AI-Generated Phishing: Evaluating Whether Traditional Linguistic Indicators Remain Effective in Detecting AI-Enhanced Phishing Attacks

This paper examines whether traditional linguistic indicators, particularly spelling and grammatical errors, remain effective in identifying phishing attacks in an environment increasingly influenced by generative artificial intelligence. The study explores how AI-generated phishing messages can imitate legitimate organizational communications through polished language, accurate grammar, and persuasive wording. It evaluates the limitations of relying on language quality as a standalone detection method and discusses the continuing value of linguistic analysis when combined with contextual, behavioral, and technical indicators. Using a qualitative literature-based approach, the paper examines traditional phishing detection practices, AI-generated social engineering, and emerging approaches to identifying suspicious communications. It also proposes a conceptual multilayered phishing detection framework that integrates linguistic, contextual, identity, technical, and human-review considerations. The paper concludes that effective phishing detection requires organizations to move beyond spelling and grammar checks and assess the sender's identity, message context, requested actions, and associated technical indicators. Research type: Qualitative literature-based analysis. Research status: Independent research paper. The proposed detection framework is conceptual and has not yet been empirically validated.

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-17
DOI
https://doi.org/10.5281/zenodo.24326556
Primary Topic
Spam and Phishing Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

AI-Generated Phishing: Evaluating Whether Traditional Linguistic Indicators Remain Effective in Detecting AI-Enhanced Phishing Attacks

Tinotenda Ngorima
4 links
Zenodo (CERN European Organization for Nuclear Research)
Spam and Phishing Detection
article

AI-Generated Phishing: Evaluating Whether Traditional Linguistic Indicators Remain Effective in Detecting AI-Enhanced Phishing Attacks

Tinotenda Ngorima
article en

Abstract

This paper examines whether traditional linguistic indicators, particularly spelling and grammatical errors, remain effective in identifying phishing attacks in an environment increasingly influenced by generative artificial intelligence. The study explores how AI-generated phishing messages can imitate legitimate organizational communications through polished language, accurate grammar, and persuasive wording. It evaluates the limitations of relying on language quality as a standalone detection method and discusses the continuing value of linguistic analysis when combined with contextual, behavioral, and technical indicators. Using a qualitative literature-based approach, the paper examines traditional phishing detection practices, AI-generated social engineering, and emerging approaches to identifying suspicious communications. It also proposes a conceptual multilayered phishing detection framework that integrates linguistic, contextual, identity, technical, and human-review considerations. The paper concludes that effective phishing detection requires organizations to move beyond spelling and grammar checks and assess the sender's identity, message context, requested actions, and associated technical indicators. Research type: Qualitative literature-based analysis. Research status: Independent research paper. The proposed detection framework is conceptual and has not yet been empirically validated.

Zenodo (CERN European Organization for Nuclear Research)
Spam and Phishing Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon