On a curated 100-email test set, three of four evaluated LLMs detected phishing intent from email text with 88 to 97 percent accuracy and categorized attacks into link, attachment, or service types.
Durumeric *et al.*, ”Neither snow nor rain nor MITM
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LLM-Powered Intent-Based Categorization of Phishing Emails
On a curated 100-email test set, three of four evaluated LLMs detected phishing intent from email text with 88 to 97 percent accuracy and categorized attacks into link, attachment, or service types.