting such content is critical; however, existing methods can be resource-intensive and slow to adapt. In this research, we present a dual-layered detection framework that combines supervised learning for accurate classification with unsupervised techniques to uncover emerging threats. In controlled testing environments, our approach demonstrates strong performance. Recognising that human users are often the weakest link in information security systems, we examine historical deception patterns and psychological principles commonly exploited in phishing attacks. We also explore watermarking as a complementary method for tracing AI-generated content. Together, these strategies offer a scalable, adaptive defence against increasingly sophisticated phishing attacks driven by Large Language Models.

Item Type: Article
Identifier: 10.3390/electronics14132611
Keywords: phishing detection; large language models; AI-generated content; watermarking; techniques; paraphrasing detection; hybrid detection models
Subjects: Computing
Depositing User: Julie Wall
Date Deposited: 04 Jul 2025 14:02
Last Modified: 04 Jul 2025 14:15
URI: https://repository.uwl.ac.uk/id/eprint/13810

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item

Menu